Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

loading pretrained resent model in Unet encoder#427

ramchandracheke started this conversation inGeneral
Discussion options

Hi,
Thanks for this amazing repo. I am wondering, how can I load pretrained model(resnet) in Unet configuration. Currently only imagenet weights are supported.
Thanks

You must be logged in to vote

Replies: 1 comment 2 replies

Comment options

Try model.encoder.load_state_dict()

You must be logged in to vote
2 replies
@ramchandracheke
Comment options

Thanks King for quick reply!

@ramchandracheke
Comment options

Thanks@qubvel . That works. There were few extra state_dict in the old_resnet and name was also different. I posted question and solution at :https://discuss.pytorch.org/t/how-to-load-load-state-dict-for-resnet-model/125998

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment
Category
General
Labels
None yet
2 participants
@ramchandracheke@qubvel
[8]ページ先頭
©2009-2025 Movatter.jp