yjxiong / tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch
BSD 2-Clause "Simplified" License
1.07k stars 308 forks source link

Error: return int(self._data[1]) IndexError: list index out of range #116

Closed yhc1994 closed 4 years ago

yhc1994 commented 4 years ago

Hi,

I have edited my list file under the for mat video_frame_path 100 10 But I will get a new error immediately after epoch 4. It will return int(self._data[1]) IndexError rather than self._data[2] The code is attached.

clipping gradient: 45.87702178955078 with coef 0.43594807386398315 Freezing BatchNorm2D except the first one. Traceback (most recent call last): File "main.py", line 301, in main() File "main.py", line 128, in main prec1 = validate(val_loader, model, criterion, (epoch + 1) * len(train_loader)) File "main.py", line 213, in validate for i, (input, target) in enumerate(val_loader): File "D:\Anaconda3\envs\dissertation\lib\site-packages\torch\utils\data\dataloader.py", line 286, in next return self._process_next_batch(batch) File "D:\Anaconda3\envs\dissertation\lib\site-packages\torch\utils\data\dataloader.py", line 307, in _process_next_batch raise batch.exc_type(batch.exc_msg) IndexError: Traceback (most recent call last): File "D:\Anaconda3\envs\dissertation\lib\site-packages\torch\utils\data\dataloader.py", line 57, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "D:\Anaconda3\envs\dissertation\lib\site-packages\torch\utils\data\dataloader.py", line 57, in samples = collate_fn([dataset[i] for i in batch_indices]) File "D:\Developments\Dissertation\tsn-pytorch\dataset.py", line 95, in getitem segment_indices = self._sample_indices(record) if self.random_shift else self._get_val_indices(record) File "D:\Developments\Dissertation\tsn-pytorch\dataset.py", line 76, in _get_val_indices if record.num_frames > self.num_segments + self.new_length - 1: File "D:\Developments\Dissertation\tsn-pytorch\dataset.py", line 19, in num_frames return int(self._data[1]) IndexError: list index out of range