Resnet18 model weights issues when running on multi-GPU system.

Hello Johnson,

Thank you for the nice tutorial.
I was able to change the code in cnn-benchmarks.lua to run it for multi-GPU system(8 GPU).
It gave me a speed-up of 3x.

I am facing issues with "Resnet-x" model weights. I am able to work with the Alexnet, Googlenet, VGG16 and VGG19 model weights but Resnet is giving me problem for 224x224 image size.

Can you please let me know about it.

Also, I am not able to find model weight for inception-V3 graph. Can you add the Inception V3 to the models folder.

Thank you for your help.

Regards,
Bhushan

Start with cnn-benchmarks.lua and inspect how the Resnet-x model weights are loaded for 224x224 images on a multi-GPU system. Then review the models folder and the existing model-weight entries, including the request for an Inception V3 graph. Done means the Resnet weights work for the reported image size and the requested Inception V3 model weights are available.

Written by the indexing model from the issue text.