LL-XSJ
LL-XSJ
How to train with multiple GPUs?
The error reported is like this 
How to solve the above problems
Hello, I found that there are no attributes other than "state_dict" in the weight you provided, but when training your own dataset, you need to load the attributes of checkpoint...
Hello author, there was an error in the tool/train.py file. He said that without a model [meta], it does not exist. The model does not have a meta attribute, and...
Just like this 
Which file to use load_from loading the weight file
Hello author, what is the reason for the error in distributed training?
Just like this 
May I ask how to solve it