RuntimeError: Error(s) in loading state_dict for DistributedDataParallel: Missing key(s) in state_di

RuntimeError: Error(s) in loading state_dict for DistributedDataParallel: Missing key(s) in state_dict: "module.stage.0.0.coordinate_attention.conv1.weight",

Traceback (most recent call last): File "/root/miniconda3/envs/litepose/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap fn(i, *args) File "/root/autodl-tmp/litepose/dist_train.py", line 325, in main_worker model.load_state_dict(checkpoint['state_dict']) File "/root/miniconda3/envs/litepose/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1406, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for DistributedDataParallel: Missing key(s) in state_dict: "module.stage.0.0.coordinate_attention.conv1.weight", "module.stage.0.0.coordinate_attention.conv1.bias", "module.stage.0.0.coordinate_attention.bn1.weight", "module.stage.0.0.coordinate_attention.bn1.bias", "module.stage.0.0.coordinate_attention.bn1.running_mean", "module.stage.0.0.coordinate_attention.bn1.running_var", "module.stage.0.0.coordinate_attention.conv2.weight", "module.stage.0.0.coordinate_attention.conv2.bias", "module.stage.0.0.coordinate_attention.conv3.weight", "module.stage.0.0.coordinate_attention.conv3.bias", "module.stage.0.0.coordinate_attention.conv_h.weight", "module.stage.0.0.coordinate_attention.conv_h.bias", "module.stage.0.0.coordinate_attention.conv_w.weight", "module.stage.0.0.coordinate_attention.conv_w.bias",

这个错误通常是因为键值对不匹配的问题，也就是说在训练过程中，你保存的checkpoints文件中的键值对对应不上，这个时候你需要把原来的训练的文件删除，然后再重新进行训练即可。