[GitHub] ThomasDelteil commented on a change in pull request #10283: [MXNET-242][Tutorial] Fine-tuning ONNX model in Gluon

[GitBox <gi...@apache.org>]

ThomasDelteil commented on a change in pull request #10283: [MXNET-242][Tutorial] Fine-tuning ONNX model in Gluon
URL: https://github.com/apache/incubator-mxnet/pull/10283#discussion_r177922138
 
 

 ##########
 File path: docs/tutorials/onnx/fine_tuning_gluon.md
 ##########
 @@ -0,0 +1,441 @@
+
+# Fine-tuning an ONNX model with MXNet/Gluon
+
+Fine-tuning is a common practice in Transfer Learning. One can take advantage of the pre-trained weights of a network, and use them as an initializer for their own task. Indeed, quite often it is difficult to gather a dataset large enough that it would allow training from scratch deep and complex networks such as ResNet152 or VGG16. For example in an image classification task, using a network trained on a large dataset like ImageNet gives a good base from which the weights can be slightly updated, or fine-tuned, to predict accurately the new classes. We will see in this tutorial that this can be achieved even with a relatively small number of new training examples.
+
+
+[Open Neural Network Exchange (ONNX)](https://github.com/onnx/onnx) provides an open source format for AI models. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.
+
+In this tutorial we will:
+    
+- learn how to pick a specific layer from a pre-trained .onnx model file
+- learn how to load this model in Gluon and fine-tune it on a different dataset
+
+## Pre-requisite
+
+To run the tutorial you will need to have installed the following python modules:
+- [MXNet](http://mxnet.incubator.apache.org/install/index.html)
+- [onnx](https://github.com/onnx/onnx)
+- matplotlib
+- wget
 
 Review comment:
   Sounds like a good idea

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services