TypeError: Caught TypeError in DataLoader worker process 0.

[shuyu888]

2022-04-21 16:30:09 | INFO | yolox.data.datasets.mot:43 - loading annotations into memory... 2022-04-21 16:30:09 | INFO | yolox.data.datasets.mot:43 - Done (t=0.00s) 2022-04-21 16:30:09 | INFO | pycocotools.coco:88 - creating index... 2022-04-21 16:30:09 | INFO | pycocotools.coco:88 - index created! 2022-04-21 16:30:09 | INFO | yolox.core.trainer:149 - init prefetcher, this might take one minute or less... 2022-04-21 16:30:11 | ERROR | yolox.core.launch:90 - An error has been caught in function 'launch', process 'MainProcess' (3566), thread 'MainThread' (139726425002176): Traceback (most recent call last):

File "tools/train.py", line 126, in launch( m <function launch at 0x7f14358bea60> ........................................... File "/home/ubuntu/anaconda3/envs/bytetrack/lib/python3.8/site-packages/torch/_utils.py", line 457, in reraise raise exception m TypeError('Caught TypeError in DataLoader worker process 0.\nOriginal Traceback (most recent call last):\n File "/home/ubunt...

TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/ubuntu/anaconda3/envs/bytetrack/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/ubuntu/anaconda3/envs/bytetrack/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch return self.collate_fn(data) File "/home/ubuntu/anaconda3/envs/bytetrack/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 180, in default_collate raise TypeError(default_collate_err_msg_format.format(elem_type)) TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'NoneType'>

[shuyu888]

anybody help????

[YamacTan]

Same problem, cannot start any training processes. Any updates? @shuyu888

[shuyu888]

it is a datasets problem done by pip install yolox

[shuyu888]

you can reinstall the yolox file ,it will work