N
Nikita
Ребят , подскажите в чём проблема
Train Epoch: 0 [0/22500 (0%)] Loss: 0.690619
Train Epoch: 0 [6400/22500 (28%)] Loss: 0.665732
Train Epoch: 0 [12800/22500 (57%)] Loss: 0.708257
Train Epoch: 0 [19200/22500 (85%)] Loss: 0.710413
Traceback (most recent call last):
File "/root/test/main.py", line 118, in <module>
trainer.test()
File "/root/test/main.py", line 81, in test
output = self.net(data)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/root/test/model.py", line 43, in forward
x = F.relu(self.conv1(x))
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/conv.py", line 345, in forward
return self.conv2d_forward(input, self.weight)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/conv.py", line 341, in conv2d_forward
return F.conv2d(input, weight, self.bias, self.stride,
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
root@39950:~/Cats-and-Dogs-classification/data# pip install torch.FloatTensor
Collecting torch.FloatTensor
Train Epoch: 0 [0/22500 (0%)] Loss: 0.690619
Train Epoch: 0 [6400/22500 (28%)] Loss: 0.665732
Train Epoch: 0 [12800/22500 (57%)] Loss: 0.708257
Train Epoch: 0 [19200/22500 (85%)] Loss: 0.710413
Traceback (most recent call last):
File "/root/test/main.py", line 118, in <module>
trainer.test()
File "/root/test/main.py", line 81, in test
output = self.net(data)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/root/test/model.py", line 43, in forward
x = F.relu(self.conv1(x))
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/conv.py", line 345, in forward
return self.conv2d_forward(input, self.weight)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/conv.py", line 341, in conv2d_forward
return F.conv2d(input, weight, self.bias, self.stride,
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
root@39950:~/Cats-and-Dogs-classification/data# pip install torch.FloatTensor
Collecting torch.FloatTensor
выбираю колличесво эпох , считает всё нормально , но в конце падает
