---
license: mit
tags:
- computer-vision
- emotion-detection
- facial-recognition
- efficientnet
- pytorch
datasets:
- custom
language:
- en
model-index:
- name: emotion-detection-efficientnet-b2-v1
  results:
  - task:
      type: image-classification
      name: Emotion Detection
    dataset:
      name: Facial Emotion Dataset (Kaggle)
      type: image
    metrics:
      - type: accuracy
        value: 0.8025
---

# EfficientNet-B2 Emotion Detection (v1)

This model classifies facial emotions into 7 categories:
`angry`, `disgust`, `fear`, `happy`, `neutral`, `sad`, `surprise`.

**Architecture:** EfficientNet-B2  
**Training Platform:** Kaggle GPU  
**Accuracy:** ~80.25%  
**Framework:** PyTorch  
**Developer:** Varad V. Choudhari (Atman AI)  
**License:** MIT  

### Example Usage
```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(
    repo_id="AtmanAI/emotion-detection-efficientnet-b2-v1",
    filename="efficientnet_b2_emotion_final.pth"
)