training error

[hitxing]

Thanks for the great work ! My enviornment as follows: CUDA10.0 torch1.1.0 torchvision0.3.0 python3.6.5 spconv1.0 cmake3.16.0 Evaluate the model is OK, however, when I try to train a model by run the script "python3 train.py ../configs/car_cfg.py" , An error was encountered: (SASSD) weixing@weixing:~/deeplearning/projects/SA-SSD/tools$ python3 train.py ../configs/car_cfg.py /home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/numba/cuda/envvars.py:17: NumbaWarning: Environment variables with the 'NUMBAPRO' prefix are deprecated and consequently ignored, found use of NUMBAPRO_CUDA_DRIVER=/usr/lib/x86_64-linux-gnu/libcuda.so.

For more information about alternatives visit: ('https://numba.pydata.org/numba-doc/latest/cuda/overview.html', '#cudatoolkit-lookup') warnings.warn(errors.NumbaWarning(msg)) /home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/numba/cuda/envvars.py:17: NumbaWarning: Environment variables with the 'NUMBAPRO' prefix are deprecated and consequently ignored, found use of NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so.

For more information about alternatives visit: ('https://numba.pydata.org/numba-doc/latest/cuda/overview.html', '#cudatoolkit-lookup') warnings.warn(errors.NumbaWarning(msg)) /home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/numba/cuda/envvars.py:17: NumbaWarning: Environment variables with the 'NUMBAPRO' prefix are deprecated and consequently ignored, found use of NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice.

For more information about alternatives visit: ('https://numba.pydata.org/numba-doc/latest/cuda/overview.html', '#cudatoolkit-lookup') warnings.warn(errors.NumbaWarning(msg)) 2020-12-07 10:37:17,116 - INFO - Distributed training: False [40, 1600, 1408] load 28742 Car database infos After filter database: load 21375 Car database infos /home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/mmcv/runner/epoch_based_runner.py:168: UserWarning: Runner was deprecated, please use EpochBasedRunner instead 'Runner was deprecated, please use EpochBasedRunner instead') /home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/mmcv/runner/base_runner.py:59: UserWarning: batch_processor is deprecated, please implement train_step() and val_step() in the model instead. warnings.warn('batch_processor is deprecated, please implement ' Traceback (most recent call last): File "train.py", line 101, in main() File "train.py", line 94, in main logger=logger) File "/home/weixing/deeplearning/projects/SA-SSD/mmdet/apis/train.py", line 60, in train_detector _non_dist_train(model, dataset, cfg, validate=validate) File "/home/weixing/deeplearning/projects/SA-SSD/mmdet/apis/train.py", line 114, in _non_dist_train cfg.log_level) File "/home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/mmcv/runner/epoch_based_runner.py", line 169, in init super().init(*args, **kwargs) File "/home/weixing/anaconda3/envs/SASSD/lib/python3.6/site-packages/mmcv/runner/base_runner.py", line 79, in init f'optimizer must be a dict of torch.optim.Optimizers, ' TypeError: optimizer must be a dict of torch.optim.Optimizers, but optimizer["type"] is a <class 'str'>

Did someone encounter with the same problem? Could you please point me how to fix it?

[vehxianfish]

@hitxing .Hi,Do you solve this question? thank you.