search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

ValueError: could not broadcast input array from shape (1080,1440,3) into shape (128,171,3) #58

Open agelosk opened 3 years ago

agelosk commented 3 years ago

This error shows after running python train.py and after counting train/val/test videos.

Traceback (most recent call last):
  File "train.py", line 202, in <module>
    train_model()
  File "train.py", line 123, in train_model
    for inputs, labels in tqdm(trainval_loaders[phase]):
  File "/home/akrat/anaconda3/envs/test/lib/python3.7/site-packages/tqdm/std.py", line 1108, in __iter__
    for obj in iterable:
  File "/home/akrat/anaconda3/envs/test/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 582, in __next__
    return self._process_next_batch(batch)
  File "/home/akrat/anaconda3/envs/test/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
ValueError: Traceback (most recent call last):
  File "/home/akrat/anaconda3/envs/test/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/akrat/anaconda3/envs/test/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 99, in <listcomp>
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/akrat/pytorch-video-recognition/dataloaders/dataset.py", line 78, in __getitem__
    buffer = self.load_frames(self.fnames[index])
  File "/home/akrat/pytorch-video-recognition/dataloaders/dataset.py", line 225, in load_frames
    buffer[i] = frame

ValueError: could not broadcast input array from shape (1080,1440,3) into shape (128,171,3)