The model and loaded state dict do not match exactly

[puyiwen]

Hi，I change the input size as 224x224,and I get a message 'the model and loaded state dict do not match exactly',the code still works.However,I'm not sure if the mit_b4 pre-trained model has already loaded.Can you help me?And I want to know,have you ever done an experiment which input size as 224x224.If you have done the experiment,can you tell me the corresponding evaluation index ?Thank you very much!!

[premchedella]

I am also getting the following error, I didn't change the input size.

load checkpoint from local path: ./code/models/weights/mit_b4.pth
The model and loaded state dict do not match exactly

unexpected key in source state_dict: head.weight, head.bias

Let me know how to resolve the this.

[puyiwen]

I am also getting the following error, I didn't change the input size.

load checkpoint from local path: ./code/models/weights/mit_b4.pth
The model and loaded state dict do not match exactly

unexpected key in source state_dict: head.weight, head.bias

Let me know how to resolve the this.

may be you should set the strict = False, like model.load_state_dict(torch.load(path),strict=False)

[premchedella]

thanks, let me look into this

I made a change incode\models\model.py

load_checkpoint(self.encoder, ckpt_path, logger=None)
to
load_checkpoint(self.encoder, ckpt_path, strict=False, logger=None)