e-lab/ENet-training

CPU Implementation

Closed this issue · 1 comments

Deleted user commented

Hi, I would like to use this for segmenting images on CPU. I tried to run the trained classifier to segment one of the image, by taking out the Cuda line in demo.lua. But the model shows requirement for cuda. Is there some option to run it?

Thanks

codeAC29 commented

@sethitanmay the model provided was trained using cuda. So, you will have to convert cudnn modules into nn modules in order to be able to use them in CPU.
This can be done by:

model = torch.load('trained/model/path/model.net')
cudnn.convert(model, nn)