siam_mask_dataset error

Traceback (most recent call last):
File "/home/soyeon/SiamMask/tools/train_siammask.py", line 292, in
main()
File "/home/soyeon/SiamMask/tools/train_siammask.py", line 168, in main
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch, cfg)
File "/home/soyeon/SiamMask/tools/train_siammask.py", line 186, in train
for iter, input in enumerate(train_loader):
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in __next__
return self._process_data(data)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
data.reraise()
File "/opt/conda/lib/python3.6/site-packages/torch/_utils.py", line 385, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/soyeon/SiamMask/datasets/siam_mask_dataset.py", line 551, in __getitem__
search_mask = (cv2.imread(search[2], 0) > 0).astype(np.float32)
TypeError: '>' not supported between instances of 'NoneType' and 'int'

How can I fix this error? Please...
I want to use training set without ytb. (I use only coco, vid, det)

Read datasets/siam_mask_dataset.py around line 551 and tools/train_siammask.py around lines 168-186, then trace which COCO, VID, or DET dataset entry produces the failing image path. Reproduce the training run without YTB and verify that the DataLoader no longer raises this TypeError.

Written by the indexing model from the issue text.