CNTK Examples: Image/Classification/VGG

Python

VGG16_ImageNet_Distributed.py

This is the VGG model that contains 16 layers, which was referred as ConvNet configuration D in the original paper.

Run the example from the current folder using:

python VGG16_ImageNet_Distributed.py

To run it in a distributed manner, please check here. For example, the command for distributed training on the same machine (with multiple GPUs) with Windows is:

mpiexec -n <#workers> python VGG16_ImageNet_Distributed.py

VGG19_ImageNet_Distributed.py

This is the VGG model that contains 19 layers, which was referred as ConvNet configuration E in the original paper.

Run the example from the current folder using:

python VGG19_ImageNet_Distributed.py

To run it in a distributed manner, please check here. For example, the command for distributed training on the same machine (with multiple GPUs) with Windows is:

mpiexec -n <#workers> python VGG19_ImageNet_Distributed.py