hyf015
commented
3 years ago Thank you for your interest in the code! I've never met such problems and neither did other reproducers. Can you check whether the optical flow files are correct? Maybe it is a data preprocessing problem.
BIT-LiuQingXiao
Thanks for your shared code! When I followed the guidelines, I met the problem as below: Traceback (most recent call last): File "gaze_full.py", line 99, in
sp.train()
File "/home/lqx/LabCode/Gaze/SP.py", line 199, in train
loss1 = self.trainSP()
File "/home/lqx/LabCode/Gaze/SP.py", line 125, in trainSP
for i, sample in tqdm(enumerate(self.STTrainLoader)):
File "/usr/local/lib/python3.5/dist-packages/tqdm/std.py", line 1178, in iter
for obj in iterable:
File "/home/lqx/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 286, in next
return self._process_next_batch(batch)
File "/home/lqx/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
File "/home/lqx/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/lqx/.local/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 57, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/lqx/LabCode/Gaze/data/STdatas.py", line 68, in getitem
flowarr.append(torch.from_numpy(currflowx))
TypeError: expected np.ndarray (got list).
I used python 3.5, Cuda 8.0, torch 0.4, opencv 2.4.13, numpy 1.14. It seems like caused by wrong numpy