_pickle.UnpicklingError: STACK_GLOBAL requires str

[AT9991]

Can anyone please help, why I might be getting this error while running train.py.

A few days ago, the error was not there.

Transferred 330/344 items from yolov7-tiny.pt Scaled weight_decay = 0.0005 Optimizer groups: 58 .bias, 58 conv.weight, 61 other Traceback (most recent call last): File "train.py", line 616, in train(hyp, opt, device, tb_writer) File "train.py", line 245, in train dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt, File "/content/yolov7/utils/datasets.py", line 69, in create_dataloader dataset = LoadImagesAndLabels(path, imgsz, batch_size, File "/content/yolov7/utils/datasets.py", line 392, in init cache, exists = torch.load(cache_path), True # load File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 795, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 1002, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: STACK_GLOBAL requires str

[imihassan]

I am also facing same problem. Anyone has any idea why?

[TECOLOGYxyz]

Same issue.

[lihaolin88]

Try to delete the .cache file in your training or testing path, this works for me.

[adilraja]

Try to delete the .cache file in your training or testing path, this works for me.

And how can I find the cache file in my training or testing path?

[adilraja]

Try to delete the .cache file in your training or testing path, this works for me.

And how can I find the cache file in my training or testing path?

Oops... I found it. What you meant was to remove the .cache files in the path of the training or testing datasets.

[Anushka-N12]

Still not working for me though

[SebiGoebel]

deleting .cache files worked for me too thx :)