Update Dockerfile

Dockerfile

@@ -1,38 +1,53 @@
-FROM python:3.10-slim
-
-# Avoid interactive prompts
-ENV DEBIAN_FRONTEND=noninteractive
-
-# Set environment variables for EasyOCR and Ultralytics
-ENV EASYOCR_MODULE_PATH=/app/.EasyOCR
-ENV YOLO_CONFIG_DIR=/app/.config/Ultralytics
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    git curl build-essential ffmpeg libsm6 libxext6 \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-# Set work directory
-WORKDIR /app
-
-# Create directories for EasyOCR and Ultralytics with appropriate permissions
-RUN mkdir -p /app/.EasyOCR /app/.config/Ultralytics \
-    && chmod -R 777 /app/.EasyOCR /app/.config/Ultralytics
-
-# Copy requirements
-COPY requirements.txt .
-
-# Install Python packages
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Download YOLOv8 ANPR model weights
-RUN curl -L -o /app/anpr_yolov8.pt "https://github.com/madalinabuzatu/yolov8-license-plate-detection/releases/download/v1.0/best.pt"
-
-# Copy app code
-COPY app.py .
-
-# Expose port for Spaces or local run
-EXPOSE 7860
-
-# Run app
-CMD ["python", "app.py"]
+import torch
+from ultralytics import YOLO
+import easyocr
+import cv2
+import numpy as np
+import gradio as gr
+import os
+
+# Ensure directories exist
+os.makedirs(os.getenv('EASYOCR_MODULE_PATH', '/app/.EasyOCR'), exist_ok=True)
+os.makedirs(os.getenv('YOLO_CONFIG_DIR', '/app/.config/Ultralytics'), exist_ok=True)
+
+# Download pretrained ANPR model (trained to detect license plates)
+ANPR_WEIGHTS = "anpr_yolov8.pt"
+if not os.path.exists(ANPR_WEIGHTS):
+    os.system(f"wget -O {ANPR_WEIGHTS} https://github.com/madalinabuzatu/yolov8-license-plate-detection/releases/download/v1.0/best.pt")
+
+# Load YOLO ANPR model
+model = YOLO(ANPR_WEIGHTS)
+
+# Load OCR reader with specified model storage directory
+reader = easyocr.Reader(['en'], model_storage_directory=os.getenv('EASYOCR_MODULE_PATH', '/app/.EasyOCR'))
+
+def detect_and_read_plate(image):
+    results = model(image)
+    for result in results:
+        boxes = result.boxes.xyxy.cpu().numpy()  # [x1, y1, x2, y2]
+        for box in boxes:
+            x1, y1, x2, y2 = map(int, box)
+            # Crop the detected license plate
+            plate_img = image[y1:y2, x1:x2]
+            if plate_img.size == 0:
+                continue
+            # OCR to read text
+            ocr_result = reader.readtext(plate_img)
+            if ocr_result:
+                text = " ".join([res[1] for res in ocr_result])
+                print(f"Detected Plate: {text}")
+                # Draw bounding box + text
+                cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                cv2.putText(image, text, (x1, y1 - 10),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
+
+    return image
+
+demo = gr.Interface(
+    fn=detect_and_read_plate,
+    inputs="image",
+    outputs="image",
+    title="Automatic Number Plate Recognition (ANPR)",
+    description="Upload an image of a car to detect and read its license plate."
+)
+demo.launch(server_name="0.0.0.0", server_port=7860)