app.py

import cv2
import numpy as np
import gradio as gr
import requests

# Configuration files
config_file = "ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt"
frozen_model = "frozen_inference_graph.pb"

# Load model and set it to use the GPU
model = cv2.dnn.DetectionModel(frozen_model, config_file)
model.setInputSize(320, 320)
model.setInputScale(1.0 / 127.5)
model.setInputMean((127.5, 127.5, 127.5))
model.setInputSwapRB(True)
model.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
model.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)

# Load class labels
classLabels = []
with open('labels.txt', 'rt') as f:
    classLabels = f.read().rstrip('\n').split('\n')

def detect_objects(frame):
    """
    Detect objects in a single frame and return their coordinates and names.
    :param frame: Input image/frame
    :return: List of detected objects with coordinates and names
    """
    detections = []
    
    # Detect objects in the frame
    ClassIndex, confidence, bbox = model.detect(frame, confThreshold=0.55)
    
    if len(ClassIndex) != 0:
        for ClassInd, conf, boxes in zip(ClassIndex.flatten(), confidence.flatten(), bbox):
            if ClassInd <= 80:
                x, y, w, h = boxes
                detected_object = {
                    "name": classLabels[ClassInd - 1],
                    "coordinates": {
                        "x": int(x),
                        "y": int(y),
                        "width": int(w),
                        "height": int(h)
                    }
                }
                detections.append(detected_object)
                
    return detections

def get_image_from_url(url):
    response = requests.get(url)
    image = np.asarray(bytearray(response.content), dtype="uint8")
    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
    return image

def detect_objects_in_image_url(url):
    frame = get_image_from_url(url)
    detected_objects = detect_objects(frame)
    return detected_objects

# Define the Gradio interface
iface = gr.Interface(
    fn=detect_objects_in_image_url,
    inputs="text",
    outputs=gr.JSON(),
    title="Object Detection",
    description="Enter an image URL to detect objects. The detected objects will be returned as JSON."
)

# Launch the interface
iface.launch()