😊 Facial Emotion Detection using ResNet50
This project is a deep learning-based web application that detects human emotions from images.
The model is trained on the FER2013 dataset using transfer learning with ResNet50.
📌 Features
Detects 7 emotions:
- Angry 😠
- Disgust 🤢
- Fear 😨
- Happy 😄
- Sad 😢
- Surprise 😲
- Neutral 😐
Achieved ~68% test accuracy
Uses ResNet50 (Transfer Learning)
Real-time image upload and prediction
Deployed using Flask + Render
Model hosted on Hugging Face
🧠 Model Details
- Base Model: ResNet50 (pretrained on ImageNet)
- Input Shape:
(224, 224, 3) - Preprocessing: Pixel normalization (
/255) - Loss Function: Categorical Crossentropy
- Optimizer: Adam
- Techniques Used:
- Data Augmentation
- Class Weighting
- EarlyStopping
- ReduceLROnPlateau
- ModelCheckpoint
📊 Performance
- Train Accuracy: ~75%
- Test Accuracy: ~68%
🖼️ Pipeline
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support