updated roboflow model to improve accuracy

app.py

@@ -42,7 +42,6 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MinMaxScaler
 from inference_sdk import InferenceHTTPClient, InferenceConfiguration
 
-# Initialize Flask app
 app = Flask(__name__)
 
 GDRIVE_MODEL_URL = "https://drive.google.com/uc?id=1fzKneepaRt_--dzamTcDBM-9d3_dLX7z"
@@ -92,15 +91,11 @@ def fetchImage():
         file = io.BytesIO(response.content)
     elif "file" in request.files:
         file = request.files["file"]
-    # url = "https://firebasestorage.googleapis.com/v0/b/car-damage-detector-s34rrz.firebasestorage.app/o/users%2FYMd99dt33HaktTWpYp5MM5oYeBE3%2Fuploads%2F1737454072124000.jpg?alt=media&token=9eae79fa-4c06-41a5-9f58-236c39efaac0"
 
-    # File name for saving
     file_name = f"downloaded_image_{random.randint(1,50)}.jpg"
 
-    # Download the image
     response = requests.get(url)
 
-    # Save the image to the current directory
     if response.status_code == 200:
         image = Image.open(io.BytesIO(response.content))
 
@@ -113,120 +108,28 @@ def fetchImage():
         print(f"Failed to download image. Status code: {response.status_code}")
     image = cv2.imread(file_name)
 
-    rf = Roboflow(api_key="LqD8Cs4OsoK8seO3CPkf")
-
-    project_parts = rf.workspace().project("car-parts-segmentation")
-    model_parts = project_parts.version(2).model
-
-    project_damage = rf.workspace().project("car-damage-detection-ha5mm")
-    model_damage = project_damage.version(1).model
-
-    # Run the damage detection model
-    result_damage = model_damage.predict(
-        file_name,
-        confidence=40,
-    ).json()
-
-    # Extract detections from the result
-    detections_damage = sv.Detections.from_inference(result_damage)
-
-    # Read the input image
-
-    # Annotate damaged areas of the car
-    mask_annotator = sv.MaskAnnotator()
-    annotated_image_damage = mask_annotator.annotate(
-        scene=image, detections=detections_damage
-    )
-
-    # temp_dir = tempfile.mkdtemp()
-
-    # Define a repair cost dictionary (per part)
-    repair_costs = {
-        "damage-front-windscreen": 500,
-        "damaged-door": 550,
-        "damaged-fender": 450,
-        "damaged-front-bumper": 440,
-        "damaged-head-light": 480,
-        "damaged-hood": 490,
-        "damaged-rear-bumper": 510,
-        "damaged-rear-window": 505,
-        "damaged-side-window": 501,
-        "damaged-tail-light": 478,
-        "quaterpanel-dent": 520
+    repair_costs_inr = {
+        "damage-front-windscreen": 1200,  # Includes glass replacement and labor
+        "damaged-door": 1500,  # Includes denting, painting, and panel replacement if needed
+        "damaged-fender": 900,  # Includes denting, painting, and possible part replacement
+        "damaged-front-bumper": 1100,  # Includes bumper replacement and painting
+        "damaged-head-light": 700,  # Headlight unit replacement
+        "damaged-hood": 1400,  # Hood denting, painting, or full replacement
+        "damaged-rear-bumper": 1000,  # Bumper replacement and painting
+        "damaged-rear-window": 1100,  # Rear windshield glass replacement
+        "damaged-side-window": 800,  # Side window glass replacement
+        "damaged-tail-light": 600,  # Tail light unit replacement
+        "quarterpanel-dent": 1200  # Dent removal and repainting
     }
 
     total_cost = 0
 
-    # coordinates = list(map(int, detections_damage.xyxy.flatten()))
-    # num_damages = (
-    #     len(coordinates) // 4
-    # )  # Each damage has 4 coordinates (x1, y1, x2, y2)
-
-    # Iterate through damages
-    # for i in range(num_damages):
-    #     x1, y1, x2, y2 = coordinates[i * 4: (i + 1) * 4]
-
-    #     # Ensure the coordinates are within image bounds
-    #     x1, y1 = max(0, x1), max(0, y1)
-    #     x2, y2 = min(image.shape[1], x2), min(image.shape[0], y2)
-
-    #     # Crop the damaged region
-    #     cropped_damage = image[y1:y2, x1:x2]
-
-    #     # Check if the cropped region is valid
-    #     if cropped_damage.size == 0:
-    #         print(f"Skipping empty crop for damage region {i + 1}")
-    #         continue
-
-    #     # Save the cropped damaged area
-    #     damage_image_path = os.path.join(temp_dir, f"damage_image_{i}.png")
-    #     cv2.imwrite(damage_image_path, cropped_damage)
-
-    #     # Run the parts detection model on the cropped damage
-    #     result_parts = model_parts.predict(
-    #         damage_image_path, confidence=15).json()
-    #     detections_parts = sv.Detections.from_inference(result_parts)
-
-    #     # Calculate repair cost for each detected part
-    #     for part in result_parts["predictions"]:
-    #         part_name = part["class"]
-    #         damage_area = part["width"] * part["height"]
-    #         cropped_area = (x2 - x1) * (y2 - y1)
-    #         damage_percentage = (damage_area / cropped_area) * 100
-
-    #         # Lookup cost and add to total
-    #         base_cost = repair_cost_dict.get(
-    #             part_name, 0
-    #         )  # Default to 0 if part not in dict
-    #         repair_cost = (damage_percentage / 100) * 10 * base_cost
-    #         total_cost += round(repair_cost, ndigits=1)
-
-    #         print(
-    #             f"Damage {i + 1} - {part_name}: {damage_percentage:.2f}% damaged, Cost: ${repair_cost:.2f}"
-    #         )
-
-    #     # Annotate and save the result
-    #     part_annotator = sv.LabelAnnotator()
-    #     annotated_parts_image = part_annotator.annotate(
-    #         scene=cropped_damage, detections=detections_parts
-    #     )
-    #     annotated_parts_path = os.path.join(
-    #         temp_dir, f"annotated_parts_{i}.png")
-    #     cv2.imwrite(annotated_parts_path, annotated_parts_image)
-
-    # # Save the overall annotated image
-    # annotated_image_path = os.path.join(temp_dir, "annotated_image_damage.png")
-    # cv2.imwrite(annotated_image_path, annotated_image_damage)
-
-    # # Return the total cost in the specified format
-
     CLIENT = InferenceHTTPClient(
         api_url="https://detect.roboflow.com",
         api_key="LqD8Cs4OsoK8seO3CPkf"
     )
     print(file_name)
 
-    # Set confidence threshold to 50%
     custom_configuration = InferenceConfiguration(confidence_threshold=0.7)
     with CLIENT.use_configuration(custom_configuration):
         result = CLIENT.infer(