integration-tests/examples/test_templates/deeplearning/template_caffe.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "# Make sure that caffe is on the python path:\n",
    "caffe_root = './'  # this file is expected to be in {caffe_root}/examples\n",
    "import sys\n",
    "sys.path.insert(0, caffe_root + 'python')\n",
    "\n",
    "import caffe\n",
    "\n",
    "# configure plotting\n",
    "plt.rcParams['figure.figsize'] = (10, 10)\n",
    "plt.rcParams['image.interpolation'] = 'nearest'\n",
    "plt.rcParams['image.cmap'] = 'gray'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the net, list its data and params, and filter an example image.\n",
    "caffe.set_mode_gpu()\n",
    "net = caffe.Net('test_templates/conv.prototxt', caffe.TEST)\n",
    "print(\"blobs {}\\nparams {}\".format(net.blobs.keys(), net.params.keys()))\n",
    "\n",
    "# load image and prepare as a single input batch for Caffe\n",
    "im = np.array(caffe.io.load_image('test_templates/cat_gray.jpg', color=False)).squeeze()\n",
    "plt.title(\"original image\")\n",
    "plt.imshow(im)\n",
    "plt.axis('off')\n",
    "\n",
    "im_input = im[np.newaxis, np.newaxis, :, :]\n",
    "net.blobs['data'].reshape(*im_input.shape)\n",
    "net.blobs['data'].data[...] = im_input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# helper show filter outputs\n",
    "def show_filters(net):\n",
    "    net.forward()\n",
    "    plt.figure()\n",
    "    filt_min, filt_max = net.blobs['conv'].data.min(), net.blobs['conv'].data.max()\n",
    "    for i in range(3):\n",
    "        plt.subplot(1,4,i+2)\n",
    "        plt.title(\"filter #{} output\".format(i))\n",
    "        plt.imshow(net.blobs['conv'].data[0, i], vmin=filt_min, vmax=filt_max)\n",
    "        plt.tight_layout()\n",
    "        plt.axis('off')\n",
    "\n",
    "# filter the image with initial \n",
    "show_filters(net)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "KERNEL_NAME"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}