search

voldemortX / pytorch-auto-drive

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help
BSD 3-Clause "New" or "Revised" License
839 stars 137 forks source link

train #34

Closed miao02830 closed 2 years ago

miao02830 commented 2 years ago

when i train i meet a problem

image image

I saw on the Internet that it may be a multi-threaded problem. I had encountered this situation before I could only run one round. Later, I changed the number of workers to 1. Now I ran three rounds and encountered this problem again.

i'm confused about this question. thank you for your help!

voldemortX commented 2 years ago

@miao02830 Did you manage to finish a full epoch? If not, you should check if your dataset has broken images (or possibly a upgrade of Pillow https://github.com/python-pillow/Pillow/issues/3185). If yes, then probably your machine has limited loading power, which suggests setting workers to 0.

voldemortX commented 2 years ago

@miao02830 This issue happened a long time ago. Please open a new issue if the problem continues to show up in the new master branch.