mmathew23 / lag-pytorch Goto Github PK

How to open the samples.pt file to view the output?

thanks for your work ,i want use your git to train my dataset, may i get the command of training ?

From the model.py, I'm getting the following error.
Error code
2021-03-05 16:06:53.115048: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
Traceback (most recent call last):
File "train.py", line 109, in
fire.Fire(train)
File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 471, in _Fire
target=component.name)
File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 681, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "train.py", line 103, in train
n_iter = model.train(dataloader, epochs, lr, wass_target, mse_weight, ttur)
File "/content/LAG-Pytorch/model.py", line 391, in train
fake = self.G(lores, eps=torch.zeros_like(eps))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/content/LAG-Pytorch/model.py", line 169, in forward
x = self.conv1(torch.cat([x, eps], dim=1))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(input, **kwargs)
File "/content/LAG-Pytorch/model.py", line 64, in forward
return self.activation(self.conv2d_forward(x, self.scaleself.weight))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 779, in getattr
type(self).name, name))
torch.nn.modules.module.ModuleAttributeError: 'ScaledConv2dWithAct' object has no attribute 'conv2d_forward'