Hello.

I am trying to train on the custom dataset having 6 classes. But here is the error I'm facing. Any help is appreciated.

Exception has occurred: RuntimeError
Error(s) in loading state_dict for C1DeepSup:
size mismatch for conv_last.weight: copying a param with shape torch.Size([150, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([6, 80, 1, 1]).
size mismatch for conv_last.bias: copying a param with shape torch.Size([150]) from checkpoint, the shape in current model is torch.Size([6]).
size mismatch for conv_last_deepsup.weight: copying a param with shape torch.Size([150, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([6, 80, 1, 1]).
size mismatch for conv_last_deepsup.bias: copying a param with shape torch.Size([150]) from checkpoint, the shape in current model is torch.Size([6]).
File "/home/irl/sem_seg _custom/mit_semseg/models/models.py", line 160, in build_decoder
torch.load(weights, map_location=lambda storage, loc: storage), strict=False)
File "/home/irl/sem_seg _custom/train.py", line 155, in main
weights=cfg.MODEL.weights_decoder)
File "/home/irl/sem_seg _custom/train.py", line 288, in
main(cfg, gpus)
RuntimeError: Error(s) in loading state_dict for C1DeepSup:
size mismatch for conv_last.weight: copying a param with shape torch.Size([150, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([6, 80, 1, 1]).
size mismatch for conv_last.bias: copying a param with shape torch.Size([150]) from checkpoint, the shape in current model is torch.Size([6]).
size mismatch for conv_last_deepsup.weight: copying a param with shape torch.Size([150, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([6, 80, 1, 1]).
size mismatch for conv_last_deepsup.bias: copying a param with shape torch.Size([150]) from checkpoint, the shape in current model is torch.Size([6]).