Revision e1467a79dc6580ae009d827b5e6f274faff3b339 authored by liqunfu on 27 March 2020, 21:42:04 UTC, committed by GitHub on 27 March 2020, 21:42:04 UTC
support Pooling ops with Sequence axis
README.md
# CNTK Examples: Image/Classification/VGG
## Overview
|Data: |The ILSVRC2012 dataset (http://www.image-net.org/challenges/LSVRC/2012/) for image classification.
|:---------|:---
|Purpose |This folder contains examples that demonstrate how to use CNTK to define VGG network (https://arxiv.org/abs/1409.1556) for image classification.
|Network |VGG.
|Training |Stochastic gradient descent with momentum.
|Comments |See below.
## Running the example
### Getting the data
We use the ILSVRC2012 datasets to demonstrate how to train the VGG model which was developed by the [Visual Geometry Group in University of Oxford](http://www.robots.ox.ac.uk/~vgg/research/very_deep/). It won the second place in the ILSVRC-2014 challenge. VGG has been a very popular model for its simple architect and high accuracy.
ILSVRC2012 datasets are not included in the CNTK distribution. You may obtain it through http://image-net.org.
## Details
We give examples for both Python and BrainScript.
### [Python](./Python)
### [BrainScript](./BrainScript)
## Pre-trained Models
Pre-trained VGG models can be found [here](../../../../PretrainedModels/Image.md#vgg).
Computing file changes ...