Since THE WEIGHT CLASS I DOWNLOADED IS 80 and I need TO BE 2, how do I not load this layer for training, or what is a good idea

[weikai520]

Prerequisite

• I have searched the existing and past issues but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

🐞 Describe the bug

Since THE WEIGHT CLASS I DOWNLOADED IS 80 and I need TO BE 2, how do I not load this layer for training, or what is a good idea

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for YOLOX:
size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([2, 128, 1, 1]).

Environment

size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([2, 128, 1, 1]).

Additional information

size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([2, 128, 1, 1]).

[ZwwWayne]

In training, simply setting load_from to be the path of the weight should be fine, those mismatched weights will be ignored.