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

Missing pickle files for training deeplab #38

Closed
AbdouMechraoui opened this issue Nov 24, 2021 · 3 comments
Closed

Missing pickle files for training deeplab #38

AbdouMechraoui opened this issue Nov 24, 2021 · 3 comments

Comments

@AbdouMechraoui
Copy link

Hello,
Thank you so much for providing the code for this paper :)
I am trying to generate an annotated face dataset, but I am having some trouble with the train_deeplab.py.
In ln[95] there is all_pickle = glob.glob(data_path + '/*.pickle'), which loads the 16 manually annotated data if I understood the docs correctly. However, I can't seem to find these .pickle files.
I guess one can load the training/test data provided in dataset_release, but it would still be missing the uncertainty_score.

@arieling
Copy link
Collaborator

no. The pickle files are created during
Step 2. Run GAN Sampling

@AbdouMechraoui
Copy link
Author

Thank you so much for your reply :)
The annotations of face images are lacking color/labels, it is similar to what #36 reported. Does this have anything to do with the color palette chosen?

Sampled images from Step2:
label0
img0

@arieling
Copy link
Collaborator

https://github.com/nv-tlabs/datasetGAN_release/blob/master/datasetGAN/train_interpreter.py#L318

check this line and function for vis.

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

No branches or pull requests

2 participants