Problem with Model_Composite_PL_NoBG

When i tried to use Model_Composite_PL_NoBG, i had a problem about the weight of the checkpoint. I posted the problem here:

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Model_Composite_PL_NoBG:
size mismatch for PL.conv1.weight: copying a param with shape torch.Size([64, 7, 7, 7]) from checkpoint, the shape in current model is torch.Size([64, 4, 7, 7]).
size mismatch for gainnet.conv0.weight: copying a param with shape torch.Size([32, 10, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 7, 3, 3]).

I tried to fix it but it did not work. Could you help me with this problem, please? Thank you so much.