tasks/image.py

from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
import numpy as np
from sklearn.metrics import accuracy_score
import random
import os

from ultralytics import YOLO  # Import YOLO
from .utils.evaluation import ImageEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info

from dotenv import load_dotenv
load_dotenv()

router = APIRouter()

DESCRIPTION = "YOLO Smoke Detection"
ROUTE = "/image"

yolo_model = YOLO("best.pt")

def parse_boxes(annotation_string):
    """Parse multiple boxes from a single annotation string.
    Each box has 5 values: class_id, x_center, y_center, width, height"""
    values = [float(x) for x in annotation_string.strip().split()]
    boxes = []
    # Each box has 5 values
    for i in range(0, len(values), 5):
        if i + 5 <= len(values):
            # Skip class_id (first value) and take the next 4 values
            box = values[i+1:i+5]
            boxes.append(box)
    return boxes

def compute_iou(box1, box2):
    """Compute Intersection over Union (IoU) between two YOLO format boxes."""
    # Convert YOLO format (x_center, y_center, width, height) to corners
    def yolo_to_corners(box):
        x_center, y_center, width, height = box
        x1 = x_center - width/2
        y1 = y_center - height/2
        x2 = x_center + width/2
        y2 = y_center + height/2
        return np.array([x1, y1, x2, y2])
    
    box1_corners = yolo_to_corners(box1)
    box2_corners = yolo_to_corners(box2)
    
    # Calculate intersection
    x1 = max(box1_corners[0], box2_corners[0])
    y1 = max(box1_corners[1], box2_corners[1])
    x2 = min(box1_corners[2], box2_corners[2])
    y2 = min(box1_corners[3], box2_corners[3])
    
    intersection = max(0, x2 - x1) * max(0, y2 - y1)
    
    # Calculate union
    box1_area = (box1_corners[2] - box1_corners[0]) * (box1_corners[3] - box1_corners[1])
    box2_area = (box2_corners[2] - box2_corners[0]) * (box2_corners[3] - box2_corners[1])
    union = box1_area + box2_area - intersection
    
    return intersection / (union + 1e-6)

def compute_max_iou(true_boxes, pred_box):
    """Compute maximum IoU between a predicted box and all true boxes"""
    max_iou = 0
    for true_box in true_boxes:
        iou = compute_iou(true_box, pred_box)
        max_iou = max(max_iou, iou)
    return max_iou

@router.post(ROUTE, tags=["Image Task"],
             description=DESCRIPTION)
async def evaluate_image(request: ImageEvaluationRequest):
    """
    Evaluate image classification and object detection for forest fire smoke.
    
    Current Model: Random Baseline
    - Makes random predictions for both classification and bounding boxes
    - Used as a baseline for comparison
    
    Metrics:
    - Classification accuracy: Whether an image contains smoke or not
    - Object Detection accuracy: IoU (Intersection over Union) for smoke bounding boxes
    """
    # Get space info
    username, space_url = get_space_info()
    
    # Load and prepare the dataset
    dataset = load_dataset(request.dataset_name, token=os.getenv("HF_TOKEN"))
    
    # Split dataset
    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
    test_dataset = train_test["test"]
    
    # Start tracking emissions
    tracker.start()
    tracker.start_task("inference")
    
    #--------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE CODE HERE
    # Update the code below to replace the random baseline with your model inference
    #--------------------------------------------------------------------------------------------   
    predictions = []
    true_labels = []
    pred_boxes = []  # Flattened list of predicted boxes
    true_boxes_list = []  # Flattened list of ground truth boxes

    for example in test_dataset:
        # Extract image and annotations
        image = example["image"]
        annotation = example.get("annotations", "").strip()
        
        # Determine if ground truth smoke is present
        has_smoke = len(annotation) > 0
        true_labels.append(1 if has_smoke else 0)
    
        # Parse ground truth boxes if smoke is present
        if has_smoke:
            image_true_boxes = parse_boxes(annotation)
            if image_true_boxes:
                true_boxes_list.append(image_true_boxes)
            else:
                true_boxes_list.append([])  # Add empty list if parsing fails
        else:
            true_boxes_list.append([])  # Add empty list for no ground truth smoke
    
        # Perform YOLO inference
        results = yolo_model .predict(image, verbose=False)
        
        # Extract predicted box if predictions exist
        if len(results[0].boxes):
            pred_box = results[0].boxes.xywhn[0].cpu().numpy().tolist()
            predictions.append(1)  # Predicted smoke
            pred_boxes.append(pred_box)
        else:
            predictions.append(0)  # No smoke predicted
            pred_boxes.append([])  # Add empty list if no prediction

    # Filter out entries with empty boxes
    filtered_true_boxes_list = []
    filtered_pred_boxes = []

    for true_boxes, pred_boxes_entry in zip(true_boxes_list, pred_boxes):
        if true_boxes and pred_boxes_entry:  # Keep only if neither is empty
            filtered_true_boxes_list.append(true_boxes)
            filtered_pred_boxes.append(pred_boxes_entry)
    
    
    # Replace the original lists with the filtered ones
    true_boxes_list = filtered_true_boxes_list
    pred_boxes = filtered_pred_boxes
    
       

    
    #--------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE STOPS HERE
    #--------------------------------------------------------------------------------------------   
    
    # Stop tracking emissions
    emissions_data = tracker.stop_task()
    
    # Calculate classification accuracy
    classification_accuracy = accuracy_score(true_labels, predictions)
    
    # Calculate mean IoU for object detection (only for images with smoke)
    # For each image, we compute the max IoU between the predicted box and all true boxes
    ious = []
    for true_boxes, pred_box in zip(true_boxes_list, pred_boxes):
        max_iou = compute_max_iou(true_boxes, pred_box)
        ious.append(max_iou)
    
    mean_iou = float(np.mean(ious)) if ious else 0.0
    
    # Prepare results dictionary
    results = {
        "username": username,
        "space_url": space_url,
        "submission_timestamp": datetime.now().isoformat(),
        "model_description": DESCRIPTION,
        "classification_accuracy": float(classification_accuracy),
        "mean_iou": mean_iou,
        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
        "emissions_gco2eq": emissions_data.emissions * 1000,
        "emissions_data": clean_emissions_data(emissions_data),
        "api_route": ROUTE,
        "dataset_config": {
            "dataset_name": request.dataset_name,
            "test_size": request.test_size,
            "test_seed": request.test_seed
        }
    }
    return results