|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
# Model Description |
|
|
|
The LeNNon_smile_detector model is used to detect smiling and not-smiling faces. |
|
|
|
The model was trained with CelebA dataset. |
|
|
|
## Details |
|
|
|
- Dataset: [CelebFaces Attributes](https://www.kaggle.com/datasets/jessicali9530/celeba-dataset/) |
|
|
|
The creators of the dataset wrote the following paper employing CelebA for face detection: |
|
S. Yang, P. Luo, C. C. Loy, and X. Tang, |
|
"From Facial Parts Responses to Face Detection: A Deep Learning Approach", in IEEE International Conference on Computer Vision (ICCV), 2015. |
|
- Language: English |
|
- Number of Training Steps: 20 |
|
- Batch size: 32 |
|
- Optimizer: Adam |
|
- Learning Rate: 0.001 |
|
- GPU: T4 |
|
- This repository has the source [code used](https://github.com/Nkluge-correa/teeny-tiny_castle/blob/master/ML%20Fairness/fair_metrics_celeba.ipynb) to train this model. |
|
|
|
|
|
## Performance |
|
|
|
Final Validation Accuracy: 90.56% Final Validation Loss: 0.6397 |
|
|
|
# Cite as 🤗 |
|
``` |
|
@misc{teenytinycastle, |
|
doi = {10.5281/zenodo.7112065}, |
|
url = {https://huggingface.co/AiresPucrs/LeNNon_smile_detector}, |
|
author = {Nicholas Kluge Corr{\^e}a}, |
|
title = {Teeny-Tiny Castle}, |
|
year = {2023}, |
|
publisher = {HuggingFace}, |
|
journal = {HuggingFace repository}, |
|
} |
|
``` |
|
## License |
|
The LeNNon_smile_detector model is licensed under the Apache License, Version 2.0. See the LICENSE file for more details. |
