Training error about maptr_tiny_r50_24e_bevpool.py

[hctian713]

I met the bug when I tried running

tools/dist_train.sh projects/configs/maptr/maptr_tiny_r50_24e_bevpool.py

the common error is as

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. 
If you already have done the above, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's `forward` function. Please include the loss function and the structure of the return value of `forward` of your module when reporting this issue (e.g. list, dict, iterable).

and for convenience, I have solved this problem by setting in maptr_tiny_r50_24e_bevpool.py. find_unused_parameters=True

hope this will help others🤓🥰

[jhkwag970]

Thanks much appreciated!