Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Model fix, and inference script #2

Merged
merged 1 commit into from
May 5, 2019

Conversation

zphang
Copy link
Contributor

@zphang zphang commented May 4, 2019

  • Fixed some dimension in model to match TensorFlow implementation
  • Added link to exported ImageNet model
  • Added inference script for infilling image

@daa233
Copy link
Owner

daa233 commented May 5, 2019

Hi @zphang,

Thanks for your great contribution! Could you tell me how to convert the TF model to a PyTorch one?

@daa233 daa233 merged commit e989cf6 into daa233:master May 5, 2019
@zphang
Copy link
Contributor Author

zphang commented May 5, 2019

Hey, I did it semi-manually - matched the weight/shapes/names between the TensorFlow variables and PyTorch model weights, and then just copied/reshaped the relevant weights. It was pretty easy because your code/naming was very close to the TensorFlow model's, so that's to your credit!

@daa233
Copy link
Owner

daa233 commented May 5, 2019

Haha, I see. I may try it myself later. Thank you again!

@zphang zphang deleted the model_fix_inference branch May 5, 2019 18:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants