search

jeffreyyihuang / two-stream-action-recognition

Using two stream architecture to implement a classic action recognition method on UCF101 dataset
MIT License
855 stars 252 forks source link

Error while testing. #63

Open astha0899 opened 5 years ago

astha0899 commented 5 years ago

While running the following code: python spatial_cnn.py --resume /home/cvlab/ --evaluate I receive the error: Namespace(batch_size=25, epochs=500, evaluate=True, lr=0.0005, resume='/home/cvlab/', start_epoch=0) ==> (Training video, Validation video):( 9537 3783 ) ==> sampling testing frames ==> Training data : 9537 frames Traceback (most recent call last): File "spatial_cnn.py", line 265, in main() File "spatial_cnn.py", line 48, in main train_loader, test_loader, test_video = data_loader.run() File "/home/cvlab/dataloader/spatial_dataloader.py", line 98, in run train_loader = self.train() File "/home/cvlab/dataloader/spatial_dataloader.py", line 131, in train print (training_set[1][0]['img1'].size()) File "/home/cvlab/dataloader/spatial_dataloader.py", line 38, in getitem video_name, nb_clips = list(self).split(' ') File "/home/cvlab/dataloader/spatial_dataloader.py", line 38, in getitem video_name, nb_clips = list(self).split(' ') File "/home/cvlab/dataloader/spatial_dataloader.py", line 38, in getitem video_name, nb_clips = list(self).split(' ') [Previous line repeated 245 more times] RecursionError: maximum recursion depth exceeded while calling a Python object I request you to help me with this issue.