loaded state dict contains a parameter group that doesn’t match the size of optimizer’s group

Traceback (most recent call last):
  File "tools/train.py", line 98, in <module>
    main()
  File "tools/train.py", line 94, in main
    logger=logger)
  File "/home/omnisky/Code/redet-improve-new/mmdet/apis/train.py", line 61, in train_detector
    _non_dist_train(model, dataset, cfg, validate=validate)
  File "/home/omnisky/Code/redet-improve-new/mmdet/apis/train.py", line 194, in _non_dist_train
    runner.resume(cfg.resume_from)
  File "/home/omnisky/anaconda3/envs/redet/lib/python3.7/site-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/runner.py", line 313, in resume
    self.optimizer.load_state_dict(checkpoint['optimizer'])
  File "/home/omnisky/anaconda3/envs/redet/lib/python3.7/site-packages/torch/optim/optimizer.py", line 116, in load_state_dict
    raise ValueError("loaded state dict contains a parameter group "
ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group

解决方法（注意文件路径）：

vi ~/anaconda3/envs/环境名/lib/python3.7/site-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/runner.py

把这行代码注释掉：

#        if 'optimizer' in checkpoint and resume_optimizer:
#            self.optimizer.load_state_dict(checkpoint['optimizer'])

重新跑就可以了。