|
|
--- |
|
|
license: mit |
|
|
library_name: pytorch |
|
|
pipeline_tag: image-classification |
|
|
tags: |
|
|
- skin-disease |
|
|
- medical-imaging |
|
|
- cnn |
|
|
- deep-learning |
|
|
- healthcare |
|
|
--- |
|
|
|
|
|
# Skin Diseases Detection Model (DermaDL) |
|
|
|
|
|
## Overview |
|
|
DermaDL is a deep learning–based **skin disease detection model** trained on dermoscopic images. |
|
|
It uses a **Convolutional Neural Network (CNN)** to classify multiple skin conditions and is intended for **research, educational, and prototype applications**. |
|
|
|
|
|
> ⚠️ **Disclaimer:** This model is NOT a medical diagnostic tool and should not be used as a substitute for professional medical advice. |
|
|
|
|
|
--- |
|
|
|
|
|
## Model Details |
|
|
- **Task:** Image Classification |
|
|
- **Architecture:** CNN with Transfer Learning |
|
|
- **Framework:** PyTorch |
|
|
- **Input Size:** 224 × 224 RGB images |
|
|
- **Accuracy:** ~91% (validation set) |
|
|
|
|
|
--- |
|
|
|
|
|
## Supported Skin Conditions |
|
|
- Melanoma |
|
|
- Basal Cell Carcinoma |
|
|
- Squamous Cell Carcinoma |
|
|
- Benign Keratosis |
|
|
- Actinic Keratosis |
|
|
- Dermatofibroma |
|
|
- Vascular Lesions |
|
|
- Nevus |
|
|
|
|
|
*(Class labels may vary depending on dataset version)* |
|
|
|
|
|
--- |
|
|
|
|
|
## Training Information |
|
|
- **Dataset:** Public dermoscopic skin lesion datasets |
|
|
- **Loss Function:** Cross-Entropy Loss |
|
|
- **Optimizer:** Adam |
|
|
- **Evaluation Metric:** Accuracy |
|
|
- **Data Augmentation:** Rotation, flipping, normalization |
|
|
|
|
|
--- |
|
|
|
|
|
## How to Use |
|
|
|
|
|
### 1️⃣ Install Dependencies |
|
|
```bash |
|
|
pip install torch torchvision pillow |
|
|
|
