RuntimeError: Error(s) in loading state_dict for BNInception:

when i train tsn-pytorch,it show:

RuntimeError: Error(s) in loading state_dict for BNInception:
	size mismatch for conv1_7x7_s2_bn.weight: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv1_7x7_s2_bn.bias: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv1_7x7_s2_bn.running_mean: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv1_7x7_s2_bn.running_var: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv2_3x3_reduce_bn.weight: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv2_3x3_reduce_bn.bias: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.
	size mismatch for conv2_3x3_reduce_bn.running_mean: copying a param of torch.Size([64]) from checkpoint, where the shape is torch.Size([1, 64]) in current model.

...

size mismatch for inception_5b_pool_proj_bn.running_var: copying a param of torch.Size([128]) from checkpoint, where the shape is torch.Size([1, 128]) in current model.

How can this happen and how to solve it?

I also need help with this. Help is appreciated.

Regards,
Brian,

hello, have you guys solve the problem now ? i got the same question, can you tell me how to solve it ?

many thanks!

The same question,has it been solved?How?
I would appreciate it if you can help me!:pray:

The same question,has it been solved?How?
I would appreciate it if you can help me!:pray: