Exercise 02_pytorch_classification shape error : ValueError: Expected input batch_size (300) to match target batch_size (240).

[rajsahu2004]

In the cell 21 of my notebook in the training loop I am getting mismatch in the shape of y_logits which should be [240,4] but it is showing [300,4] which is the considering the whole training dataset but I am using X_train for the training whose shape is [240,2].

Link for the notebook github link

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-21-18a35cc52119> in <cell line: 4>()
     12   y_pred = torch.softmax(y_logits,dim=1).argmax(dim=1)
     13   # 2. Calculate the loss
---> 14   loss = loss_func(y_logits,y_train)
     15   acc = acc_func(y_pred,y_train)
     16   # 3. Optimizer zero grad

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in _wrapped_call_impl(self, *args, **kwargs)
   1516             return self._compiled_call_impl(*args, **kwargs)  # type: ignore[misc]
   1517         else:
-> 1518             return self._call_impl(*args, **kwargs)
   1519 
   1520     def _call_impl(self, *args, **kwargs):

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
   1525                 or _global_backward_pre_hooks or _global_backward_hooks
   1526                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1527             return forward_call(*args, **kwargs)
   1528 
   1529         try:

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
   1177 
   1178     def forward(self, input: Tensor, target: Tensor) -> Tensor:
-> 1179         return F.cross_entropy(input, target, weight=self.weight,
   1180                                ignore_index=self.ignore_index, reduction=self.reduction,
   1181                                label_smoothing=self.label_smoothing)

/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
   3051     if size_average is not None or reduce is not None:
   3052         reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 3053     return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
   3054 
   3055 

ValueError: Expected input batch_size (300) to match target batch_size (240).

[shisirkha]

I think it's a problem with your input shape in subclassing nn.Module

Please give me the code for your neural network