Aherobo Ovie Victor
0b7af4050e
✅ Added Simple API Documentation: - Created API_DOCS.md with comprehensive endpoint documentation - Added /docs endpoint to serve formatted API documentation - Updated /api endpoint to include documentation reference - Simple HTML formatting for better readability ✅ Documentation Features: - Complete endpoint descriptions with examples - Request/response formats for all endpoints - cURL and Python usage examples - Error response documentation - Model information and specifications ✅ Access Points: - /api - Basic API info (JSON) - /docs - Detailed documentation (HTML) - API_DOCS.md - Raw markdown documentation Simple, clean documentation without complex Swagger UI overhead.
4.0 KiB
4.0 KiB
Memory Module Detection API Documentation
Base URL
http://localhost:5002
Endpoints
1. Health Check
GET /health
Check if the API is running and model is loaded.
Response:
{
"status": "healthy",
"model_loaded": true,
"timestamp": "2025-07-12T07:41:46.123456"
}
2. API Information
GET /api
Get basic API information and available endpoints.
Response:
{
"name": "Memory Module Detection API",
"version": "1.0",
"description": "AI-powered memory module detection using YOLOv8",
"model_loaded": true,
"endpoints": ["/health", "/api", "/detect", "/detect/hardcoded", "/detect/base64"]
}
3. Upload Image Detection
POST /detect
Upload an image file for memory module detection.
Request:
- Content-Type:
multipart/form-data - Body: Form data with
filefield containing image - Optional:
confidenceparameter (default: 0.8)
Response:
{
"success": true,
"detections": [
{
"x1": 100.5,
"y1": 150.2,
"x2": 200.8,
"y2": 250.6,
"confidence": 0.95,
"class": "memory_module"
}
],
"num_detections": 1,
"annotated_image": "base64_encoded_image_string",
"confidence_threshold": 0.8
}
4. Hardcoded Test Image
GET /detect/hardcoded
Process the hardcoded test image for detection.
Query Parameters:
confidence(optional): Confidence threshold (default: 0.8)
Example:
GET /detect/hardcoded?confidence=0.9
Response:
{
"success": true,
"detections": [...],
"num_detections": 2,
"annotated_image": "base64_encoded_image_string",
"confidence_threshold": 0.9,
"test_image_path": "training/memory/out1.png"
}
5. Base64 Image Detection
POST /detect/base64
Process a base64 encoded image for detection.
Request:
{
"image_data": "base64_encoded_image_string",
"confidence": 0.8
}
Response:
{
"success": true,
"detections": [...],
"num_detections": 1,
"annotated_image": "base64_encoded_image_string",
"confidence_threshold": 0.8
}
Error Responses
All endpoints return error responses in this format:
{
"error": "Error message description",
"success": false
}
Common HTTP status codes:
200- Success400- Bad Request (invalid file, missing parameters)404- Not Found (endpoint or file not found)413- File Too Large (max 16MB)500- Internal Server Error (model not loaded, processing error)
Supported Image Formats
- PNG
- JPG/JPEG
- GIF
- BMP
File Size Limits
- Maximum upload size: 16MB
Detection Response Format
Each detection object contains:
x1, y1: Top-left corner coordinatesx2, y2: Bottom-right corner coordinatesconfidence: Detection confidence score (0.0-1.0)class: Detected object class ("memory_module")
Usage Examples
cURL Examples
Health Check:
curl http://localhost:5002/health
Upload Image:
curl -X POST -F "file=@image.jpg" -F "confidence=0.8" http://localhost:5002/detect
Hardcoded Test:
curl "http://localhost:5002/detect/hardcoded?confidence=0.9"
Python Examples
Health Check:
import requests
response = requests.get('http://localhost:5002/health')
print(response.json())
Upload Image:
import requests
with open('image.jpg', 'rb') as f:
files = {'file': f}
data = {'confidence': 0.8}
response = requests.post('http://localhost:5002/detect', files=files, data=data)
print(response.json())
Base64 Detection:
import requests
import base64
with open('image.jpg', 'rb') as f:
image_data = base64.b64encode(f.read()).decode()
payload = {
'image_data': image_data,
'confidence': 0.8
}
response = requests.post('http://localhost:5002/detect/base64', json=payload)
print(response.json())
Model Information
- Architecture: YOLOv8 Nano
- Classes: memory_module
- Input Size: 640x640
- Accuracy: 99.5% mAP50
- Inference Time: ~37ms on CPU