|
|
--- |
|
|
license: mit |
|
|
base_model: google/mobilenet_v2_1.0_224 |
|
|
tags: |
|
|
- medical |
|
|
- glaucoma |
|
|
- eye-disease |
|
|
- image-classification |
|
|
library_name: transformers.js |
|
|
pipeline_tag: image-classification |
|
|
--- |
|
|
|
|
|
# Glaucoma Detection Model |
|
|
|
|
|
This model detects glaucoma from fundus (retinal) images using deep learning. |
|
|
|
|
|
## Model Details |
|
|
- **Model Type**: Image Classification (Binary) |
|
|
- **Base Architecture**: MobileNetV2 |
|
|
- **Input**: Fundus images (224x224 pixels) |
|
|
- **Output**: Binary classification (Glaucoma/No Glaucoma) |
|
|
- **Framework**: TensorFlow → ONNX |
|
|
|
|
|
## Usage with Transformers.js |
|
|
|
|
|
```javascript |
|
|
import { pipeline } from '@huggingface/transformers'; |
|
|
|
|
|
// Create image classification pipeline |
|
|
const classifier = await pipeline( |
|
|
'image-classification', |
|
|
'tonyanyanwu5448/nzube-glaucoma-detection-model' |
|
|
); |
|
|
|
|
|
// Classify fundus image |
|
|
const result = await classifier('path/to/fundus-image.jpg'); |
|
|
console.log(result); |
|
|
|
|
|
|
|
|
Classes |
|
|
Class 0: No Glaucoma |
|
|
Class 1: Glaucoma |
|
|
|
|
|
Medical Disclaimer: |
|
|
This model is for research purposes only and should not be used for medical diagnosis without professional medical consultation. |
|
|
|
