I converted the googlenet (inception_v1) model from Torch to Pytorch using https://github.com/clcarwin/convert_torch_to_pytorch and trying to run the imagenet validation (https://github.com/pytorch/examples/blob/master/imagenet/main.py) but I am getting the following error:
Traceback (most recent call last):
File “main.py”, line 287, in
main()
File “main.py”, line 122, in main
validate(val_loader, model, criterion)
File “main.py”, line 211, in validate
output = model(input_var)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 206, in call
result = self.forward(*input, **kwargs)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py”, line 61, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py”, line 71, in parallel_apply
return parallel_apply(replicas, inputs, kwargs)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py”, line 46, in parallel_apply
raise output
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py”, line 25, in _worker
output = module(*input, **kwargs)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 206, in call
result = self.forward(*input, **kwargs)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/modules/container.py”, line 64, in forward
input = module(input)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 206, in call
result = self.forward(input, **kwargs)
File “/media/me/E/pytorch_examples/example7_imagenet/googlenet_v1.py”, line 19, in forward
return self.lambda_func(self.forward_prepare(input))
File “/media/me/E/pytorch_examples/example7_imagenet/googlenet_v1.py”, line 34, in
Lambda(lambda x,lrn=torch.legacy.nn.SpatialCrossMapLRN((11, 0.00109999999404, 0.5, 2)): Variable(lrn.forward(x.data))),
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/legacy/nn/Module.py”, line 33, in forward
return self.updateOutput(input)
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/legacy/nn/SpatialCrossMapLRN.py”, line 25, in updateOutput
self._backend.SpatialCrossMapLRN_updateOutput(
File “/home/me/anaconda3/lib/python3.6/site-packages/torch/_thnn/utils.py”, line 22, in getattr
raise NotImplementedError
NotImplementedError
Looks like Pytorch doesn’t have SpatialCrossMapLRN (Torch Architecture in Pytorch). Is there any work-around for this?
OR anybody has pretrained model for inception-v1 in Pytorch?