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

Bugs in GANs #103

Merged
merged 19 commits into from
May 13, 2024
Merged

Bugs in GANs #103

merged 19 commits into from
May 13, 2024

Conversation

HarshithBachimanchi
Copy link
Collaborator

No description provided.

Removed pool layers
Instance norm should not be there in the last layer
Spelling mistakes!!! (Because of which activations were not being applied properly)
Changed the dimensions of the hidden channels
Embedding layer missing from weight initialization.
@JesusPinedaC
Copy link
Collaborator

Hi @HarshithBachimanchi

I've reviewed the changes and I think they look good, especially if the examples work as expected now.

However, I suggest that we implement unit tests for both CycleGAN and DCGAN. This will help us keep track of any possible changes to the models. The unit tests can be quite simple and focus on evaluating the correct order of operations, expected number of layers, and appropriate output dimensions of the model.

@HarshithBachimanchi
Copy link
Collaborator Author

Hi! @JesusPinedaC

I have created the unit tests now, and adjusted few other minor things. The models are working as expected now, and the weights are being initialized properly for dcgan.

If everything looks good, I think this can be merged now.

@BenjaminMidtvedt
Copy link
Collaborator

These are excellent unittests! @HarshithBachimanchi

Everything looks good to me.

@giovannivolpe giovannivolpe merged commit e2a5f8d into DeepTrackAI:develop May 13, 2024
12 checks passed
@HarshithBachimanchi HarshithBachimanchi deleted the hb/gan branch May 14, 2024 10:57
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.

4 participants