Created
April 21, 2022 15:43
-
-
Save andrewnc/c744607028123d273d68b7c0f31d3ade to your computer and use it in GitHub Desktop.
Code to soup two models in pytorch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def soup_two_models(model, second_model): | |
| souped_model = copy.deepcopy(model) | |
| for param in souped_model.named_parameters(): | |
| name = param[0] | |
| param[1].data = (model.state_dict()[name] + second_model.state_dict()[name]) / 2 | |
| return souped_model |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment