Initial commit: Recycling object detection project

- Added Fast api web application for recycling object detection
- Included YOLOv8 model training notebook
- Set up project structure with datasets and training directories
- Added requirements.txt for dependencies
- Configured .gitignore for Python virtual environment and cache files

.gitignore

@@ -0,0 +1,6 @@
+.venv
+__pycache__
+
+augmented_dataset
+
+training

README.md

@@ -0,0 +1,54 @@
+# DS Task Recycling Project
+
+This project is a toy project for training and quality assurance purposes. It involves developing a simple Flask API that processes an image (or a hardcoded image) of a motherboard and detects memory modules present on it. The API will return the image with bounding boxes drawn around each detected memory module.
+
+## Project Overview
+
+- **Input Types:**
+
+  - Image upload via the Flask API.
+  - A hardcoded image for testing purposes.
+- **Dataset:**
+
+  - 20 pictures of motherboards with memory.
+  - 20 pictures of motherboards without memory.
+- **Output:**
+
+  - An annotated image with bounding boxes around each detected memory module.
+    For example, if there are two memory modules, two boxes are drawn; if only one is detected, then one box is drawn.
+- **Annotation Tool Suggestion:**
+
+  - We suggest using [makesense.ai](https://www.makesense.ai/) for manual annotation if needed.
+
+## Task Details
+
+The developer is required to research and answer the following questions as part of the task:
+
+1. **Algorithm Choice:**
+
+   - Which algorithm will you use for detecting the memory modules?
+   - Why do you choose this particular algorithm?
+2. **Hardware Considerations:**
+
+   - Does CPU or GPU have an impact on your decision? Please explain.
+3. **Video Input:**
+
+   - What if a video is provided instead of single images?
+   - Does your approach change when processing videos? Please describe your approach.
+
+## Proposed Flask API Implementation
+
+1. **API Endpoints:**
+
+   - An endpoint for uploading images which processes and returns the annotated image.
+   - An endpoint parameter for using a hardcoded image for testing purposes.
+2. **Processing Workflow:**
+
+   - Receive an image (either via file upload or from a hardcoded source).
+   - Apply the chosen object detection algorithm to detect memory modules.
+   - Draw bounding boxes around each detected memory module.
+   - Return the annotated image to the user.
+
+## Data Set:
+
+Dataset in on the `training` folder. And there is `memory` and `no_memory` subfolder in it.

app.py

@@ -0,0 +1,50 @@
+from fastapi import FastAPI, File, UploadFile, Request
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+import uvicorn
+from ultralytics import YOLO
+import cv2
+import numpy as np
+from PIL import Image
+import io
+import os
+import base64
+
+app = FastAPI()
+
+# Initialize templates
+templates = Jinja2Templates(directory="templates")
+
+# Load YOLO model
+current_directory = os.getcwd()
+model_path = current_directory + '\\datasets\\runs\\detect\\train8\\weights\\last.pt'
+model = YOLO(model_path)
+
+@app.get("/", response_class=HTMLResponse)
+async def home(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+@app.post("/upload")
+async def upload_image(file: UploadFile = File(...)):
+    # Read the uploaded file
+    contents = await file.read()
+    
+    # Convert to numpy array
+    nparr = np.frombuffer(contents, np.uint8)
+    img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
+    
+    # Run YOLO prediction
+    results = model(img)
+    
+    # Draw bounding boxes
+    annotated_img = results[0].plot()
+    
+    # Convert to base64
+    _, img_encoded = cv2.imencode('.jpg', annotated_img)
+    img_base64 = base64.b64encode(img_encoded).decode('utf-8')
+    
+    return {"image": img_base64}
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="localhost", port=8000)

datasets/data.yaml

@@ -0,0 +1,6 @@
+
+train: images/train
+val: images/val
+
+nc: 1
+names: ['memory']