search

hongfz16 / DS-Net

[CVPR 2021/TPAMI 2023] Rank 1st in the public leaderboard of SemanticKITTI Panoptic Segmentation (2020-11-16)
MIT License
243 stars 29 forks source link

Error: Caught Exception in DataLoader worker process 0 #6

Closed zhanghm1995 closed 3 years ago

zhanghm1995 commented 3 years ago

Hi, thanks for you excellent work firstly.

I got the error like

TypeError: Caught TypeError in DataLoader worker process 0.
TypeError: expected dtype object, got 'numpy.dtype[uint8]'

when running into the line for i_iter, inputs in enumerate(val_dataset_loader): in cfg_train.py script, I have googled different solutions but not worked.

Hope you could do me a favor, thanks in advance.

hongfz16 commented 3 years ago

Hi. Could you please try to locate which line in DataLoader throws the error? Currently, the provided information is not enough for me to help you. I personally have not encountered a similar issue.

zhanghm1995 commented 3 years ago

When the code execute this line, it cause this problem.

BTW, I have found an solution that to change the num_worker from 1 to 0, maybe it refers to the parallel data loader process.

hongfz16 commented 3 years ago

That's strange. I would expect the TypeError came from somewhere in this file. However, if disabling parallel data loading solves the issue, then the problem is not in the DataLoader. Parallel data loading works smoothly in my machine. Maybe it is some weird low-level bug in your machine or the computing power is not enough?

zhanghm1995 commented 3 years ago

I'm not the sure what the problem exactly. Thanks for your kindly reply.