Updated Readme
Browse files
README.md
CHANGED
|
@@ -6,4 +6,27 @@ metrics:
|
|
| 6 |
- accuracy
|
| 7 |
pipeline_tag: image-classification
|
| 8 |
library_name: keras
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- accuracy
|
| 7 |
pipeline_tag: image-classification
|
| 8 |
library_name: keras
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Dermacare Skin Lesion Classification
|
| 12 |
+
|
| 13 |
+
Dermacare is a skin lesion classification model built using Keras. It classifies dermatoscopic images into various types of skin lesions, aiding in the early detection of skin cancer.
|
| 14 |
+
|
| 15 |
+
## Model Architecture
|
| 16 |
+
The model is a Convolutional Neural Network (CNN) trained on the [HAM10000 dataset](https://www.kaggle.com/datasets/ultralytics/ham10000) with the following key specifications:
|
| 17 |
+
|
| 18 |
+
- **Input**: 224x224 RGB images
|
| 19 |
+
- **Architecture**: Keras-based CNN
|
| 20 |
+
- **Output**: 7-class classification for different types of skin lesions
|
| 21 |
+
|
| 22 |
+
## Usage Example
|
| 23 |
+
To use the model for predictions, send an image to the inference endpoint as shown below:
|
| 24 |
+
|
| 25 |
+
```python
|
| 26 |
+
import requests
|
| 27 |
+
|
| 28 |
+
API_URL = "https://api-inference.huggingface.co/models/sreejith782/Dermacare_Skin_Lesion_classification"
|
| 29 |
+
headers = {"Authorization": "Bearer YOUR_HUGGING_FACE_TOKEN"}
|
| 30 |
+
|
| 31 |
+
response = requests.post(API_URL, headers=headers, files={"inputs": open("path_to_image.jpg", "rb")})
|
| 32 |
+
print(response.json())
|