Stuck there when I run "python main_single_gpu.py datasets/" about two-stream-pytorch HOT 5 CLOSED

Hi, there. The thing is, you may not have those optical flow images as I have.

As I wrote in here, if the code couldn't find the optical flow images, the program will stop and exit. So that is why no progress.

I suggest you change the setting files, e.g., train_flow_split1.txt according to your situation. Usually due to different video codec, we may have different number of RGB or optical flow images.

from two-stream-pytorch.

Thanks so much for your fast reply. Get it.

from two-stream-pytorch.

Hello, I add the data files but it reports below errors, do you have any suggestions?

python main_single_gpu.py datasets/ucfnew
2017-09-24 08:46:46,667 - INFO - Building model ...
2017-09-24 08:47:05,368 - INFO - Model rgb_vgg16 is loaded.
2017-09-24 08:47:05,369 - INFO - Saving everything to directory ./checkpoints.
2017-09-24 08:47:05,369 - INFO - reach here
2017-09-24 08:47:05,494 - INFO - 13320 samples found, 9537 train samples and 3783 test samples.
2017-09-24 08:47:05,494 - INFO - 0.005
2017-09-24 08:47:05,495 - INFO - reach here
Traceback (most recent call last):
File "main_single_gpu.py", line 368, in
main()
File "main_single_gpu.py", line 190, in main
train(train_loader, model, criterion, optimizer, epoch)
File "main_single_gpu.py", line 232, in train
for i, (input, target) in enumerate(train_loader):
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 201, in next
return self._process_next_batch(batch)
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 221, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 40, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 109, in default_collate
return [default_collate(samples) for samples in transposed]
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 109, in
return [default_collate(samples) for samples in transposed]
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 89, in default_collate
storage = batch[0].storage()._new_shared(numel)
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/storage.py", line 113, in _new_shared
return cls._new_using_fd(size)
RuntimeError: unable to write to file </torch_25231_36990222> at /opt/conda/conda-bld/pytorch_1503970438496/work/torch/lib/TH/THAllocator.c:271

from two-stream-pytorch.

Sorry, I don't know why such error occurs. I think it maybe due to different version of python or pytorch. I am modifying my code right now to achieve good accuracy on flow stream. I will test on different versions of pytorch to see if I can reproduce your errors.

from two-stream-pytorch.

from two-stream-pytorch.