app.py

import gradio as gr
import mediapipe as mp
import cv2
import numpy as np

BaseOptions = mp.tasks.BaseOptions
ObjectDetector = mp.tasks.vision.ObjectDetector
ObjectDetectorOptions = mp.tasks.vision.ObjectDetectorOptions
VisionRunningMode = mp.tasks.vision.RunningMode

MARGIN = 10  # pixels
ROW_SIZE = 10  # pixels
FONT_SIZE = 1
FONT_THICKNESS = 1
TEXT_COLOR = (255, 0, 0)  # red

def visualize(image, detection_result) -> np.ndarray:
  for detection in detection_result.detections:
    # Draw bounding_box
    bbox = detection.bounding_box
    start_point = bbox.origin_x, bbox.origin_y
    end_point = bbox.origin_x + bbox.width, bbox.origin_y + bbox.height
    cv2.rectangle(image, start_point, end_point, TEXT_COLOR, 3)

    # Draw label and score
    category = detection.categories[0]
    category_name = category.category_name
    probability = round(category.score, 2)
    result_text = category_name + ' (' + str(probability) + ')'
    text_location = (MARGIN + bbox.origin_x,
                     MARGIN + ROW_SIZE + bbox.origin_y)
    cv2.putText(image, result_text, text_location, cv2.FONT_HERSHEY_PLAIN,
                FONT_SIZE, TEXT_COLOR, FONT_THICKNESS)
  return image

def analyze_image(image):
    model_path = "efficientdet_lite0.tflite"

    options = ObjectDetectorOptions(
    base_options=BaseOptions(model_asset_path=model_path),
    max_results=5,
    running_mode=VisionRunningMode.IMAGE)

    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=image)

    with ObjectDetector.create_from_options(options) as detector:
        detection_result = detector.detect(mp_image)

    image_copy = np.copy(mp_image.numpy_view())
    annotated_image = visualize(image_copy, detection_result)

    return annotated_image

img_in = gr.Image()
#img_out = gr.Image()

iface = gr.Interface(fn=analyze_image, inputs=img_in, outputs="image")
iface.launch()