RuntimeError: Error(s) in loading state_dict for DataParallel:
size mismatch for module.pre_block1.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]).
size mismatch for module.pre_block2.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]).
size mismatch for module.pre_block3.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]).
size mismatch for module.pre_block4.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]).
size mismatch for module.pre_block5.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]).
Hello, first of all thanks for your open source code MBCNN.But today I am facing the above problem when I run them using the pth from the link you shared, may I know what could be the reason for this?
RuntimeError: Error(s) in loading state_dict for DataParallel: size mismatch for module.pre_block1.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]). size mismatch for module.pre_block2.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]). size mismatch for module.pre_block3.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]). size mismatch for module.pre_block4.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]). size mismatch for module.pre_block5.adaptive_implicit_trans1.it_weights.it_weights: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1]). Hello, first of all thanks for your open source code MBCNN.But today I am facing the above problem when I run them using the pth from the link you shared, may I know what could be the reason for this?