Error while running classifier.py on custom set

[pngmafia]

Getting this error while running the classifier.py script on custom dataset.

Image sizes 64 train, 64 test
Using 4 dataloader workers
Logging results to runs/train/exp7
Starting training for 1 epochs...

epoch     gpu_mem   train_loss  val_loss    accuracy    
  0%|                                                                                         | 0/165 [00:02<?, ?it/s]
Traceback (most recent call last):
  File "classifier.py", line 241, in <module>
    train()
  File "classifier.py", line 125, in train
    for i, (images, labels) in pbar:
  File "/opt/conda/lib/python3.8/site-packages/tqdm/std.py", line 1193, in __iter__
    for obj in iterable:
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 518, in __next__
    data = self._next_data()
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1200, in _next_data
    return self._process_data(data)
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1226, in _process_data
    data.reraise()
  File "/opt/conda/lib/python3.8/site-packages/torch/_utils.py", line 428, in reraise
    raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
    return self.collate_fn(data)
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 84, in default_collate
    return [default_collate(samples) for samples in transposed]
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 84, in <listcomp>
    return [default_collate(samples) for samples in transposed]
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 56, in default_collate
    return torch.stack(batch, 0, out=out)
RuntimeError: stack expects each tensor to be equal size, but got [3, 37, 32] at entry 0 and [3, 111, 154] at entry 1```

[pngmafia]

Solution #2438 (comment)