cicerothoma/naija-food-classifier-server
Domaine:
agricultureType de record:
softwaremodel
Créateur:
cic
Hôte:
# Naija Food Classification Server
A Flask-based REST API for classifying Nigerian food dishes using PyTorch image classification.
## Features
- **Image Classification**: Identifies 18 different Nigerian food dishes
- **Multiple Input Formats**: Supports both file upload and base64 encoded images
- **Top-3 Predictions**: Returns the top 3 most likely food classes with confidence scores
- **CORS Enabled**: Ready for frontend integration
- **Health Check**: Monitor server status and model loading
## Supported Food Classes
The model can identify the following Nigerian dishes:
- Jollof Rice
- Egusi Soup
- Moi Moi
- Akara
- Suya
- Efo Riro
- Okra Soup
- Ofada Rice
- Pounded Yam
- Banga Soup
- Pepper Soup
- Nkwobi
- Amala
- Ewedu Soup
- Ogbono Soup
- Yam Porridge
- Puff Puff
- Chin Chin
## Installation
1. **Install Dependencies**:
```bash
pip install -r requirements.txt
```
2. **Ensure Model File**: Make sure your trained PyTorch model file `best.pt` is in the project root directory.
3. **Run the Server**:
```bash
python app.py
```
The server will start on `localhost`
## API Endpoints
### 1. Health Check
**GET** `/`
Returns server status and model information.
```bash
curl localhost
```
**Response:**
```json
{
"status": "healthy",
"message": "Naija Food Classification API is running!",
"model_loaded": true,
"classes_loaded": true,
"total_classes": 18
}
```
### 2. Get Food Classes
**GET** `/classes`
Returns the list of all supported food classes.
```bash
curl localhost
```
**Response:**
```json
{
"classes": ["Jollof Rice", "Egusi Soup", "Moi Moi", ...],
"total_classes": 18
}
```
### 3. Predict from Image File
**POST** `/predict`
Upload an image file for classification.
```bash
curl -X POST -F "image=@path/to/your/image.jpg" localhost
```
**Response:**
```json
{
"success": true,
"predictions": [
{
"class": "Jollof Rice",
"confidence": 0.89,
"percentage": "89.00%"
},
{
"class": "Ofada Ric …