RuntimeError: output with shape [1, 256, 192] doesn't match the broadcast shape [3, 256, 192]

[17sushmita]

Getting this error while running train_gmm.py

Namespace(batch_size=16, data_root='data', fine_height=256, fine_width=192, gpu_id='0', grid_size=5, log_freq=100, n_epoch=100, n_worker=16, name='GMM', out_dir='../result', radius=5)
Loading dataset
Building GMM model
Total Parameters: 19057650
Start training GMM
0% 0/100 [00:00<?, ?it/s]Epoch: 0

epoch: 0: 0% 0/1 [00:00<?, ?it/s]
0% 0/100 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train_gmm.py", line 140, in
main()
File "train_gmm.py", line 127, in main
loss = trainer.train(epoch)
File "train_gmm.py", line 33, in train
return self.iteration(epoch, self.dataloader_train)
File "train_gmm.py", line 45, in iteration
for i, _data in data_iter:
File "/usr/local/lib/python3.6/dist-packages/tqdm/std.py", line 1104, in iter
for obj in iterable:
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/usr/local/lib/python3.6/dist-packages/torch/_utils.py", line 395, in reraise
raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/content/drive/My Drive/viton-gan/viton_gan/dataset.py", line 155, in getitem
data = self._get_item_base(index)
File "/content/drive/My Drive/viton-gan/viton_gan/dataset.py", line 103, in get_item_base
feature_shape_tensor = self.transform(self.downsample(shape_im)) # [-1,1]
File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/transforms.py", line 61, in call
img = t(img)
File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/transforms.py", line 166, in call
return F.normalize(tensor, self.mean, self.std, self.inplace)
File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/functional.py", line 208, in normalize
tensor.sub(mean).div(std)
RuntimeError: output with shape [1, 256, 192] doesn't match the broadcast shape [3, 256, 192]

epoch: 0: 0% 0/1 [00:00<?, ?it/s]

[Naveen-Nanda]

Has this problem been fixed?

[tasinislam21]

I had this problem before but on a different repository. I fixed it by using a specific version of PyTorch. Use pytorch 0.4.1 and torchvision 0.2.1