diaoenmao / HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients

[ICLR 2021] HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
MIT License
154 stars 33 forks source link

how to load pt file #6

Closed kase113 closed 2 years ago

kase113 commented 2 years ago

If i have trained a new model,and get a 'pt' file.Can i how to load this pt file?

diaoenmao commented 2 years ago

The 'pt' extension does not matter much. It is a acronym convention of Pytorch. You can use the method in ./utils.py to load the pt file. It is a dictionary contains model, optimizer and scheduler state_dict().