search

bradyz / cross_view_transformers

Cross-view Transformers for real-time Map-view Semantic Segmentation (CVPR 2022 Oral)
MIT License
531 stars 81 forks source link

error training #40

Open Estrellama opened 1 year ago

Estrellama commented 1 year ago

my env: torch==1.11.0+cu113.

Estrellama commented 1 year ago

1.when i run the train scripts :

python3 scripts/train.py \ +experiment=cvt_nuscenes_vehicle data.dataset_dir=/media/datasets/nuscenes \ data.labels_dir=/media/datasets/cvt_labels_nuscenes,

Error occurs:

[RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument find_unused_parameters=True to torch.nn.parallel.DistributedDataParallel, and by making sure all forward function outputs participate in calculating loss. ]

  1. Then, i try to change find_unused_parameters=True in scripts/train.py. But, the second error occurs:

[RuntimeError: Expected to mark a variable ready only once. This error is caused by one of the following reasons: 1) Use of a module parameter outside the forward function. Please make sure model parameters are not shared across multiple concurrent forward-backward passes. or try to use _set_static_graph() as a workaround if this module graph does not change during training loop.2) Reused parameters in multiple reentrant backward passes. For example, if you use multiple checkpoint functions to wrap the same part of your model, it would result in the same set of parameters been used by different reentrant backward passes multiple times, and hence marking a variable ready multiple times. DDP does not support such use cases in default. You can try to use _set_static_graph() as a workaround if your module graph does not change over iterations.]

This seriously bothers me, do you have any advice?