RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File “/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py”, line 302, in _worker_loop
data = fetcher.fetch(index)
File “/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py”, line 39, in fetch
data = next(self.dataset_iter)
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 140, in create_batches
yield from map(self.do_batch, self.chunkify(res))
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 170, in do_batch
def do_batch(self, b): return self.retain(self.create_batch(self.before_batch(b)), b)
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 168, in create_batch
if not self.prebatched: collate_error(e,b)
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 166, in create_batch
try: return (fa_collate,fa_convert)self.prebatched
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 52, in fa_collate
else type(t[0])([fa_collate(s) for s in zip(*t)]) if isinstance(b, Sequence)
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 52, in
else type(t[0])([fa_collate(s) for s in zip(*t)]) if isinstance(b, Sequence)
File “/usr/local/lib/python3.7/dist-packages/fastai/data/load.py”, line 51, in fa_collate
return (default_collate(t) if isinstance(b, _collate_types)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/utils/collate.py", line 140, in default_collate
out = elem.new(storage).resize(len(batch), *list(elem.size()))
File “/usr/local/lib/python3.7/dist-packages/fastai/torch_core.py”, line 376, in torch_function
res = super().torch_function(func, types, args, ifnone(kwargs, {}))
File “/usr/local/lib/python3.7/dist-packages/torch/_tensor.py”, line 1121, in torch_function
ret = func(*args, **kwargs)
RuntimeError: Error when trying to collate the data into batches with fa_collate, at least two tensors in the batch are not the same size.
Mismatch found on axis 0 of the batch and is of type TensorImage:
Item at index 0 has shape: torch.Size([3, 4000, 6000])
Item at index 2 has shape: torch.Size([3, 256, 256])
Please include a transform in after_item that ensures all data of type TensorImage is the same size