16 lines
1 KiB
Text
16 lines
1 KiB
Text
runnning on cuda:0
|
|
|
|
0%| | 0/4000 [00:00<?, ?it/s]
|
|
Traceback (most recent call last):
|
|
File "mnist_classifier.py", line 59, in <module>
|
|
output = net(X.view(-1, 784)) # pass in the reshaped batch (recall they are 28x28 atm)
|
|
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__
|
|
result = self.forward(*input, **kwargs)
|
|
File "mnist_classifier.py", line 34, in forward
|
|
x = F.relu(self.fc1(x))
|
|
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in __call__
|
|
result = self.forward(*input, **kwargs)
|
|
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/linear.py", line 87, in forward
|
|
return F.linear(input, self.weight, self.bias)
|
|
File "/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py", line 1370, in linear
|
|
ret = torch.addmm(bias, input, weight.t())
|
|
RuntimeError: Expected object of device type cuda but got device type cpu for argument #2 'mat1' in call to _th_addmm
|