Error while training CANNET

[MagazzuGaetano]

[NWPU DATASET]: 3109 training images.
[NWPU DATASET]: 500 validation images.
dataset preparation finished!
training has started!
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2973: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:1569: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.
warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.")
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py:432: UserWarning: Using a target size (torch.Size([4, 576, 768])) that is different to the input size (torch.Size([4, 72, 96])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
return F.mse_loss(input, target, reduction=self.reduction)
Traceback (most recent call last):
File "train.py", line 34, in
cc_trainer.forward()
File "/content/drive/My Drive/Stage Crowd Counting/NPWU-CROWD/trainer.py", line 66, in forward
self.train()
File "/content/drive/My Drive/Stage Crowd Counting/NPWU-CROWD/trainer.py", line 102, in train
pred_map, _ = self.net(img, gt_map)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/content/drive/My Drive/Stage Crowd Counting/NPWU-CROWD/models/CC.py", line 35, in forward
self.loss_mse= self.build_loss(density_map.squeeze(), gt_map.squeeze())
File "/content/drive/My Drive/Stage Crowd Counting/NPWU-CROWD/models/CC.py", line 39, in build_loss
loss_mse = self.loss_mse_fn(density_map, gt_data)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py", line 432, in forward
return F.mse_loss(input, target, reduction=self.reduction)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py", line 2542, in mse_loss
expanded_input, expanded_target = torch.broadcast_tensors(input, target)
File "/usr/local/lib/python3.6/dist-packages/torch/functional.py", line 62, in broadcast_tensors
return _VF.broadcast_tensors(tensors)
RuntimeError: The size of tensor a (96) must match the size of tensor b (768) at non-singleton dimension 2

[msn199959]

I have the same question, how to solve it?