[FIXED] How to fix incorrect channel size in pytorch neural network?

Issue

I'm working with the Google utterance dataset in spectrogram form. Each data point has dimension (160, 101). In my data loader, I used batch_size=128. Therefore, each batch has dimension (128, 160, 101).

I use a LeNet model with the following code as the model:

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1   = nn.Linear(16*5*5, 120)
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 30)

    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = F.max_pool2d(out, 2)
        out = F.relu(self.conv2(out))
        out = F.max_pool2d(out, 2)
        out = out.view(out.size(0), -1)
        out = F.relu(self.fc1(out))
        out = F.relu(self.fc2(out))
        out = self.fc3(out)
        return out

I tried unsqueezing the data with dim=3, but got this error:

Traceback (most recent call last):
  File "train_speech.py", line 359, in <module>
    train_loss, reg_loss, train_acc, cost = train(epoch)
  File "train_speech.py", line 258, in train
    outputs = (net(inputs))['out']
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/content/gdrive/My Drive/Colab Notebooks/mixup_erm-master/models/lenet.py", line 15, in forward
    out = F.relu(self.conv1(x))
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 443, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 440, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [6, 1, 5, 5], expected input[128, 160, 101, 1] to have 1 channels, but got 160 channels instead

How do I fix this issue?

---

EDIT: New Error Message Below

torch.Size([128, 160, 101])
torch.Size([128, 1, 160, 101])
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /pytorch/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
Traceback (most recent call last):
  File "train_speech.py", line 363, in <module>
    train_loss, reg_loss, train_acc, cost = train(epoch)
  File "train_speech.py", line 262, in train
    outputs = (net(inputs))['out']
IndexError: too many indices for tensor of dimension 2

I'm unsqueezing the data in each batch. The relevant section of my training code is below. inputs is analogous to x.

print(inputs.shape)
inputs = inputs.unsqueeze(1)
print(inputs.shape)
outputs = (net(inputs))['out']

---

Edit 2: New Error

Traceback (most recent call last):
  File "train_speech.py", line 361, in <module>
    train_loss, reg_loss, train_acc, cost = train(epoch)
  File "train_speech.py", line 270, in train
    loss.backward()
  File "/usr/local/lib/python3.7/dist-packages/torch/_tensor.py", line 255, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
  File "/usr/local/lib/python3.7/dist-packages/torch/autograd/__init__.py", line 149, in backward
    allow_unreachable=True, accumulate_grad=True)  # allow_unreachable flag
RuntimeError: Function AddmmBackward returned an invalid gradient at index 1 - got [128, 400] but expected shape compatible with [128, 13024]

---

Edit 3: Train Loop Below

def train(epoch):
    print('\nEpoch: %d' % epoch)
    net.train()
    train_loss = 0
    reg_loss = 0
    correct = 0
    total = 0
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        if use_cuda:
            inputs, targets = inputs.cuda(), targets.cuda()
        inputs, targets_a, targets_b, lam,layer, cost = mixup_data(inputs, targets,
                                                       args.alpha,args.mixupBatch, use_cuda)
        inputs, targets_a, targets_b = map(Variable, (inputs,
                                                      targets_a, targets_b))
        outputs = net(inputs)
        loss = mixup_criterion(criterion, outputs, targets_a, targets_b, lam)
    
        train_loss += loss.item()
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += (lam * predicted.eq(targets_a.data).cpu().sum().float()
                    + (1 - lam) * predicted.eq(targets_b.data).cpu().sum().float())
    
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    return (train_loss/batch_idx, reg_loss/batch_idx, 100.*correct/total, cost/batch_idx)

Solution

You should expand on axis=1 a.k.a. the channel axis:

>>> x = x.unsqueeze(1)

If you're inside the dataset __getitem__, then it corresponds to axis=0.

Answered By - Ivan