yuhongtian17 / Spatial-Transform-Decoupling

MIT License
74 stars 7 forks source link

Report errors when i try to "CUDA_VISIBLE_DEVICES=0,1./tools/dist_train.sh ./configs/rotated_faster_rcnn/rotated_faster_rcnn_r50_fpn_1x_dota_le90.py 2 #25

Open BiangBiangH opened 1 month ago

BiangBiangH commented 1 month ago

I have read the relevant issues. I cannot directly run through this demo by following the steps in readme.The main issues were with the CUDA and pytorch environments. After continuous attempts, I resolved the environmental issues. When I tried to run it again, the following issues occurred. I suspect it may be a data issue, and I am not particularly clear which directory DOTA's test data should be placed in or how it should be stored. I tried to find the answer online, but it didn't solve the problem. Could you please give me some help.Here is my error message:

2024-07-09 22:01:11,785 - mmrotate - INFO - Saving checkpoint at 1 epochs completed: 0, elapsed: 0sTraceback (most recent call last): File "./tools/train.py", line 198, in main() File "./tools/train.py", line 187, in main train_detector( File "/data1/zhb/TZ/mmrotate/mmrotate/apis/train.py", line 144, in train_detector runner.run(data_loaders, cfg.workflow) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run epoch_runner(data_loaders[i], kwargs) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 58, in train self.call_hook('after_train_epoch') File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmcv/runner/base_runner.py", line 317, in call_hook getattr(hook, fn_name)(self) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 271, in after_train_epoch self._do_evaluate(runner) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmdet/core/evaluation/eval_hooks.py", line 126, in _do_evaluate results = multi_gpu_test( File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/mmdet/apis/test.py", line 107, in multi_gpu_test for i, data in enumerate(data_loader): File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 444, in iter return self._get_iterator() File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 390, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1115, in init self._reset(loader, first_iter=True) File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1148, in _reset self._try_put_index() File "/data1/Anaconda/envs/kky/lib/python3.8/site-packages/torch/utils/data/dataloader.py

yuhongtian17 commented 1 month ago

The error info provided by you is not a complete one…? If possible, please upload screenshots instead of copying texts. Is there an error hint such as "Runtime Error: …"?

BiangBiangH commented 1 month ago

The error info provided by you is not a complete one…? If possible, please upload screenshots instead of copying texts. Is there an error hint such as "Runtime Error: …"? Sorry bro, now the following screenshots are the complete error:

1720539519613 1720539564099 1720539609764 1720539627901
yuhongtian17 commented 1 month ago

This error is due to the program not being able to find the dataset. Please confirm your dataset in cfg exists.

BiangBiangH commented 1 month ago

This error is due to the program not being able to find the dataset. Please confirm your dataset in cfg exists.

Thank you for patiently answering. I have run the model successfully under your suggestion.