Updated API

requirements.txt

@@ -6,4 +6,5 @@ scikit-learn>=1.0.2
 pydantic>=1.10.0
 python-dotenv>=1.0.0
 gradio>=4.0.0
-requests>=2.31.0
+requests>=2.31.0
+librosa==0.10.2.post1

tasks/audio.py

@@ -3,16 +3,21 @@ from datetime import datetime
 from datasets import load_dataset
 from sklearn.metrics import accuracy_score
 import random
+import os
 
 from .utils.evaluation import AudioEvaluationRequest
 from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
+from dotenv import load_dotenv
+load_dotenv()
+
 router = APIRouter()
 
 DESCRIPTION = "Random Baseline"
 ROUTE = "/audio"
 
 
+
 @router.post(ROUTE, tags=["Audio Task"],
              description=DESCRIPTION)
 async def evaluate_audio(request: AudioEvaluationRequest):
@@ -31,19 +36,10 @@ async def evaluate_audio(request: AudioEvaluationRequest):
         "chainsaw": 0,
         "environment": 1
     }
-
-    try:
-        from huggingface_hub import login
-        login()
-    except:
-        pass
-
     # Load and prepare the dataset
-    dataset = load_dataset(request.dataset_name)
-
-    # Convert string labels to integers
-    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
-
+    # Because the dataset is gated, we need to use the HF_TOKEN environment variable to authenticate
+    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"]

tasks/image.py

@@ -1,32 +1,172 @@
 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 .utils.evaluation import ImageEvaluationRequest
-from .utils.emissions import get_space_info
+from .utils.emissions import tracker, clean_emissions_data, get_space_info
+
+from dotenv import load_dotenv
+load_dotenv()
 
 router = APIRouter()
 
 DESCRIPTION = "Random Baseline"
 ROUTE = "/image"
 
+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.
+    Evaluate image classification and object detection for forest fire smoke.
     
     Current Model: Random Baseline
-    - Makes random predictions
+    - 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()
-    return {
-        "message": "Image evaluation endpoint not yet implemented",
+    
+    # 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 = []
+    true_boxes_list = []  # List of lists, each inner list contains boxes for one image
+    
+    for example in test_dataset:
+        # Parse true annotation (YOLO format: class_id x_center y_center width height)
+        annotation = example.get("annotations", "").strip()
+        has_smoke = len(annotation) > 0
+        true_labels.append(int(has_smoke))
+        
+        # Make random classification prediction
+        pred_has_smoke = random.random() > 0.5
+        predictions.append(int(pred_has_smoke))
+        
+        # If there's a true box, parse it and make random box prediction
+        if has_smoke:
+            # Parse all true boxes from the annotation
+            image_true_boxes = parse_boxes(annotation)
+            true_boxes_list.append(image_true_boxes)
+            
+            # For baseline, make one random box prediction per image
+            # In a real model, you might want to predict multiple boxes
+            random_box = [
+                random.random(),  # x_center
+                random.random(),  # y_center
+                random.random() * 0.5,  # width (max 0.5)
+                random.random() * 0.5   # height (max 0.5)
+            ]
+            pred_boxes.append(random_box)
+    
+    #--------------------------------------------------------------------------------------------
+    # 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,
-        "route": ROUTE,
+        "submission_timestamp": datetime.now().isoformat(),
         "model_description": DESCRIPTION,
-        "received_config": {
+        "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