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

Inconsistency with bias enabled in the pytorch model (Conv2d) for image classification #147

Open
embrya-technologies opened this issue Feb 5, 2024 · 1 comment

Comments

@embrya-technologies
Copy link

Hello,

I am interested in running the image classification model to benchmark our accelerator and, currently, my environment is in pytorch therefore, I had a look at your experimental model under:
/tiny/benchmark/experimental/training_torch/image_classification/utils/model.py

The model contains ResNetBlock with two Conv2d convolutions followed per Batch Normalization. However, each Conv2d layer is configured with the bias enabled (bias=True) which is inconsistent with the Con2d layers in the Keras model that don't have the use_bias flag enabled (also it is not coherent with the purpose of batch normalization layer that follows).

Thank you,
Best regards,
Jean-Baptiste

@cskiraly
Copy link
Contributor

Thanks for opening the issue @embrya-technologies !

Just to be clear for someone stumbling on this issue, as stated in the README, the PyTorch training code is not official and cannot be used for closed submissions. Even the original training code is only for documentation purposes. The only official source for closed submissions is the trained model itself.

Having said that, it is important to make this code map as closely as possible. Thanks again for reporting it! It would be great if you could make a PR to fix the issue.

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