the differences between checkpoint and pretrained model

[EricKani]

Hi,

I just want to know the differences between checkpoint and pretrained model in pytorch. Does pytorch have checkpoint files like tensorflow? I just know the .pth file created by function of torch.save.( I am a new user in pytorch, please don't mind if my qusetion is easy...)

Thank you very much!

[twtygqyy]

Hi @EricKani basically a pretrained model can be also considered as one checkpoint, the only difference is the way how you would like to use it. For fine-tuning, you could initialize all the weight in the network with a pretrained model, while you could also resume the training from a pretrained model, just treat it as a checkpoint.