| <!DOCTYPE html> |
| |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta charset="utf-8" /> |
| <meta charset="utf-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> |
| <meta http-equiv="x-ua-compatible" content="ie=edge"> |
| <style> |
| .dropdown { |
| position: relative; |
| display: inline-block; |
| } |
| |
| .dropdown-content { |
| display: none; |
| position: absolute; |
| background-color: #f9f9f9; |
| min-width: 160px; |
| box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2); |
| padding: 12px 16px; |
| z-index: 1; |
| text-align: left; |
| } |
| |
| .dropdown:hover .dropdown-content { |
| display: block; |
| } |
| |
| .dropdown-option:hover { |
| color: #FF4500; |
| } |
| |
| .dropdown-option-active { |
| color: #FF4500; |
| font-weight: lighter; |
| } |
| |
| .dropdown-option { |
| color: #000000; |
| font-weight: lighter; |
| } |
| |
| .dropdown-header { |
| color: #FFFFFF; |
| display: inline-flex; |
| } |
| |
| .dropdown-caret { |
| width: 18px; |
| } |
| |
| .dropdown-caret-path { |
| fill: #FFFFFF; |
| } |
| </style> |
| |
| <title>mxnet.image — Apache MXNet documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/mxnet.css" /> |
| <link rel="stylesheet" href="../../../_static/material-design-lite-1.3.0/material.blue-deep_orange.min.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/sphinx_materialdesign_theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fontawesome/all.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fonts.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/feedback.css" type="text/css" /> |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/matomo_analytics.js"></script> |
| <script src="../../../_static/autodoc.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="shortcut icon" href="../../../_static/mxnet-icon.png"/> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <link rel="next" title="mxnet.io" href="../io/index.html" /> |
| <link rel="prev" title="mxnet.executor_manager" href="../executor_manager/index.html" /> |
| </head> |
| <body><header class="site-header" role="banner"> |
| <div class="wrapper"> |
| <a class="site-title" rel="author" href="/versions/1.9.1/"><img |
| src="../../../_static/mxnet_logo.png" class="site-header-logo"></a> |
| <nav class="site-nav"> |
| <input type="checkbox" id="nav-trigger" class="nav-trigger"/> |
| <label for="nav-trigger"> |
| <span class="menu-icon"> |
| <svg viewBox="0 0 18 15" width="18px" height="15px"> |
| <path d="M18,1.484c0,0.82-0.665,1.484-1.484,1.484H1.484C0.665,2.969,0,2.304,0,1.484l0,0C0,0.665,0.665,0,1.484,0 h15.032C17.335,0,18,0.665,18,1.484L18,1.484z M18,7.516C18,8.335,17.335,9,16.516,9H1.484C0.665,9,0,8.335,0,7.516l0,0 c0-0.82,0.665-1.484,1.484-1.484h15.032C17.335,6.031,18,6.696,18,7.516L18,7.516z M18,13.516C18,14.335,17.335,15,16.516,15H1.484 C0.665,15,0,14.335,0,13.516l0,0c0-0.82,0.665-1.483,1.484-1.483h15.032C17.335,12.031,18,12.695,18,13.516L18,13.516z"/> |
| </svg> |
| </span> |
| </label> |
| |
| <div class="trigger"> |
| <a class="page-link" href="/versions/1.9.1/get_started">Get Started</a> |
| <a class="page-link" href="/versions/1.9.1/features">Features</a> |
| <a class="page-link" href="/versions/1.9.1/ecosystem">Ecosystem</a> |
| <a class="page-link page-current" href="/versions/1.9.1/api">Docs & Tutorials</a> |
| <a class="page-link" href="/versions/1.9.1/trusted_by">Trusted By</a> |
| <a class="page-link" href="https://github.com/apache/incubator-mxnet">GitHub</a> |
| <div class="dropdown" style="min-width:100px"> |
| <span class="dropdown-header">Apache |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content" style="min-width:250px"> |
| <a href="https://www.apache.org/foundation/">Apache Software Foundation</a> |
| <a href="https://incubator.apache.org/">Apache Incubator</a> |
| <a href="https://www.apache.org/licenses/">License</a> |
| <a href="/versions/1.9.1/api/faq/security.html">Security</a> |
| <a href="https://privacy.apache.org/policies/privacy-policy-public.html">Privacy</a> |
| <a href="https://www.apache.org/events/current-event">Events</a> |
| <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a> |
| <a href="https://www.apache.org/foundation/thanks.html">Thanks</a> |
| </div> |
| </div> |
| <div class="dropdown"> |
| <span class="dropdown-header">1.9.1 |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content"> |
| <a class="dropdown-option" href="/">master</a><br> |
| <a class="dropdown-option-active" href="/versions/1.9.1/">1.9.1</a><br> |
| <a class="dropdown-option" href="/versions/1.8.0/">1.8.0</a><br> |
| <a class="dropdown-option" href="/versions/1.7.0/">1.7.0</a><br> |
| <a class="dropdown-option" href="/versions/1.6.0/">1.6.0</a><br> |
| <a class="dropdown-option" href="/versions/1.5.0/">1.5.0</a><br> |
| <a class="dropdown-option" href="/versions/1.4.1/">1.4.1</a><br> |
| <a class="dropdown-option" href="/versions/1.3.1/">1.3.1</a><br> |
| <a class="dropdown-option" href="/versions/1.2.1/">1.2.1</a><br> |
| <a class="dropdown-option" href="/versions/1.1.0/">1.1.0</a><br> |
| <a class="dropdown-option" href="/versions/1.0.0/">1.0.0</a><br> |
| <a class="dropdown-option" href="/versions/0.12.1/">0.12.1</a><br> |
| <a class="dropdown-option" href="/versions/0.11.0/">0.11.0</a> |
| </div> |
| </div> |
| </div> |
| </nav> |
| </div> |
| </header> |
| <div class="mdl-layout mdl-js-layout mdl-layout--fixed-header mdl-layout--fixed-drawer"><header class="mdl-layout__header mdl-layout__header--waterfall "> |
| <div class="mdl-layout__header-row"> |
| |
| <nav class="mdl-navigation breadcrumb"> |
| <a class="mdl-navigation__link" href="../../index.html">Python API</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link" href="../index.html">mxnet</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link is-active">mxnet.image</a> |
| </nav> |
| <div class="mdl-layout-spacer"></div> |
| <nav class="mdl-navigation"> |
| |
| <form class="form-inline pull-sm-right" action="../../../search.html" method="get"> |
| <div class="mdl-textfield mdl-js-textfield mdl-textfield--expandable mdl-textfield--floating-label mdl-textfield--align-right"> |
| <label id="quick-search-icon" class="mdl-button mdl-js-button mdl-button--icon" for="waterfall-exp"> |
| <i class="material-icons">search</i> |
| </label> |
| <div class="mdl-textfield__expandable-holder"> |
| <input class="mdl-textfield__input" type="text" name="q" id="waterfall-exp" placeholder="Search" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </div> |
| </div> |
| <div class="mdl-tooltip" data-mdl-for="quick-search-icon"> |
| Quick search |
| </div> |
| </form> |
| |
| <a id="button-show-source" |
| class="mdl-button mdl-js-button mdl-button--icon" |
| href="../../../_sources/api/mxnet/image/index.rst" rel="nofollow"> |
| <i class="material-icons">code</i> |
| </a> |
| <div class="mdl-tooltip" data-mdl-for="button-show-source"> |
| Show Source |
| </div> |
| </nav> |
| </div> |
| <div class="mdl-layout__header-row header-links"> |
| <div class="mdl-layout-spacer"></div> |
| <nav class="mdl-navigation"> |
| </nav> |
| </div> |
| </header><header class="mdl-layout__drawer"> |
| |
| <div class="globaltoc"> |
| <span class="mdl-layout-title toc">Table Of Contents</span> |
| |
| |
| |
| <nav class="mdl-navigation"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Python Tutorials</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/getting-started/index.html">Getting Started</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/index.html">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-ndarray.html">Manipulate data with <code class="docutils literal notranslate"><span class="pre">ndarray</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-nn.html">Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Automatic differentiation with <code class="docutils literal notranslate"><span class="pre">autograd</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-train.html">Train the neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-predict.html">Predict with a pre-trained model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-use_gpus.html">Use GPUs</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom_layer_beginners.html">Customer Layers (Beginners)</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/image-augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/pretrained_models.html">Using pre-trained models in MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/train.html">Train a Linear Regression Model with Sparse Symbols</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/super_resolution.html">Importing an ONNX model into MXNet</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/index.html">Intel MKL-DNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html">Quantize with MKL-DNN backend</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html#Improving-accuracy-with-Intel®-Neural-Compressor">Improving accuracy with Intel® Neural Compressor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/tensorrt.html">Optimizing Deep Learning Computation Graphs with TensorRT</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/scala.html">Deploy into a Java or Scala Environment</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/wine_detector.html">Real-time Object Detection with MXNet On The Raspberry Pi</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/custom_layer.html">Custom Layers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Python API</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../../ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../gluon/index.html">mxnet.gluon</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/parameter_dict.html">gluon.ParameterDict</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../gluon/data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../gluon/data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../gluon/data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/loss/index.html">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../metric/index.html">mxnet.metric</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html">mxnet.kvstore</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../module/index.html">mxnet.module</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/autograd/index.html">contrib.autograd</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html">mxnet</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../attribute/index.html">mxnet.attribute</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../base/index.html">mxnet.base</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../context/index.html">mxnet.context</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../executor_manager/index.html">mxnet.executor_manager</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../libinfo/index.html">mxnet.libinfo</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../log/index.html">mxnet.log</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../model/index.html">mxnet.model</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../monitor/index.html">mxnet.monitor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../name/index.html">mxnet.name</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../notebook/index.html">mxnet.notebook</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../operator/index.html">mxnet.operator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../random/index.html">mxnet.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../registry/index.html">mxnet.registry</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../runtime/index.html">mxnet.runtime</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../torch/index.html">mxnet.torch</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../util/index.html">mxnet.util</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav> |
| |
| </div> |
| |
| </header> |
| <main class="mdl-layout__content" tabIndex="0"> |
| |
| <script type="text/javascript" src="../../../_static/sphinx_materialdesign_theme.js "></script> |
| <script type="text/javascript" src="../../../_static/feedback.js"></script> |
| <header class="mdl-layout__drawer"> |
| |
| <div class="globaltoc"> |
| <span class="mdl-layout-title toc">Table Of Contents</span> |
| |
| |
| |
| <nav class="mdl-navigation"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Python Tutorials</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/getting-started/index.html">Getting Started</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/index.html">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-ndarray.html">Manipulate data with <code class="docutils literal notranslate"><span class="pre">ndarray</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-nn.html">Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Automatic differentiation with <code class="docutils literal notranslate"><span class="pre">autograd</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-train.html">Train the neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-predict.html">Predict with a pre-trained model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-use_gpus.html">Use GPUs</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom_layer_beginners.html">Customer Layers (Beginners)</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/image-augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/pretrained_models.html">Using pre-trained models in MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/train.html">Train a Linear Regression Model with Sparse Symbols</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/super_resolution.html">Importing an ONNX model into MXNet</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/index.html">Intel MKL-DNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html">Quantize with MKL-DNN backend</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html#Improving-accuracy-with-Intel®-Neural-Compressor">Improving accuracy with Intel® Neural Compressor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/tensorrt.html">Optimizing Deep Learning Computation Graphs with TensorRT</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/scala.html">Deploy into a Java or Scala Environment</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/wine_detector.html">Real-time Object Detection with MXNet On The Raspberry Pi</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/custom_layer.html">Custom Layers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Python API</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../../ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../gluon/index.html">mxnet.gluon</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/parameter_dict.html">gluon.ParameterDict</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../gluon/data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../gluon/data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../gluon/data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/loss/index.html">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../gluon/utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../metric/index.html">mxnet.metric</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html">mxnet.kvstore</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../module/index.html">mxnet.module</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/autograd/index.html">contrib.autograd</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html">mxnet</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../attribute/index.html">mxnet.attribute</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../base/index.html">mxnet.base</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../context/index.html">mxnet.context</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../executor_manager/index.html">mxnet.executor_manager</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../libinfo/index.html">mxnet.libinfo</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../log/index.html">mxnet.log</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../model/index.html">mxnet.model</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../monitor/index.html">mxnet.monitor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../name/index.html">mxnet.name</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../notebook/index.html">mxnet.notebook</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../operator/index.html">mxnet.operator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../random/index.html">mxnet.random</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../registry/index.html">mxnet.registry</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../runtime/index.html">mxnet.runtime</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../torch/index.html">mxnet.torch</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../util/index.html">mxnet.util</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav> |
| |
| </div> |
| |
| </header> |
| |
| <div class="document"> |
| <div class="page-content" role="main"> |
| |
| <div class="section" id="mxnet-image"> |
| <h1>mxnet.image<a class="headerlink" href="#mxnet-image" title="Permalink to this headline">¶</a></h1> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>This API is best used in conjunction with <code class="docutils literal notranslate"><span class="pre">mxnet.io</span></code> data iterators. |
| For augmentation and transforms in gluon with Datasets and DataLoaders see <code class="docutils literal notranslate"><span class="pre">mxnet.gluon.data</span></code></p> |
| </div> |
| <span class="target" id="module-mxnet.image"></span><p>Image Iterators and image augmentation functions</p> |
| <p><strong>Classes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.Augmenter" title="mxnet.image.Augmenter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Augmenter</span></code></a>(**kwargs)</p></td> |
| <td><p>Image Augmenter base class</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.BrightnessJitterAug" title="mxnet.image.BrightnessJitterAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">BrightnessJitterAug</span></code></a>(brightness)</p></td> |
| <td><p>Random brightness jitter augmentation.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.CastAug" title="mxnet.image.CastAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CastAug</span></code></a>([typ])</p></td> |
| <td><p>Cast to float32</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.CenterCropAug" title="mxnet.image.CenterCropAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CenterCropAug</span></code></a>(size[, interp])</p></td> |
| <td><p>Make center crop augmenter.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ColorJitterAug" title="mxnet.image.ColorJitterAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ColorJitterAug</span></code></a>(brightness, contrast, saturation)</p></td> |
| <td><p>Apply random brightness, contrast and saturation jitter in random order.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ColorNormalizeAug" title="mxnet.image.ColorNormalizeAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ColorNormalizeAug</span></code></a>(mean, std)</p></td> |
| <td><p>Mean and std normalization.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ContrastJitterAug" title="mxnet.image.ContrastJitterAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ContrastJitterAug</span></code></a>(contrast)</p></td> |
| <td><p>Random contrast jitter augmentation.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.DetAugmenter" title="mxnet.image.DetAugmenter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetAugmenter</span></code></a>(**kwargs)</p></td> |
| <td><p>Detection base augmenter</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetBorrowAug" title="mxnet.image.DetBorrowAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetBorrowAug</span></code></a>(augmenter)</p></td> |
| <td><p>Borrow standard augmenter from image classification.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.DetHorizontalFlipAug" title="mxnet.image.DetHorizontalFlipAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetHorizontalFlipAug</span></code></a>(p)</p></td> |
| <td><p>Random horizontal flipping.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetRandomCropAug" title="mxnet.image.DetRandomCropAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetRandomCropAug</span></code></a>([min_object_covered, …])</p></td> |
| <td><p>Random cropping with constraints</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.DetRandomPadAug" title="mxnet.image.DetRandomPadAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetRandomPadAug</span></code></a>([aspect_ratio_range, …])</p></td> |
| <td><p>Random padding augmenter.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetRandomSelectAug" title="mxnet.image.DetRandomSelectAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DetRandomSelectAug</span></code></a>(aug_list[, skip_prob])</p></td> |
| <td><p>Randomly select one augmenter to apply, with chance to skip all.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ForceResizeAug" title="mxnet.image.ForceResizeAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ForceResizeAug</span></code></a>(size[, interp])</p></td> |
| <td><p>Force resize to size regardless of aspect ratio</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.HorizontalFlipAug" title="mxnet.image.HorizontalFlipAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">HorizontalFlipAug</span></code></a>(p)</p></td> |
| <td><p>Random horizontal flip.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.HueJitterAug" title="mxnet.image.HueJitterAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">HueJitterAug</span></code></a>(hue)</p></td> |
| <td><p>Random hue jitter augmentation.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter" title="mxnet.image.ImageDetIter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ImageDetIter</span></code></a>(batch_size, data_shape[, …])</p></td> |
| <td><p>Image iterator with a large number of augmentation choices for detection.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter" title="mxnet.image.ImageIter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ImageIter</span></code></a>(batch_size, data_shape[, …])</p></td> |
| <td><p>Image data iterator with a large number of augmentation choices.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.LightingAug" title="mxnet.image.LightingAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LightingAug</span></code></a>(alphastd, eigval, eigvec)</p></td> |
| <td><p>Add PCA based noise.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.Number" title="mxnet.image.Number"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Number</span></code></a></p></td> |
| <td><p>All numbers inherit from this class.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.RandomCropAug" title="mxnet.image.RandomCropAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RandomCropAug</span></code></a>(size[, interp])</p></td> |
| <td><p>Make random crop augmenter</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.RandomGrayAug" title="mxnet.image.RandomGrayAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RandomGrayAug</span></code></a>(p)</p></td> |
| <td><p>Randomly convert to gray image.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.RandomOrderAug" title="mxnet.image.RandomOrderAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RandomOrderAug</span></code></a>(ts)</p></td> |
| <td><p>Apply list of augmenters in random order</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.RandomSizedCropAug" title="mxnet.image.RandomSizedCropAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RandomSizedCropAug</span></code></a>(size, area, ratio[, interp])</p></td> |
| <td><p>Make random crop with random resizing and random aspect ratio jitter augmenter.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ResizeAug" title="mxnet.image.ResizeAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ResizeAug</span></code></a>(size[, interp])</p></td> |
| <td><p>Make resize shorter edge to size augmenter.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.SaturationJitterAug" title="mxnet.image.SaturationJitterAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SaturationJitterAug</span></code></a>(saturation)</p></td> |
| <td><p>Random saturation jitter augmentation.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.SequentialAug" title="mxnet.image.SequentialAug"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SequentialAug</span></code></a>(ts)</p></td> |
| <td><p>Composing a sequential augmenter list.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Functions</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.CreateAugmenter" title="mxnet.image.CreateAugmenter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CreateAugmenter</span></code></a>(data_shape[, resize, …])</p></td> |
| <td><p>Creates an augmenter list.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.CreateDetAugmenter" title="mxnet.image.CreateDetAugmenter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CreateDetAugmenter</span></code></a>(data_shape[, resize, …])</p></td> |
| <td><p>Create augmenters for detection.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.CreateMultiRandCropAugmenter" title="mxnet.image.CreateMultiRandCropAugmenter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CreateMultiRandCropAugmenter</span></code></a>([…])</p></td> |
| <td><p>Helper function to create multiple random crop augmenters.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.center_crop" title="mxnet.image.center_crop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">center_crop</span></code></a>(src, size[, interp])</p></td> |
| <td><p>Crops the image <cite>src</cite> to the given <cite>size</cite> by trimming on all four sides and preserving the center of the image.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.color_normalize" title="mxnet.image.color_normalize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">color_normalize</span></code></a>(src, mean[, std])</p></td> |
| <td><p>Normalize src with mean and std.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.copyMakeBorder" title="mxnet.image.copyMakeBorder"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copyMakeBorder</span></code></a>([src, top, bot, left, right, …])</p></td> |
| <td><p>Pad image border with OpenCV.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.fixed_crop" title="mxnet.image.fixed_crop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fixed_crop</span></code></a>(src, x0, y0, w, h[, size, interp])</p></td> |
| <td><p>Crop src at fixed location, and (optionally) resize it to size.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.imdecode" title="mxnet.image.imdecode"><code class="xref py py-obj docutils literal notranslate"><span class="pre">imdecode</span></code></a>(buf, *args, **kwargs)</p></td> |
| <td><p>Decode an image to an NDArray.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.imread" title="mxnet.image.imread"><code class="xref py py-obj docutils literal notranslate"><span class="pre">imread</span></code></a>(filename, *args, **kwargs)</p></td> |
| <td><p>Read and decode an image to an NDArray.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.imresize" title="mxnet.image.imresize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">imresize</span></code></a>(src, w, h, *args, **kwargs)</p></td> |
| <td><p>Resize image with OpenCV.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.imrotate" title="mxnet.image.imrotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">imrotate</span></code></a>(src, rotation_degrees[, zoom_in, …])</p></td> |
| <td><p>Rotates the input image(s) of a specific rotation degree.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.is_np_array" title="mxnet.image.is_np_array"><code class="xref py py-obj docutils literal notranslate"><span class="pre">is_np_array</span></code></a>()</p></td> |
| <td><p>Checks whether the NumPy-array semantics is currently turned on.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.random_crop" title="mxnet.image.random_crop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">random_crop</span></code></a>(src, size[, interp])</p></td> |
| <td><p>Randomly crop <cite>src</cite> with <cite>size</cite> (width, height).</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.random_rotate" title="mxnet.image.random_rotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">random_rotate</span></code></a>(src, angle_limits[, zoom_in, …])</p></td> |
| <td><p>Random rotates <cite>src</cite> by an angle included in angle limits.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.random_size_crop" title="mxnet.image.random_size_crop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">random_size_crop</span></code></a>(src, size, area, ratio[, …])</p></td> |
| <td><p>Randomly crop src with size.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.resize_short" title="mxnet.image.resize_short"><code class="xref py py-obj docutils literal notranslate"><span class="pre">resize_short</span></code></a>(src, size[, interp])</p></td> |
| <td><p>Resizes shorter edge to size.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.scale_down" title="mxnet.image.scale_down"><code class="xref py py-obj docutils literal notranslate"><span class="pre">scale_down</span></code></a>(src_size, size)</p></td> |
| <td><p>Scales down crop size if it’s larger than image size.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="class"> |
| <dt id="mxnet.image.Augmenter"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">Augmenter</code><span class="sig-paren">(</span><em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#Augmenter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.Augmenter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p> |
| <p>Image Augmenter base class</p> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.Augmenter.dumps" title="mxnet.image.Augmenter.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Saves the Augmenter to string</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.Augmenter.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#Augmenter.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.Augmenter.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Saves the Augmenter to string</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Returns</dt> |
| <dd class="field-odd"><p>JSON formatted string that describes the Augmenter.</p> |
| </dd> |
| <dt class="field-even">Return type</dt> |
| <dd class="field-even"><p>str</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.BrightnessJitterAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">BrightnessJitterAug</code><span class="sig-paren">(</span><em class="sig-param">brightness</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#BrightnessJitterAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.BrightnessJitterAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Random brightness jitter augmentation.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>brightness</strong> (<em>float</em>) – The brightness jitter ratio range, [0, 1]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.CastAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">CastAug</code><span class="sig-paren">(</span><em class="sig-param">typ='float32'</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#CastAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.CastAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Cast to float32</p> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.CenterCropAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">CenterCropAug</code><span class="sig-paren">(</span><em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#CenterCropAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.CenterCropAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Make center crop augmenter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>size</strong> (<em>list</em><em> or </em><em>tuple of int</em>) – The desired output image size.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ColorJitterAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ColorJitterAug</code><span class="sig-paren">(</span><em class="sig-param">brightness</em>, <em class="sig-param">contrast</em>, <em class="sig-param">saturation</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ColorJitterAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ColorJitterAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.RandomOrderAug</span></code></p> |
| <p>Apply random brightness, contrast and saturation jitter in random order.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>brightness</strong> (<em>float</em>) – The brightness jitter ratio range, [0, 1]</p></li> |
| <li><p><strong>contrast</strong> (<em>float</em>) – The contrast jitter ratio range, [0, 1]</p></li> |
| <li><p><strong>saturation</strong> (<em>float</em>) – The saturation jitter ratio range, [0, 1]</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ColorNormalizeAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ColorNormalizeAug</code><span class="sig-paren">(</span><em class="sig-param">mean</em>, <em class="sig-param">std</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ColorNormalizeAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ColorNormalizeAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Mean and std normalization.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>mean</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – RGB mean to be subtracted</p></li> |
| <li><p><strong>std</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – RGB standard deviation to be divided</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ContrastJitterAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ContrastJitterAug</code><span class="sig-paren">(</span><em class="sig-param">contrast</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ContrastJitterAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ContrastJitterAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Random contrast jitter augmentation.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>contrast</strong> (<em>float</em>) – The contrast jitter ratio range, [0, 1]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.CreateAugmenter"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">CreateAugmenter</code><span class="sig-paren">(</span><em class="sig-param">data_shape</em>, <em class="sig-param">resize=0</em>, <em class="sig-param">rand_crop=False</em>, <em class="sig-param">rand_resize=False</em>, <em class="sig-param">rand_mirror=False</em>, <em class="sig-param">mean=None</em>, <em class="sig-param">std=None</em>, <em class="sig-param">brightness=0</em>, <em class="sig-param">contrast=0</em>, <em class="sig-param">saturation=0</em>, <em class="sig-param">hue=0</em>, <em class="sig-param">pca_noise=0</em>, <em class="sig-param">rand_gray=0</em>, <em class="sig-param">inter_method=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#CreateAugmenter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.CreateAugmenter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Creates an augmenter list.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>data_shape</strong> (<em>tuple of int</em>) – Shape for output data</p></li> |
| <li><p><strong>resize</strong> (<em>int</em>) – Resize shorter edge if larger than 0 at the begining</p></li> |
| <li><p><strong>rand_crop</strong> (<em>bool</em>) – Whether to enable random cropping other than center crop</p></li> |
| <li><p><strong>rand_resize</strong> (<em>bool</em>) – Whether to enable random sized cropping, require rand_crop to be enabled</p></li> |
| <li><p><strong>rand_gray</strong> (<em>float</em>) – [0, 1], probability to convert to grayscale for all channels, the number |
| of channels will not be reduced to 1</p></li> |
| <li><p><strong>rand_mirror</strong> (<em>bool</em>) – Whether to apply horizontal flip to image with probability 0.5</p></li> |
| <li><p><strong>mean</strong> (<em>np.ndarray</em><em> or </em><em>None</em>) – Mean pixel values for [r, g, b]</p></li> |
| <li><p><strong>std</strong> (<em>np.ndarray</em><em> or </em><em>None</em>) – Standard deviations for [r, g, b]</p></li> |
| <li><p><strong>brightness</strong> (<em>float</em>) – Brightness jittering range (percent)</p></li> |
| <li><p><strong>contrast</strong> (<em>float</em>) – Contrast jittering range (percent)</p></li> |
| <li><p><strong>saturation</strong> (<em>float</em>) – Saturation jittering range (percent)</p></li> |
| <li><p><strong>hue</strong> (<em>float</em>) – Hue jittering range (percent)</p></li> |
| <li><p><strong>pca_noise</strong> (<em>float</em>) – Pca noise level (percent)</p></li> |
| <li><p><strong>inter_method</strong> (<em>int</em><em>, </em><em>default=2</em><em>(</em><em>Area-based</em><em>)</em>) – <p>Interpolation method for all resizing operations</p> |
| <p>Possible values: |
| 0: Nearest Neighbors Interpolation. |
| 1: Bilinear interpolation. |
| 2: Bicubic interpolation over 4x4 pixel neighborhood. |
| 3: Area-based (resampling using pixel area relation). It may be a |
| preferred method for image decimation, as it gives moire-free |
| results. But when the image is zoomed, it is similar to the Nearest |
| Neighbors method. (used by default). |
| 4: Lanczos interpolation over 8x8 pixel neighborhood. |
| 9: Cubic for enlarge, area for shrink, bilinear for others |
| 10: Random select from interpolation method metioned above. |
| Note: |
| When shrinking an image, it will generally look best with AREA-based |
| interpolation, whereas, when enlarging an image, it will generally look best |
| with Bicubic (slow) or Bilinear (faster but still looks OK).</p> |
| </p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="c1"># An example of creating multiple augmenters</span> |
| <span class="gp">>>> </span><span class="n">augs</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">CreateAugmenter</span><span class="p">(</span><span class="n">data_shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">),</span> <span class="n">rand_mirror</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="gp">... </span> <span class="n">mean</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">brightness</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> <span class="n">rand_gray</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> |
| <span class="gp">... </span> <span class="n">saturation</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> <span class="n">pca_noise</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">inter_method</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="c1"># dump the details</span> |
| <span class="gp">>>> </span><span class="k">for</span> <span class="n">aug</span> <span class="ow">in</span> <span class="n">augs</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">aug</span><span class="o">.</span><span class="n">dumps</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.CreateDetAugmenter"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">CreateDetAugmenter</code><span class="sig-paren">(</span><em class="sig-param">data_shape</em>, <em class="sig-param">resize=0</em>, <em class="sig-param">rand_crop=0</em>, <em class="sig-param">rand_pad=0</em>, <em class="sig-param">rand_gray=0</em>, <em class="sig-param">rand_mirror=False</em>, <em class="sig-param">mean=None</em>, <em class="sig-param">std=None</em>, <em class="sig-param">brightness=0</em>, <em class="sig-param">contrast=0</em>, <em class="sig-param">saturation=0</em>, <em class="sig-param">pca_noise=0</em>, <em class="sig-param">hue=0</em>, <em class="sig-param">inter_method=2</em>, <em class="sig-param">min_object_covered=0.1</em>, <em class="sig-param">aspect_ratio_range=(0.75</em>, <em class="sig-param">1.33)</em>, <em class="sig-param">area_range=(0.05</em>, <em class="sig-param">3.0)</em>, <em class="sig-param">min_eject_coverage=0.3</em>, <em class="sig-param">max_attempts=50</em>, <em class="sig-param">pad_val=(127</em>, <em class="sig-param">127</em>, <em class="sig-param">127)</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#CreateDetAugmenter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.CreateDetAugmenter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Create augmenters for detection.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>data_shape</strong> (<em>tuple of int</em>) – Shape for output data</p></li> |
| <li><p><strong>resize</strong> (<em>int</em>) – Resize shorter edge if larger than 0 at the begining</p></li> |
| <li><p><strong>rand_crop</strong> (<em>float</em>) – [0, 1], probability to apply random cropping</p></li> |
| <li><p><strong>rand_pad</strong> (<em>float</em>) – [0, 1], probability to apply random padding</p></li> |
| <li><p><strong>rand_gray</strong> (<em>float</em>) – [0, 1], probability to convert to grayscale for all channels</p></li> |
| <li><p><strong>rand_mirror</strong> (<em>bool</em>) – Whether to apply horizontal flip to image with probability 0.5</p></li> |
| <li><p><strong>mean</strong> (<em>np.ndarray</em><em> or </em><em>None</em>) – Mean pixel values for [r, g, b]</p></li> |
| <li><p><strong>std</strong> (<em>np.ndarray</em><em> or </em><em>None</em>) – Standard deviations for [r, g, b]</p></li> |
| <li><p><strong>brightness</strong> (<em>float</em>) – Brightness jittering range (percent)</p></li> |
| <li><p><strong>contrast</strong> (<em>float</em>) – Contrast jittering range (percent)</p></li> |
| <li><p><strong>saturation</strong> (<em>float</em>) – Saturation jittering range (percent)</p></li> |
| <li><p><strong>hue</strong> (<em>float</em>) – Hue jittering range (percent)</p></li> |
| <li><p><strong>pca_noise</strong> (<em>float</em>) – Pca noise level (percent)</p></li> |
| <li><p><strong>inter_method</strong> (<em>int</em><em>, </em><em>default=2</em><em>(</em><em>Area-based</em><em>)</em>) – <p>Interpolation method for all resizing operations</p> |
| <p>Possible values: |
| 0: Nearest Neighbors Interpolation. |
| 1: Bilinear interpolation. |
| 2: Area-based (resampling using pixel area relation). It may be a |
| preferred method for image decimation, as it gives moire-free |
| results. But when the image is zoomed, it is similar to the Nearest |
| Neighbors method. (used by default). |
| 3: Bicubic interpolation over 4x4 pixel neighborhood. |
| 4: Lanczos interpolation over 8x8 pixel neighborhood. |
| 9: Cubic for enlarge, area for shrink, bilinear for others |
| 10: Random select from interpolation method metioned above. |
| Note: |
| When shrinking an image, it will generally look best with AREA-based |
| interpolation, whereas, when enlarging an image, it will generally look best |
| with Bicubic (slow) or Bilinear (faster but still looks OK).</p> |
| </p></li> |
| <li><p><strong>min_object_covered</strong> (<em>float</em>) – The cropped area of the image must contain at least this fraction of |
| any bounding box supplied. The value of this parameter should be non-negative. |
| In the case of 0, the cropped area does not need to overlap any of the |
| bounding boxes supplied.</p></li> |
| <li><p><strong>min_eject_coverage</strong> (<em>float</em>) – The minimum coverage of cropped sample w.r.t its original size. With this |
| constraint, objects that have marginal area after crop will be discarded.</p></li> |
| <li><p><strong>aspect_ratio_range</strong> (<em>tuple of floats</em>) – The cropped area of the image must have an aspect ratio = width / height |
| within this range.</p></li> |
| <li><p><strong>area_range</strong> (<em>tuple of floats</em>) – The cropped area of the image must contain a fraction of the supplied |
| image within in this range.</p></li> |
| <li><p><strong>max_attempts</strong> (<em>int</em>) – Number of attempts at generating a cropped/padded region of the image of the |
| specified constraints. After max_attempts failures, return the original image.</p></li> |
| <li><p><strong>pad_val</strong> (<em>float</em>) – Pixel value to be filled when padding is enabled. pad_val will automatically |
| be subtracted by mean and divided by std if applicable.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="c1"># An example of creating multiple augmenters</span> |
| <span class="gp">>>> </span><span class="n">augs</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">CreateDetAugmenter</span><span class="p">(</span><span class="n">data_shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">),</span> <span class="n">rand_crop</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> |
| <span class="gp">... </span> <span class="n">rand_pad</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">rand_mirror</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">mean</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">brightness</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> |
| <span class="gp">... </span> <span class="n">saturation</span><span class="o">=</span><span class="mf">0.125</span><span class="p">,</span> <span class="n">pca_noise</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">inter_method</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">min_object_covered</span><span class="o">=</span><span class="p">[</span><span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">],</span> |
| <span class="gp">... </span> <span class="n">area_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.3</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="c1"># dump the details</span> |
| <span class="gp">>>> </span><span class="k">for</span> <span class="n">aug</span> <span class="ow">in</span> <span class="n">augs</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">aug</span><span class="o">.</span><span class="n">dumps</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.CreateMultiRandCropAugmenter"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">CreateMultiRandCropAugmenter</code><span class="sig-paren">(</span><em class="sig-param">min_object_covered=0.1</em>, <em class="sig-param">aspect_ratio_range=(0.75</em>, <em class="sig-param">1.33)</em>, <em class="sig-param">area_range=(0.05</em>, <em class="sig-param">1.0)</em>, <em class="sig-param">min_eject_coverage=0.3</em>, <em class="sig-param">max_attempts=50</em>, <em class="sig-param">skip_prob=0</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#CreateMultiRandCropAugmenter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.CreateMultiRandCropAugmenter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Helper function to create multiple random crop augmenters.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>min_object_covered</strong> (<em>float</em><em> or </em><em>list of float</em><em>, </em><em>default=0.1</em>) – The cropped area of the image must contain at least this fraction of |
| any bounding box supplied. The value of this parameter should be non-negative. |
| In the case of 0, the cropped area does not need to overlap any of the |
| bounding boxes supplied.</p></li> |
| <li><p><strong>min_eject_coverage</strong> (<em>float</em><em> or </em><em>list of float</em><em>, </em><em>default=0.3</em>) – The minimum coverage of cropped sample w.r.t its original size. With this |
| constraint, objects that have marginal area after crop will be discarded.</p></li> |
| <li><p><strong>aspect_ratio_range</strong> (<em>tuple of floats</em><em> or </em><em>list of tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>0.75</em><em>, </em><em>1.33</em><em>)</em>) – The cropped area of the image must have an aspect ratio = width / height |
| within this range.</p></li> |
| <li><p><strong>area_range</strong> (<em>tuple of floats</em><em> or </em><em>list of tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>0.05</em><em>, </em><em>1.0</em><em>)</em>) – The cropped area of the image must contain a fraction of the supplied |
| image within in this range.</p></li> |
| <li><p><strong>max_attempts</strong> (<em>int</em><em> or </em><em>list of int</em><em>, </em><em>default=50</em>) – Number of attempts at generating a cropped/padded region of the image of the |
| specified constraints. After max_attempts failures, return the original image.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="c1"># An example of creating multiple random crop augmenters</span> |
| <span class="gp">>>> </span><span class="n">min_object_covered</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.7</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">]</span> <span class="c1"># use 5 augmenters</span> |
| <span class="gp">>>> </span><span class="n">aspect_ratio_range</span> <span class="o">=</span> <span class="p">(</span><span class="mf">0.75</span><span class="p">,</span> <span class="mf">1.33</span><span class="p">)</span> <span class="c1"># use same range for all augmenters</span> |
| <span class="gp">>>> </span><span class="n">area_range</span> <span class="o">=</span> <span class="p">[(</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.3</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)]</span> |
| <span class="gp">>>> </span><span class="n">min_eject_coverage</span> <span class="o">=</span> <span class="mf">0.3</span> |
| <span class="gp">>>> </span><span class="n">max_attempts</span> <span class="o">=</span> <span class="mi">50</span> |
| <span class="gp">>>> </span><span class="n">aug</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">det</span><span class="o">.</span><span class="n">CreateMultiRandCropAugmenter</span><span class="p">(</span><span class="n">min_object_covered</span><span class="o">=</span><span class="n">min_object_covered</span><span class="p">,</span> |
| <span class="go"> aspect_ratio_range=aspect_ratio_range, area_range=area_range,</span> |
| <span class="go"> min_eject_coverage=min_eject_coverage, max_attempts=max_attempts,</span> |
| <span class="go"> skip_prob=0)</span> |
| <span class="gp">>>> </span><span class="n">aug</span><span class="o">.</span><span class="n">dumps</span><span class="p">()</span> <span class="c1"># show some details</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetAugmenter"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetAugmenter</code><span class="sig-paren">(</span><em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetAugmenter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetAugmenter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p> |
| <p>Detection base augmenter</p> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetAugmenter.dumps" title="mxnet.image.DetAugmenter.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Saves the Augmenter to string</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.DetAugmenter.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetAugmenter.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetAugmenter.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Saves the Augmenter to string</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Returns</dt> |
| <dd class="field-odd"><p>JSON formatted string that describes the Augmenter.</p> |
| </dd> |
| <dt class="field-even">Return type</dt> |
| <dd class="field-even"><p>str</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetBorrowAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetBorrowAug</code><span class="sig-paren">(</span><em class="sig-param">augmenter</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetBorrowAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetBorrowAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.detection.DetAugmenter</span></code></p> |
| <p>Borrow standard augmenter from image classification. |
| Which is good once you know label won’t be affected after this augmenter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>augmenter</strong> (<em>mx.image.Augmenter</em>) – The borrowed standard augmenter which has no effect on label</p> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetBorrowAug.dumps" title="mxnet.image.DetBorrowAug.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Override the default one to avoid duplicate dump.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.DetBorrowAug.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetBorrowAug.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetBorrowAug.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override the default one to avoid duplicate dump.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetHorizontalFlipAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetHorizontalFlipAug</code><span class="sig-paren">(</span><em class="sig-param">p</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetHorizontalFlipAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetHorizontalFlipAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.detection.DetAugmenter</span></code></p> |
| <p>Random horizontal flipping.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>p</strong> (<em>float</em>) – chance [0, 1] to flip</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetRandomCropAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetRandomCropAug</code><span class="sig-paren">(</span><em class="sig-param">min_object_covered=0.1</em>, <em class="sig-param">aspect_ratio_range=(0.75</em>, <em class="sig-param">1.33)</em>, <em class="sig-param">area_range=(0.05</em>, <em class="sig-param">1.0)</em>, <em class="sig-param">min_eject_coverage=0.3</em>, <em class="sig-param">max_attempts=50</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetRandomCropAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetRandomCropAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.detection.DetAugmenter</span></code></p> |
| <p>Random cropping with constraints</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>min_object_covered</strong> (<em>float</em><em>, </em><em>default=0.1</em>) – The cropped area of the image must contain at least this fraction of |
| any bounding box supplied. The value of this parameter should be non-negative. |
| In the case of 0, the cropped area does not need to overlap any of the |
| bounding boxes supplied.</p></li> |
| <li><p><strong>min_eject_coverage</strong> (<em>float</em><em>, </em><em>default=0.3</em>) – The minimum coverage of cropped sample w.r.t its original size. With this |
| constraint, objects that have marginal area after crop will be discarded.</p></li> |
| <li><p><strong>aspect_ratio_range</strong> (<em>tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>0.75</em><em>, </em><em>1.33</em><em>)</em>) – The cropped area of the image must have an aspect ratio = width / height |
| within this range.</p></li> |
| <li><p><strong>area_range</strong> (<em>tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>0.05</em><em>, </em><em>1.0</em><em>)</em>) – The cropped area of the image must contain a fraction of the supplied |
| image within in this range.</p></li> |
| <li><p><strong>max_attempts</strong> (<em>int</em><em>, </em><em>default=50</em>) – Number of attempts at generating a cropped/padded region of the image of the |
| specified constraints. After max_attempts failures, return the original image.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetRandomPadAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetRandomPadAug</code><span class="sig-paren">(</span><em class="sig-param">aspect_ratio_range=(0.75</em>, <em class="sig-param">1.33)</em>, <em class="sig-param">area_range=(1.0</em>, <em class="sig-param">3.0)</em>, <em class="sig-param">max_attempts=50</em>, <em class="sig-param">pad_val=(128</em>, <em class="sig-param">128</em>, <em class="sig-param">128)</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetRandomPadAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetRandomPadAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.detection.DetAugmenter</span></code></p> |
| <p>Random padding augmenter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>aspect_ratio_range</strong> (<em>tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>0.75</em><em>, </em><em>1.33</em><em>)</em>) – The padded area of the image must have an aspect ratio = width / height |
| within this range.</p></li> |
| <li><p><strong>area_range</strong> (<em>tuple of floats</em><em>, </em><em>default=</em><em>(</em><em>1.0</em><em>, </em><em>3.0</em><em>)</em>) – The padded area of the image must be larger than the original area</p></li> |
| <li><p><strong>max_attempts</strong> (<em>int</em><em>, </em><em>default=50</em>) – Number of attempts at generating a padded region of the image of the |
| specified constraints. After max_attempts failures, return the original image.</p></li> |
| <li><p><strong>pad_val</strong> (<em>float</em><em> or </em><em>tuple of float</em><em>, </em><em>default=</em><em>(</em><em>128</em><em>, </em><em>128</em><em>, </em><em>128</em><em>)</em>) – pixel value to be filled when padding is enabled.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.DetRandomSelectAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">DetRandomSelectAug</code><span class="sig-paren">(</span><em class="sig-param">aug_list</em>, <em class="sig-param">skip_prob=0</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetRandomSelectAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetRandomSelectAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.detection.DetAugmenter</span></code></p> |
| <p>Randomly select one augmenter to apply, with chance to skip all.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>aug_list</strong> (<em>list of DetAugmenter</em>) – The random selection will be applied to one of the augmenters</p></li> |
| <li><p><strong>skip_prob</strong> (<em>float</em>) – The probability to skip all augmenters and return input directly</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.DetRandomSelectAug.dumps" title="mxnet.image.DetRandomSelectAug.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Override default.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.DetRandomSelectAug.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#DetRandomSelectAug.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.DetRandomSelectAug.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override default.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ForceResizeAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ForceResizeAug</code><span class="sig-paren">(</span><em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ForceResizeAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ForceResizeAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Force resize to size regardless of aspect ratio</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>size</strong> (<em>tuple of</em><em> (</em><em>int</em><em>, </em><em>int</em><em>)</em>) – The desired size as in (width, height)</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.HorizontalFlipAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">HorizontalFlipAug</code><span class="sig-paren">(</span><em class="sig-param">p</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#HorizontalFlipAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.HorizontalFlipAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Random horizontal flip.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>p</strong> (<em>float</em>) – Probability to flip image horizontally</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.HueJitterAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">HueJitterAug</code><span class="sig-paren">(</span><em class="sig-param">hue</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#HueJitterAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.HueJitterAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Random hue jitter augmentation.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hue</strong> (<em>float</em>) – The hue jitter ratio range, [0, 1]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ImageDetIter"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ImageDetIter</code><span class="sig-paren">(</span><em class="sig-param">batch_size</em>, <em class="sig-param">data_shape</em>, <em class="sig-param">path_imgrec=None</em>, <em class="sig-param">path_imglist=None</em>, <em class="sig-param">path_root=None</em>, <em class="sig-param">path_imgidx=None</em>, <em class="sig-param">shuffle=False</em>, <em class="sig-param">part_index=0</em>, <em class="sig-param">num_parts=1</em>, <em class="sig-param">aug_list=None</em>, <em class="sig-param">imglist=None</em>, <em class="sig-param">data_name='data'</em>, <em class="sig-param">label_name='label'</em>, <em class="sig-param">last_batch_handle='pad'</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.ImageIter</span></code></p> |
| <p>Image iterator with a large number of augmentation choices for detection.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>aug_list</strong> (<em>list</em><em> or </em><em>None</em>) – Augmenter list for generating distorted images</p></li> |
| <li><p><strong>batch_size</strong> (<em>int</em>) – Number of examples per batch.</p></li> |
| <li><p><strong>data_shape</strong> (<em>tuple</em>) – Data shape in (channels, height, width) format. |
| For now, only RGB image with 3 channels is supported.</p></li> |
| <li><p><strong>path_imgrec</strong> (<em>str</em>) – Path to image record file (.rec). |
| Created with tools/im2rec.py or bin/im2rec.</p></li> |
| <li><p><strong>path_imglist</strong> (<em>str</em>) – Path to image list (.lst). |
| Created with tools/im2rec.py or with custom script. |
| Format: Tab separated record of index, one or more labels and relative_path_from_root.</p></li> |
| <li><p><strong>imglist</strong> (<em>list</em>) – A list of images with the label(s). |
| Each item is a list [imagelabel: float or list of float, imgpath].</p></li> |
| <li><p><strong>path_root</strong> (<em>str</em>) – Root folder of image files.</p></li> |
| <li><p><strong>path_imgidx</strong> (<em>str</em>) – Path to image index file. Needed for partition and shuffling when using .rec source.</p></li> |
| <li><p><strong>shuffle</strong> (<em>bool</em>) – Whether to shuffle all images at the start of each iteration or not. |
| Can be slow for HDD.</p></li> |
| <li><p><strong>part_index</strong> (<em>int</em>) – Partition index.</p></li> |
| <li><p><strong>num_parts</strong> (<em>int</em>) – Total number of partitions.</p></li> |
| <li><p><strong>data_name</strong> (<em>str</em>) – Data name for provided symbols.</p></li> |
| <li><p><strong>label_name</strong> (<em>str</em>) – Name for detection labels</p></li> |
| <li><p><strong>last_batch_handle</strong> (<em>str</em><em>, </em><em>optional</em>) – How to handle the last batch. |
| This parameter can be ‘pad’(default), ‘discard’ or ‘roll_over’. |
| If ‘pad’, the last batch will be padded with data starting from the begining |
| If ‘discard’, the last batch will be discarded |
| If ‘roll_over’, the remaining elements will be rolled over to the next iteration</p></li> |
| <li><p><strong>kwargs</strong> – More arguments for creating augmenter. See mx.image.CreateDetAugmenter.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.augmentation_transform" title="mxnet.image.ImageDetIter.augmentation_transform"><code class="xref py py-obj docutils literal notranslate"><span class="pre">augmentation_transform</span></code></a>(data, label)</p></td> |
| <td><p>Override Transforms input data with specified augmentations.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.check_label_shape" title="mxnet.image.ImageDetIter.check_label_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">check_label_shape</span></code></a>(label_shape)</p></td> |
| <td><p>Checks if the new label shape is valid</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.draw_next" title="mxnet.image.ImageDetIter.draw_next"><code class="xref py py-obj docutils literal notranslate"><span class="pre">draw_next</span></code></a>([color, thickness, mean, std, …])</p></td> |
| <td><p>Display next image with bounding boxes drawn.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.next" title="mxnet.image.ImageDetIter.next"><code class="xref py py-obj docutils literal notranslate"><span class="pre">next</span></code></a>()</p></td> |
| <td><p>Override the function for returning next batch.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.reshape" title="mxnet.image.ImageDetIter.reshape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reshape</span></code></a>([data_shape, label_shape])</p></td> |
| <td><p>Reshape iterator for data_shape or label_shape.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageDetIter.sync_label_shape" title="mxnet.image.ImageDetIter.sync_label_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sync_label_shape</span></code></a>(it[, verbose])</p></td> |
| <td><p>Synchronize label shape with the input iterator.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.augmentation_transform"> |
| <code class="sig-name descname">augmentation_transform</code><span class="sig-paren">(</span><em class="sig-param">data</em>, <em class="sig-param">label</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.augmentation_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.augmentation_transform" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override Transforms input data with specified augmentations.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.check_label_shape"> |
| <code class="sig-name descname">check_label_shape</code><span class="sig-paren">(</span><em class="sig-param">label_shape</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.check_label_shape"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.check_label_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Checks if the new label shape is valid</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.draw_next"> |
| <code class="sig-name descname">draw_next</code><span class="sig-paren">(</span><em class="sig-param">color=None</em>, <em class="sig-param">thickness=2</em>, <em class="sig-param">mean=None</em>, <em class="sig-param">std=None</em>, <em class="sig-param">clip=True</em>, <em class="sig-param">waitKey=None</em>, <em class="sig-param">window_name='draw_next'</em>, <em class="sig-param">id2labels=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.draw_next"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.draw_next" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Display next image with bounding boxes drawn.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>color</strong> (<em>tuple</em>) – Bounding box color in RGB, use None for random color</p></li> |
| <li><p><strong>thickness</strong> (<em>int</em>) – Bounding box border thickness</p></li> |
| <li><p><strong>mean</strong> (<em>True</em><em> or </em><em>numpy.ndarray</em>) – Compensate for the mean to have better visual effect</p></li> |
| <li><p><strong>std</strong> (<em>True</em><em> or </em><em>numpy.ndarray</em>) – Revert standard deviations</p></li> |
| <li><p><strong>clip</strong> (<em>bool</em>) – If true, clip to [0, 255] for better visual effect</p></li> |
| <li><p><strong>waitKey</strong> (<em>None</em><em> or </em><em>int</em>) – Hold the window for waitKey milliseconds if set, skip ploting if None</p></li> |
| <li><p><strong>window_name</strong> (<em>str</em>) – Plot window name if waitKey is set.</p></li> |
| <li><p><strong>id2labels</strong> (<em>dict</em>) – Mapping of labels id to labels name.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>numpy.ndarray</p> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="c1"># use draw_next to get images with bounding boxes drawn</span> |
| <span class="gp">>>> </span><span class="n">iterator</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">ImageDetIter</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">600</span><span class="p">),</span> <span class="n">path_imgrec</span><span class="o">=</span><span class="s1">'train.rec'</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="k">for</span> <span class="n">image</span> <span class="ow">in</span> <span class="n">iterator</span><span class="o">.</span><span class="n">draw_next</span><span class="p">(</span><span class="n">waitKey</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="c1"># display image</span> |
| <span class="gp">>>> </span><span class="c1"># or let draw_next display using cv2 module</span> |
| <span class="gp">>>> </span><span class="k">for</span> <span class="n">image</span> <span class="ow">in</span> <span class="n">iterator</span><span class="o">.</span><span class="n">draw_next</span><span class="p">(</span><span class="n">waitKey</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">window_name</span><span class="o">=</span><span class="s1">'disp'</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="k">pass</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.next"> |
| <code class="sig-name descname">next</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.next"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.next" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override the function for returning next batch.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.reshape"> |
| <code class="sig-name descname">reshape</code><span class="sig-paren">(</span><em class="sig-param">data_shape=None</em>, <em class="sig-param">label_shape=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.reshape"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.reshape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Reshape iterator for data_shape or label_shape.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>data_shape</strong> (<em>tuple</em><em> or </em><em>None</em>) – Reshape the data_shape to the new shape if not None</p></li> |
| <li><p><strong>label_shape</strong> (<em>tuple</em><em> or </em><em>None</em>) – Reshape label shape to new shape if not None</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageDetIter.sync_label_shape"> |
| <code class="sig-name descname">sync_label_shape</code><span class="sig-paren">(</span><em class="sig-param">it</em>, <em class="sig-param">verbose=False</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/detection.html#ImageDetIter.sync_label_shape"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageDetIter.sync_label_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Synchronize label shape with the input iterator. This is useful when |
| train/validation iterators have different label padding.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>it</strong> (<a class="reference internal" href="#mxnet.image.ImageDetIter" title="mxnet.image.ImageDetIter"><em>ImageDetIter</em></a>) – The other iterator to synchronize</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em>) – Print verbose log if true</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>The synchronized other iterator, the internal label shape is updated as well.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="#mxnet.image.ImageDetIter" title="mxnet.image.ImageDetIter">ImageDetIter</a></p> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">train_iter</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">ImageDetIter</span><span class="p">(</span><span class="mi">32</span><span class="p">,</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">),</span> <span class="n">path_imgrec</span><span class="o">=</span><span class="s1">'train.rec'</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">val_iter</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">ImageDetIter</span><span class="p">(</span><span class="mi">32</span><span class="p">,</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">300</span><span class="p">,</span> <span class="mi">300</span><span class="p">),</span> <span class="n">path</span><span class="o">.</span><span class="n">imgrec</span><span class="o">=</span><span class="s1">'val.rec'</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">train_iter</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="go">(30, 6)</span> |
| <span class="gp">>>> </span><span class="n">val_iter</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="go">(25, 6)</span> |
| <span class="gp">>>> </span><span class="n">val_iter</span> <span class="o">=</span> <span class="n">train_iter</span><span class="o">.</span><span class="n">sync_label_shape</span><span class="p">(</span><span class="n">val_iter</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">train_iter</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="go">(30, 6)</span> |
| <span class="gp">>>> </span><span class="n">val_iter</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="go">(30, 6)</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ImageIter"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ImageIter</code><span class="sig-paren">(</span><em class="sig-param">batch_size</em>, <em class="sig-param">data_shape</em>, <em class="sig-param">label_width=1</em>, <em class="sig-param">path_imgrec=None</em>, <em class="sig-param">path_imglist=None</em>, <em class="sig-param">path_root=None</em>, <em class="sig-param">path_imgidx=None</em>, <em class="sig-param">shuffle=False</em>, <em class="sig-param">part_index=0</em>, <em class="sig-param">num_parts=1</em>, <em class="sig-param">aug_list=None</em>, <em class="sig-param">imglist=None</em>, <em class="sig-param">data_name='data'</em>, <em class="sig-param">label_name='softmax_label'</em>, <em class="sig-param">dtype='float32'</em>, <em class="sig-param">last_batch_handle='pad'</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.io.io.DataIter</span></code></p> |
| <p>Image data iterator with a large number of augmentation choices. |
| This iterator supports reading from both .rec files and raw image files.</p> |
| <p>To load input images from .rec files, use <cite>path_imgrec</cite> parameter and to load from raw image |
| files, use <cite>path_imglist</cite> and <cite>path_root</cite> parameters.</p> |
| <p>To use data partition (for distributed training) or shuffling, specify <cite>path_imgidx</cite> parameter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>batch_size</strong> (<em>int</em>) – Number of examples per batch.</p></li> |
| <li><p><strong>data_shape</strong> (<em>tuple</em>) – Data shape in (channels, height, width) format. |
| For now, only RGB image with 3 channels is supported.</p></li> |
| <li><p><strong>label_width</strong> (<em>int</em><em>, </em><em>optional</em>) – Number of labels per example. The default label width is 1.</p></li> |
| <li><p><strong>path_imgrec</strong> (<em>str</em>) – Path to image record file (.rec). |
| Created with tools/im2rec.py or bin/im2rec.</p></li> |
| <li><p><strong>path_imglist</strong> (<em>str</em>) – Path to image list (.lst). |
| Created with tools/im2rec.py or with custom script. |
| Format: Tab separated record of index, one or more labels and relative_path_from_root.</p></li> |
| <li><p><strong>imglist</strong> (<em>list</em>) – A list of images with the label(s). |
| Each item is a list [imagelabel: float or list of float, imgpath].</p></li> |
| <li><p><strong>path_root</strong> (<em>str</em>) – Root folder of image files.</p></li> |
| <li><p><strong>path_imgidx</strong> (<em>str</em>) – Path to image index file. Needed for partition and shuffling when using .rec source.</p></li> |
| <li><p><strong>shuffle</strong> (<em>bool</em>) – Whether to shuffle all images at the start of each iteration or not. |
| Can be slow for HDD.</p></li> |
| <li><p><strong>part_index</strong> (<em>int</em>) – Partition index.</p></li> |
| <li><p><strong>num_parts</strong> (<em>int</em>) – Total number of partitions.</p></li> |
| <li><p><strong>data_name</strong> (<em>str</em>) – Data name for provided symbols.</p></li> |
| <li><p><strong>label_name</strong> (<em>str</em>) – Label name for provided symbols.</p></li> |
| <li><p><strong>dtype</strong> (<em>str</em>) – Label data type. Default: float32. Other options: int32, int64, float64</p></li> |
| <li><p><strong>last_batch_handle</strong> (<em>str</em><em>, </em><em>optional</em>) – How to handle the last batch. |
| This parameter can be ‘pad’(default), ‘discard’ or ‘roll_over’. |
| If ‘pad’, the last batch will be padded with data starting from the begining |
| If ‘discard’, the last batch will be discarded |
| If ‘roll_over’, the remaining elements will be rolled over to the next iteration</p></li> |
| <li><p><strong>kwargs</strong> – More arguments for creating augmenter. See mx.image.CreateAugmenter.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.augmentation_transform" title="mxnet.image.ImageIter.augmentation_transform"><code class="xref py py-obj docutils literal notranslate"><span class="pre">augmentation_transform</span></code></a>(data)</p></td> |
| <td><p>Transforms input data with specified augmentation.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.check_data_shape" title="mxnet.image.ImageIter.check_data_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">check_data_shape</span></code></a>(data_shape)</p></td> |
| <td><p>Checks if the input data shape is valid</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.check_valid_image" title="mxnet.image.ImageIter.check_valid_image"><code class="xref py py-obj docutils literal notranslate"><span class="pre">check_valid_image</span></code></a>(data)</p></td> |
| <td><p>Checks if the input data is valid</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.hard_reset" title="mxnet.image.ImageIter.hard_reset"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hard_reset</span></code></a>()</p></td> |
| <td><p>Resets the iterator and ignore roll over data</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.imdecode" title="mxnet.image.ImageIter.imdecode"><code class="xref py py-obj docutils literal notranslate"><span class="pre">imdecode</span></code></a>(s)</p></td> |
| <td><p>Decodes a string or byte string to an NDArray.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.next" title="mxnet.image.ImageIter.next"><code class="xref py py-obj docutils literal notranslate"><span class="pre">next</span></code></a>()</p></td> |
| <td><p>Returns the next batch of data.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.next_sample" title="mxnet.image.ImageIter.next_sample"><code class="xref py py-obj docutils literal notranslate"><span class="pre">next_sample</span></code></a>()</p></td> |
| <td><p>Helper function for reading in next sample.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.postprocess_data" title="mxnet.image.ImageIter.postprocess_data"><code class="xref py py-obj docutils literal notranslate"><span class="pre">postprocess_data</span></code></a>(datum)</p></td> |
| <td><p>Final postprocessing step before image is loaded into the batch.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.read_image" title="mxnet.image.ImageIter.read_image"><code class="xref py py-obj docutils literal notranslate"><span class="pre">read_image</span></code></a>(fname)</p></td> |
| <td><p>Reads an input image <cite>fname</cite> and returns the decoded raw bytes.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.image.ImageIter.reset" title="mxnet.image.ImageIter.reset"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset</span></code></a>()</p></td> |
| <td><p>Resets the iterator to the beginning of the data.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.augmentation_transform"> |
| <code class="sig-name descname">augmentation_transform</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.augmentation_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.augmentation_transform" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Transforms input data with specified augmentation.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.check_data_shape"> |
| <code class="sig-name descname">check_data_shape</code><span class="sig-paren">(</span><em class="sig-param">data_shape</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.check_data_shape"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.check_data_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Checks if the input data shape is valid</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.check_valid_image"> |
| <code class="sig-name descname">check_valid_image</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.check_valid_image"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.check_valid_image" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Checks if the input data is valid</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.hard_reset"> |
| <code class="sig-name descname">hard_reset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.hard_reset"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.hard_reset" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Resets the iterator and ignore roll over data</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.imdecode"> |
| <code class="sig-name descname">imdecode</code><span class="sig-paren">(</span><em class="sig-param">s</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.imdecode"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.imdecode" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Decodes a string or byte string to an NDArray. |
| See mx.img.imdecode for more details.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.next"> |
| <code class="sig-name descname">next</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.next"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.next" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns the next batch of data.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.next_sample"> |
| <code class="sig-name descname">next_sample</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.next_sample"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.next_sample" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Helper function for reading in next sample.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.postprocess_data"> |
| <code class="sig-name descname">postprocess_data</code><span class="sig-paren">(</span><em class="sig-param">datum</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.postprocess_data"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.postprocess_data" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Final postprocessing step before image is loaded into the batch.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.read_image"> |
| <code class="sig-name descname">read_image</code><span class="sig-paren">(</span><em class="sig-param">fname</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.read_image"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.read_image" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Reads an input image <cite>fname</cite> and returns the decoded raw bytes. |
| .. rubric:: Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">dataIter</span><span class="o">.</span><span class="n">read_image</span><span class="p">(</span><span class="s1">'Face.jpg'</span><span class="p">)</span> <span class="c1"># returns decoded raw bytes.</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.image.ImageIter.reset"> |
| <code class="sig-name descname">reset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ImageIter.reset"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ImageIter.reset" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Resets the iterator to the beginning of the data.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.LightingAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">LightingAug</code><span class="sig-paren">(</span><em class="sig-param">alphastd</em>, <em class="sig-param">eigval</em>, <em class="sig-param">eigvec</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#LightingAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.LightingAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Add PCA based noise.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>alphastd</strong> (<em>float</em>) – Noise level</p></li> |
| <li><p><strong>eigval</strong> (<em>3x1 np.array</em>) – Eigen values</p></li> |
| <li><p><strong>eigvec</strong> (<em>3x3 np.array</em>) – Eigen vectors</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.Number"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">Number</code><a class="reference internal" href="../../../_modules/numbers.html#Number"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.Number" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p> |
| <p>All numbers inherit from this class.</p> |
| <p>If you just want to check if an argument x is a number, without |
| caring what kind, use isinstance(x, Number).</p> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.RandomCropAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">RandomCropAug</code><span class="sig-paren">(</span><em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#RandomCropAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.RandomCropAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Make random crop augmenter</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>size</strong> (<em>int</em>) – The length to be set for the shorter edge.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.RandomGrayAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">RandomGrayAug</code><span class="sig-paren">(</span><em class="sig-param">p</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#RandomGrayAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.RandomGrayAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Randomly convert to gray image.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>p</strong> (<em>float</em>) – Probability to convert to grayscale</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.RandomOrderAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">RandomOrderAug</code><span class="sig-paren">(</span><em class="sig-param">ts</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#RandomOrderAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.RandomOrderAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Apply list of augmenters in random order</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>ts</strong> (<em>list of augmenters</em>) – A series of augmenters to be applied in random order</p> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.RandomOrderAug.dumps" title="mxnet.image.RandomOrderAug.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Override the default to avoid duplicate dump.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.RandomOrderAug.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#RandomOrderAug.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.RandomOrderAug.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override the default to avoid duplicate dump.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.RandomSizedCropAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">RandomSizedCropAug</code><span class="sig-paren">(</span><em class="sig-param">size</em>, <em class="sig-param">area</em>, <em class="sig-param">ratio</em>, <em class="sig-param">interp=2</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#RandomSizedCropAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.RandomSizedCropAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Make random crop with random resizing and random aspect ratio jitter augmenter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>size</strong> (<em>tuple of</em><em> (</em><em>int</em><em>, </em><em>int</em><em>)</em>) – Size of the crop formatted as (width, height).</p></li> |
| <li><p><strong>area</strong> (<em>float in</em><em> (</em><em>0</em><em>, </em><em>1</em><em>] or </em><em>tuple of</em><em> (</em><em>float</em><em>, </em><em>float</em><em>)</em>) – If tuple, minimum area and maximum area to be maintained after cropping |
| If float, minimum area to be maintained after cropping, maximum area is set to 1.0</p></li> |
| <li><p><strong>ratio</strong> (<em>tuple of</em><em> (</em><em>float</em><em>, </em><em>float</em><em>)</em>) – Aspect ratio range as (min_aspect_ratio, max_aspect_ratio)</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.ResizeAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">ResizeAug</code><span class="sig-paren">(</span><em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#ResizeAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.ResizeAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Make resize shorter edge to size augmenter.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>size</strong> (<em>int</em>) – The length to be set for the shorter edge.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.SaturationJitterAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">SaturationJitterAug</code><span class="sig-paren">(</span><em class="sig-param">saturation</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#SaturationJitterAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.SaturationJitterAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Random saturation jitter augmentation.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>saturation</strong> (<em>float</em>) – The saturation jitter ratio range, [0, 1]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.image.SequentialAug"> |
| <em class="property">class </em><code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">SequentialAug</code><span class="sig-paren">(</span><em class="sig-param">ts</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#SequentialAug"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.SequentialAug" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.image.image.Augmenter</span></code></p> |
| <p>Composing a sequential augmenter list.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>ts</strong> (<em>list of augmenters</em>) – A series of augmenters to be applied in sequential order.</p> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.image.SequentialAug.dumps" title="mxnet.image.SequentialAug.dumps"><code class="xref py py-obj docutils literal notranslate"><span class="pre">dumps</span></code></a>()</p></td> |
| <td><p>Override the default to avoid duplicate dump.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.image.SequentialAug.dumps"> |
| <code class="sig-name descname">dumps</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#SequentialAug.dumps"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.SequentialAug.dumps" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Override the default to avoid duplicate dump.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.center_crop"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">center_crop</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#center_crop"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.center_crop" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Crops the image <cite>src</cite> to the given <cite>size</cite> by trimming on all four |
| sides and preserving the center of the image. Upsamples if <cite>src</cite> is smaller |
| than <cite>size</cite>.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>This requires MXNet to be compiled with USE_OPENCV.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Binary source image data.</p></li> |
| <li><p><strong>size</strong> (<em>list</em><em> or </em><em>tuple of int</em>) – The desired output image size.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><em>NDArray</em> – The cropped image.</p></li> |
| <li><p><em>Tuple</em> – (x, y, width, height) where x, y are the positions of the crop in the |
| original image and width, height the dimensions of the crop.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 2321x3482x3 @cpu(0)></span> |
| <span class="gp">>>> </span><span class="n">cropped_image</span><span class="p">,</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">height</span><span class="p">)</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">center_crop</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="p">(</span><span class="mi">1000</span><span class="p">,</span> <span class="mi">500</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">cropped_image</span> |
| <span class="go"><NDArray 500x1000x3 @cpu(0)></span> |
| <span class="gp">>>> </span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">height</span> |
| <span class="go">(1241, 910, 1000, 500)</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.color_normalize"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">color_normalize</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">mean</em>, <em class="sig-param">std=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#color_normalize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.color_normalize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Normalize src with mean and std.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Input image</p></li> |
| <li><p><strong>mean</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – RGB mean to be subtracted</p></li> |
| <li><p><strong>std</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – RGB standard deviation to be divided</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the normalized image.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.copyMakeBorder"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">copyMakeBorder</code><span class="sig-paren">(</span><em class="sig-param">src=None</em>, <em class="sig-param">top=_Null</em>, <em class="sig-param">bot=_Null</em>, <em class="sig-param">left=_Null</em>, <em class="sig-param">right=_Null</em>, <em class="sig-param">type=_Null</em>, <em class="sig-param">value=_Null</em>, <em class="sig-param">values=_Null</em>, <em class="sig-param">out=None</em>, <em class="sig-param">name=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.image.copyMakeBorder" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Pad image border with OpenCV.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – source image</p></li> |
| <li><p><strong>top</strong> (<em>int</em><em>, </em><em>required</em>) – Top margin.</p></li> |
| <li><p><strong>bot</strong> (<em>int</em><em>, </em><em>required</em>) – Bottom margin.</p></li> |
| <li><p><strong>left</strong> (<em>int</em><em>, </em><em>required</em>) – Left margin.</p></li> |
| <li><p><strong>right</strong> (<em>int</em><em>, </em><em>required</em>) – Right margin.</p></li> |
| <li><p><strong>type</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default='0'</em>) – Filling type (default=cv2.BORDER_CONSTANT).</p></li> |
| <li><p><strong>value</strong> (<em>double</em><em>, </em><em>optional</em><em>, </em><em>default=0</em>) – (Deprecated! Use <code class="docutils literal notranslate"><span class="pre">values</span></code> instead.) Fill with single value.</p></li> |
| <li><p><strong>values</strong> (<em>tuple of <double></em><em>, </em><em>optional</em><em>, </em><em>default=</em><em>[</em><em>]</em>) – Fill with value(RGB[A] or gray), up to 4 channels.</p></li> |
| <li><p><strong>out</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a><em>, </em><em>optional</em>) – The output NDArray to hold the result.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><strong>out</strong> – The output of this function.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a> or list of NDArrays</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.fixed_crop"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">fixed_crop</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">x0</em>, <em class="sig-param">y0</em>, <em class="sig-param">w</em>, <em class="sig-param">h</em>, <em class="sig-param">size=None</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#fixed_crop"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.fixed_crop" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Crop src at fixed location, and (optionally) resize it to size.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Input image</p></li> |
| <li><p><strong>x0</strong> (<em>int</em>) – Left boundary of the cropping area</p></li> |
| <li><p><strong>y0</strong> (<em>int</em>) – Top boundary of the cropping area</p></li> |
| <li><p><strong>w</strong> (<em>int</em>) – Width of the cropping area</p></li> |
| <li><p><strong>h</strong> (<em>int</em>) – Height of the cropping area</p></li> |
| <li><p><strong>size</strong> (<em>tuple of</em><em> (</em><em>w</em><em>, </em><em>h</em><em>)</em>) – Optional, resize to new size after cropping</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the cropped image.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.imdecode"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">imdecode</code><span class="sig-paren">(</span><em class="sig-param">buf</em>, <em class="sig-param">*args</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#imdecode"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.imdecode" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Decode an image to an NDArray.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p><cite>imdecode</cite> uses OpenCV (not the CV2 Python library). |
| MXNet must have been built with USE_OPENCV=1 for <cite>imdecode</cite> to work.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>buf</strong> (<em>str/bytes/bytearray</em><em> or </em><em>numpy.ndarray</em>) – Binary image data as string or numpy ndarray.</p></li> |
| <li><p><strong>flag</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=1</em>) – 1 for three channel color output. 0 for grayscale output.</p></li> |
| <li><p><strong>to_rgb</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=1</em>) – 1 for RGB formatted output (MXNet default). 0 for BGR formatted output (OpenCV default).</p></li> |
| <li><p><strong>out</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a><em>, </em><em>optional</em>) – Output buffer. Use <cite>None</cite> for automatic allocation.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the image.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 224x224x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| <p>Set <cite>flag</cite> parameter to 0 to get grayscale output</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">,</span> <span class="n">flag</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 224x224x1 @cpu(0)></span> |
| </pre></div> |
| </div> |
| <p>Set <cite>to_rgb</cite> parameter to 0 to get output in OpenCV format (BGR)</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">,</span> <span class="n">to_rgb</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 224x224x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.imread"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">imread</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">*args</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#imread"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.imread" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Read and decode an image to an NDArray.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p><cite>imread</cite> uses OpenCV (not the CV2 Python library). |
| MXNet must have been built with USE_OPENCV=1 for <cite>imdecode</cite> to work.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Name of the image file to be loaded.</p></li> |
| <li><p><strong>flag</strong> (<em>{0</em><em>, </em><em>1}</em><em>, </em><em>default 1</em>) – 1 for three channel color output. 0 for grayscale output.</p></li> |
| <li><p><strong>to_rgb</strong> (<em>bool</em><em>, </em><em>default True</em>) – True for RGB formatted output (MXNet default). |
| False for BGR formatted output (OpenCV default).</p></li> |
| <li><p><strong>out</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a><em>, </em><em>optional</em>) – Output buffer. Use <cite>None</cite> for automatic allocation.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the image.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imread</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">)</span> |
| <span class="go"><NDArray 224x224x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| <p>Set <cite>flag</cite> parameter to 0 to get grayscale output</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imread</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="n">flag</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
| <span class="go"><NDArray 224x224x1 @cpu(0)></span> |
| </pre></div> |
| </div> |
| <p>Set <cite>to_rgb</cite> parameter to 0 to get output in OpenCV format (BGR)</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imread</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">,</span> <span class="n">to_rgb</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
| <span class="go"><NDArray 224x224x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.imresize"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">imresize</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">w</em>, <em class="sig-param">h</em>, <em class="sig-param">*args</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#imresize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.imresize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Resize image with OpenCV.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p><cite>imresize</cite> uses OpenCV (not the CV2 Python library). MXNet must have been built |
| with USE_OPENCV=1 for <cite>imresize</cite> to work.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – source image</p></li> |
| <li><p><strong>w</strong> (<em>int</em><em>, </em><em>required</em>) – Width of resized image.</p></li> |
| <li><p><strong>h</strong> (<em>int</em><em>, </em><em>required</em>) – Height of resized image.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=1</em>) – Interpolation method (default=cv2.INTER_LINEAR). |
| Possible values: |
| 0: Nearest Neighbors Interpolation. |
| 1: Bilinear interpolation. |
| 2: Bicubic interpolation over 4x4 pixel neighborhood. |
| 3: Area-based (resampling using pixel area relation). It may be a |
| preferred method for image decimation, as it gives moire-free |
| results. But when the image is zoomed, it is similar to the Nearest |
| Neighbors method. (used by default). |
| 4: Lanczos interpolation over 8x8 pixel neighborhood. |
| 9: Cubic for enlarge, area for shrink, bilinear for others |
| 10: Random select from interpolation method metioned above. |
| Note: |
| When shrinking an image, it will generally look best with AREA-based |
| interpolation, whereas, when enlarging an image, it will generally look best |
| with Bicubic (slow) or Bilinear (faster but still looks OK). |
| More details can be found in the documentation of OpenCV, please refer to |
| <a class="reference external" href="http://docs.opencv.org/master/da/d54/group__imgproc__transform.html">http://docs.opencv.org/master/da/d54/group__imgproc__transform.html</a>.</p></li> |
| <li><p><strong>out</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a><em>, </em><em>optional</em>) – The output NDArray to hold the result.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><strong>out</strong> – The output of this function.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a> or list of NDArrays</p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpeg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 2321x3482x3 @cpu(0)></span> |
| <span class="gp">>>> </span><span class="n">new_image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="mi">240</span><span class="p">,</span> <span class="mi">360</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">new_image</span> |
| <span class="go"><NDArray 240x360x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.imrotate"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">imrotate</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">rotation_degrees</em>, <em class="sig-param">zoom_in=False</em>, <em class="sig-param">zoom_out=False</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#imrotate"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.imrotate" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Rotates the input image(s) of a specific rotation degree.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Input image (format CHW) or batch of images (format NCHW), |
| in both case is required a float32 data type.</p></li> |
| <li><p><strong>rotation_degrees</strong> (<em>scalar</em><em> or </em><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Wanted rotation in degrees. In case of <cite>src</cite> being a single image |
| a scalar is needed, otherwise a mono-dimensional vector of angles |
| or a scalar.</p></li> |
| <li><p><strong>zoom_in</strong> (<em>bool</em>) – If True input image(s) will be zoomed in a way so that no padding |
| will be shown in the output result.</p></li> |
| <li><p><strong>zoom_out</strong> (<em>bool</em>) – If True input image(s) will be zoomed in a way so that the whole |
| original image will be contained in the output result.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the rotated image(s).</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.is_np_array"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">is_np_array</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/util.html#is_np_array"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.is_np_array" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Checks whether the NumPy-array semantics is currently turned on. |
| This is currently used in Gluon for checking whether an array of type <cite>mxnet.numpy.ndarray</cite> |
| or <cite>mx.nd.NDArray</cite> should be created. For example, at the time when a parameter |
| is created in a <cite>Block</cite>, an <cite>mxnet.numpy.ndarray</cite> is created if this returns true; else |
| an <cite>mx.nd.NDArray</cite> is created.</p> |
| <p>Normally, users are not recommended to use this API directly unless you known exactly |
| what is going on under the hood.</p> |
| <p>Please note that this is designed as an infrastructure for the incoming |
| MXNet-NumPy operators. Legacy operators registered in the modules |
| <cite>mx.nd</cite> and <cite>mx.sym</cite> are not guaranteed to behave like their counterparts |
| in NumPy within this semantics.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Returns</dt> |
| <dd class="field-odd"><p></p> |
| </dd> |
| <dt class="field-even">Return type</dt> |
| <dd class="field-even"><p>A bool value indicating whether the NumPy-array semantics is currently on.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.random_crop"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">random_crop</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#random_crop"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.random_crop" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Randomly crop <cite>src</cite> with <cite>size</cite> (width, height). |
| Upsample result if <cite>src</cite> is smaller than <cite>size</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (Source image <cite>NDArray</cite>) – </p></li> |
| <li><p><strong>size</strong> (Size of the crop formatted as (width, height). If the <cite>size</cite> is larger) – than the image, then the source image is upsampled to <cite>size</cite> and returned.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><em>NDArray</em> – An <cite>NDArray</cite> containing the cropped image.</p></li> |
| <li><p><em>Tuple</em> – A tuple (x, y, width, height) where (x, y) is top-left position of the crop in the |
| original image and (width, height) are the dimensions of the cropped image.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">im</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">cv2</span><span class="o">.</span><span class="n">imread</span><span class="p">(</span><span class="s2">"flower.jpg"</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">cropped_im</span><span class="p">,</span> <span class="n">rect</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">random_crop</span><span class="p">(</span><span class="n">im</span><span class="p">,</span> <span class="p">(</span><span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="nb">print</span> <span class="n">cropped_im</span> |
| <span class="go"><NDArray 100x100x1 @cpu(0)></span> |
| <span class="gp">>>> </span><span class="nb">print</span> <span class="n">rect</span> |
| <span class="go">(20, 21, 100, 100)</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.random_rotate"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">random_rotate</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">angle_limits</em>, <em class="sig-param">zoom_in=False</em>, <em class="sig-param">zoom_out=False</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#random_rotate"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.random_rotate" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Random rotates <cite>src</cite> by an angle included in angle limits.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Input image (format CHW) or batch of images (format NCHW), |
| in both case is required a float32 data type.</p></li> |
| <li><p><strong>angle_limits</strong> (<em>tuple</em>) – Tuple of 2 elements containing the upper and lower limit |
| for rotation angles in degree.</p></li> |
| <li><p><strong>zoom_in</strong> (<em>bool</em>) – If True input image(s) will be zoomed in a way so that no padding |
| will be shown in the output result.</p></li> |
| <li><p><strong>zoom_out</strong> (<em>bool</em>) – If True input image(s) will be zoomed in a way so that the whole |
| original image will be contained in the output result.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An <cite>NDArray</cite> containing the rotated image(s).</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.random_size_crop"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">random_size_crop</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">size</em>, <em class="sig-param">area</em>, <em class="sig-param">ratio</em>, <em class="sig-param">interp=2</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#random_size_crop"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.random_size_crop" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Randomly crop src with size. Randomize area and aspect ratio.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – Input image</p></li> |
| <li><p><strong>size</strong> (<em>tuple of</em><em> (</em><em>int</em><em>, </em><em>int</em><em>)</em>) – Size of the crop formatted as (width, height).</p></li> |
| <li><p><strong>area</strong> (<em>float in</em><em> (</em><em>0</em><em>, </em><em>1</em><em>] or </em><em>tuple of</em><em> (</em><em>float</em><em>, </em><em>float</em><em>)</em>) – If tuple, minimum area and maximum area to be maintained after cropping |
| If float, minimum area to be maintained after cropping, maximum area is set to 1.0</p></li> |
| <li><p><strong>ratio</strong> (<em>tuple of</em><em> (</em><em>float</em><em>, </em><em>float</em><em>)</em>) – Aspect ratio range as (min_aspect_ratio, max_aspect_ratio)</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method. See resize_short for details.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><em>NDArray</em> – An <cite>NDArray</cite> containing the cropped image.</p></li> |
| <li><p><em>Tuple</em> – A tuple (x, y, width, height) where (x, y) is top-left position of the crop in the |
| original image and (width, height) are the dimensions of the cropped image.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.resize_short"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">resize_short</code><span class="sig-paren">(</span><em class="sig-param">src</em>, <em class="sig-param">size</em>, <em class="sig-param">interp=2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#resize_short"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.resize_short" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Resizes shorter edge to size.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p><cite>resize_short</cite> uses OpenCV (not the CV2 Python library). |
| MXNet must have been built with OpenCV for <cite>resize_short</cite> to work.</p> |
| </div> |
| <p>Resizes the original image by setting the shorter edge to size |
| and setting the longer edge accordingly. |
| Resizing function is called from OpenCV.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src</strong> (<a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The original image.</p></li> |
| <li><p><strong>size</strong> (<em>int</em>) – The length to be set for the shorter edge.</p></li> |
| <li><p><strong>interp</strong> (<em>int</em><em>, </em><em>optional</em><em>, </em><em>default=2</em>) – Interpolation method used for resizing the image. |
| Possible values: |
| 0: Nearest Neighbors Interpolation. |
| 1: Bilinear interpolation. |
| 2: Bicubic interpolation over 4x4 pixel neighborhood. |
| 3: Area-based (resampling using pixel area relation). It may be a |
| preferred method for image decimation, as it gives moire-free |
| results. But when the image is zoomed, it is similar to the Nearest |
| Neighbors method. (used by default). |
| 4: Lanczos interpolation over 8x8 pixel neighborhood. |
| 9: Cubic for enlarge, area for shrink, bilinear for others |
| 10: Random select from interpolation method metioned above. |
| Note: |
| When shrinking an image, it will generally look best with AREA-based |
| interpolation, whereas, when enlarging an image, it will generally look best |
| with Bicubic (slow) or Bilinear (faster but still looks OK). |
| More details can be found in the documentation of OpenCV, please refer to |
| <a class="reference external" href="http://docs.opencv.org/master/da/d54/group__imgproc__transform.html">http://docs.opencv.org/master/da/d54/group__imgproc__transform.html</a>.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>An ‘NDArray’ containing the resized image.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><a class="reference internal" href="../../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a></p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"flower.jpeg"</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">str_image</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="n">image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">str_image</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">image</span> |
| <span class="go"><NDArray 2321x3482x3 @cpu(0)></span> |
| <span class="gp">>>> </span><span class="n">size</span> <span class="o">=</span> <span class="mi">640</span> |
| <span class="gp">>>> </span><span class="n">new_image</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">resize_short</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="n">size</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">new_image</span> |
| <span class="go"><NDArray 2321x3482x3 @cpu(0)></span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="mxnet.image.scale_down"> |
| <code class="sig-prename descclassname">mxnet.image.</code><code class="sig-name descname">scale_down</code><span class="sig-paren">(</span><em class="sig-param">src_size</em>, <em class="sig-param">size</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/image/image.html#scale_down"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.image.scale_down" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Scales down crop size if it’s larger than image size.</p> |
| <p>If width/height of the crop is larger than the width/height of the image, |
| sets the width/height to the width/height of the image.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>src_size</strong> (<em>tuple of int</em>) – Size of the image in (width, height) format.</p></li> |
| <li><p><strong>size</strong> (<em>tuple of int</em>) – Size of the crop in (width, height) format.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p>A tuple containing the scaled crop size in (width, height) format.</p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>tuple of int</p> |
| </dd> |
| </dl> |
| <p class="rubric">Example</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">src_size</span> <span class="o">=</span> <span class="p">(</span><span class="mi">640</span><span class="p">,</span><span class="mi">480</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">size</span> <span class="o">=</span> <span class="p">(</span><span class="mi">720</span><span class="p">,</span><span class="mi">120</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">new_size</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">img</span><span class="o">.</span><span class="n">scale_down</span><span class="p">(</span><span class="n">src_size</span><span class="p">,</span> <span class="n">size</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">new_size</span> |
| <span class="go">(640,106)</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </div> |
| |
| |
| <hr class="feedback-hr-top" /> |
| <div class="feedback-container"> |
| <div class="feedback-question">Did this page help you?</div> |
| <div class="feedback-answer-container"> |
| <div class="feedback-answer yes-link" data-response="yes">Yes</div> |
| <div class="feedback-answer no-link" data-response="no">No</div> |
| </div> |
| <div class="feedback-thank-you">Thanks for your feedback!</div> |
| </div> |
| <hr class="feedback-hr-bottom" /> |
| </div> |
| <div class="side-doc-outline"> |
| <div class="side-doc-outline--content"> |
| </div> |
| </div> |
| |
| <div class="clearer"></div> |
| </div><div class="pagenation"> |
| <a id="button-prev" href="../executor_manager/index.html" class="mdl-button mdl-js-button mdl-js-ripple-effect mdl-button--colored" role="botton" accesskey="P"> |
| <i class="pagenation-arrow-L fas fa-arrow-left fa-lg"></i> |
| <div class="pagenation-text"> |
| <span class="pagenation-direction">Previous</span> |
| <div>mxnet.executor_manager</div> |
| </div> |
| </a> |
| <a id="button-next" href="../io/index.html" class="mdl-button mdl-js-button mdl-js-ripple-effect mdl-button--colored" role="botton" accesskey="N"> |
| <i class="pagenation-arrow-R fas fa-arrow-right fa-lg"></i> |
| <div class="pagenation-text"> |
| <span class="pagenation-direction">Next</span> |
| <div>mxnet.io</div> |
| </div> |
| </a> |
| </div> |
| <footer class="site-footer h-card"> |
| <div class="wrapper"> |
| <div class="row"> |
| <div class="col-4"> |
| <h4 class="footer-category-title">Resources</h4> |
| <ul class="contact-list"> |
| <li><a class="u-email" href="mailto:dev@mxnet.apache.org">Dev list</a></li> |
| <li><a class="u-email" href="mailto:user@mxnet.apache.org">User mailing list</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> |
| <li><a href="https://issues.apache.org/jira/projects/MXNET/issues">Jira Tracker</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/labels/Roadmap">Github Roadmap</a></li> |
| <li><a href="https://medium.com/apache-mxnet">Blog</a></li> |
| <li><a href="https://discuss.mxnet.io">Forum</a></li> |
| <li><a href="/community/contribute">Contribute</a></li> |
| |
| </ul> |
| </div> |
| |
| <div class="col-4"><ul class="social-media-list"><li><a href="https://github.com/apache/incubator-mxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#github"></use></svg> <span class="username">apache/incubator-mxnet</span></a></li><li><a href="https://www.twitter.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#twitter"></use></svg> <span class="username">apachemxnet</span></a></li><li><a href="https://youtube.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#youtube"></use></svg> <span class="username">apachemxnet</span></a></li></ul> |
| </div> |
| |
| <div class="col-4 footer-text"> |
| <p>A flexible and efficient library for deep learning.</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| <footer class="site-footer2"> |
| <div class="wrapper"> |
| <div class="row"> |
| <div class="col-3"> |
| <img src="../../../_static/apache_incubator_logo.png" class="footer-logo col-2"> |
| </div> |
| <div class="footer-bottom-warning col-9"> |
| <p>Apache MXNet is an effort undergoing incubation at <a href="http://www.apache.org/">The Apache Software Foundation</a> (ASF), <span style="font-weight:bold">sponsored by the <i>Apache Incubator</i></span>. Incubation is required |
| of all newly accepted projects until a further review indicates that the infrastructure, |
| communications, and decision making process have stabilized in a manner consistent with other |
| successful ASF projects. While incubation status is not necessarily a reflection of the completeness |
| or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. |
| </p><p>"Copyright © 2017-2018, The Apache Software Foundation Apache MXNet, MXNet, Apache, the Apache |
| feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the |
| Apache Software Foundation."</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| </body> |
| </html> |