Closed bhanushri12 closed 1 month ago
Thank you for creating this issue! 🎉 We'll look into it as soon as possible. In the meantime, please make sure to provide all the necessary details and context. If you have any questions reach out to LinkedIn. Your contributions are highly appreciated! 😊
You can also check our CONTRIBUTING.md for guidelines on contributing to this project.
@sanjay-kv can I start working on this issue?
yes
Hello @bhanushri12! Your issue #178 has been closed. Thank you for your contribution!
@sanjay-kv I would like to raise this issue as a part of the GSSoC'24 The current model architecture for facial expression recognition is based on convolutional neural networks (CNNs) designed for image classification tasks. While leveraging pre-trained models from the TIMM library has been effective, there are several ways to further enhance performance and reduce training time. Proposed Improvements
Optimizing the Training Process:
Data Augmentation: -Implement a more diverse range of data augmentations to improve model robustness and generalization.
I would like to work on this issue as I have already been working with face datasets.