docs/static_site/src/pages/features.html

---
layout: page
title: Features
subtitle: Whether you are looking for a flexible library to quickly develop cutting-edge deep learning research or a robust framework to push production workload, MXNet caters to all needs.
permalink: /features/
action: Get Started
action_url: /get_started
---

<!-- HYBRID FRONTEND -->
<div class="row">
    <div class="col-12">
        <h3 class="feature-title">Hybrid Front-End</h3>
    </div>
    <div class="col-5">
        <p class="feature-paragraph">The Gluon Python API lets you use MXNet in a fully imperative manner. It also
            allows you to simply switch to
            symbolic mode by calling the <a
                    href="{{'/api/python/docs/tutorials/packages/gluon/hybridize' | relative_url}}">hybridize</a>
            functionality. The symbolic execution provides faster and more optimized
            execution as well as the ability to export the network for inference in different language bindings like
            java or C++.
        </p>
    </div>
    <div class="col-1">

    </div>
    <div class="col-6 code-block">
        {% highlight python %}
net = model_zoo.vision.resnet50_v2(pretrained=True)
net.hybridize()

dummy_input = mx.nd.ones(shape=(1,3,224,224))
net(dummy_input)

net.export("symbolic_resnet50")
        {% endhighlight %}
    </div>
</div>

<!-- DISTRIBUTED TRAINING -->
<br>
<br>
<div class="row ">
    <div class="col-7"></div>
    <div class="col-5">
        <h3 class="feature-title">Distributed Training</h3>
    </div>

    <div class="col-6 code-block">
        {% highlight python %}
import horovod.mxnet as hvd

# Horovod: initialize Horovod
hvd.init()

# Horovod: pin a GPU to be used to local rank
context = mx.gpu(hvd.local_rank())
        {% endhighlight %}
    </div>

    <div class="col-1"></div>
    <div class="col-5">
        <p class="feature-paragraph">MXNet allows you to make the most out of your hardware, whether it is multi-gpu or
            multi-host training with near-linear scaling efficiency. MXNet recently introduced support for
            <a href="https://medium.com/apache-mxnet/distributed-training-using-apache-mxnet-with-horovod-44f98bf0e7b7">Horovod</a>,
            the distributed learning framework developed by Uber.
        </p>
    </div>
</div>


<!-- 8 Language Bindings -->
<br><br>
<div class="row">
    <div class="col-12">
        <h3 class="feature-title">8 Language Bindings</h3>
    </div>
    <div class="col-5">
        <p class="feature-paragraph">Deep integration into Python and support for Scala, Julia, Clojure, Java, C++, R
            and Perl.
            Combined with the hybridization feature, this allows a very smooth transition from Python training to
            deployment
            in the language of your choice to shorten the time to production.
        </p>
    </div>
    <div class="col-1">

    </div>
    <div class="col-6 code-block">
        {% highlight java %}
import org.apache.mxnet.javaapi.*;
...
List
<DataDesc> inputDesc = new ArrayList<>();
Shape inputShape = new Shape(new int[]{1, 3, 224, 224});
inputDesc.add(new DataDesc("data", inputShape, DType.Float32(), "NCHW"));
Predictor predictor = new Predictor(inst.modelPathPrefix, inputDesc, context,0);
...
float[][] result = predictor.predict(new float[][]{img.toArray()});
            {% endhighlight %}
    </div>
</div>


</div>