I am trying to train the model but getting error
RuntimeError: The size of tensor a (7) must match the size of tensor b (6) at non-singleton dimension 2
have the model with the following shapes
(Pdb) for _params in model.parameters(): print (_params.data.shape)
torch.Size([16, 1, 7, 7])
torch.Size([16])
torch.Size([16])
torch.Size([16])
torch.Size([16])
torch.Size([16])
torch.Size([8, 16, 1, 1])
torch.Size([8])
torch.Size([8])
torch.Size([8])
torch.Size([8, 8, 3, 3])
torch.Size([8])
torch.Size([8])
torch.Size([8])
torch.Size([16, 8, 1, 1])
torch.Size([16])
torch.Size([16])
torch.Size([16])
torch.Size([8, 16, 1, 1])
torch.Size([8])
torch.Size([8])
torch.Size([8])
torch.Size([8, 8, 3, 3])
torch.Size([8])
torch.Size([8])
torch.Size([8])
torch.Size([16, 8, 1, 1])
torch.Size([16])
my input have the shape [331, 1, 240 ,320]
I am trying to find the error using the following code
optimizer = lib.optim.SGD(model.parameters(), lr=0.035, momentum=1)
criterion = lib.torch.nn.MSELoss()
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
err += loss.item()
I am getting the following error .
==> training: (gpu 1, num_gpus 1)
==> online epoch # 0 [batchSize = 16] [learningRate = [0.001]]
Traceback (most recent call last):
File "deep_nets.py", line 119, in <module>
lib.trainEpoch(tr, _conf.model_dirname +'/results_tr', _conf, mconf, model, epoch=i)
File "pytorch-0.4/torch_2_pytorch/lib/train.py", line 76, in trainEpoch
outputs = model(inputs)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "pytorch-0.4/torch_2_pytorch/helper.py", line 68, in forward
y = self._modules[str(mx)](x[mx])
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "pytorch-0.4/torch_2_pytorch/helper.py", line 68, in forward
y = self._modules[str(mx)](x[mx])
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "pytorch-0.4/torch_2_pytorch/helper.py", line 68, in forward
y = self._modules[str(mx)](x[mx])
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "anaconda3/envs/pytorch04/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
result = self.forward(*input, **kwargs)
File "pytorch-0.4/torch_2_pytorch/helper.py", line 27, in forward
return sum(x)
RuntimeError: The size of tensor a (7) must match the size of tensor b (6) at non-singleton dimension 2
Please help me out …