app.py

import os
import cv2
import numpy as np
import importlib.util
import gradio as gr
from PIL import Image

# Load the TensorFlow Lite model
MODEL_DIR = 'model'
GRAPH_NAME = 'detect.tflite'
LABELMAP_NAME = 'labelmap.txt'

pkg = importlib.util.find_spec('tflite_runtime')
if pkg:
    from tflite_runtime.interpreter import Interpreter
    from tflite_runtime.interpreter import load_delegate
else:
    from tensorflow.lite.python.interpreter import Interpreter
    from tensorflow.lite.python.interpreter import load_delegate

PATH_TO_CKPT = os.path.join(MODEL_DIR, GRAPH_NAME)
PATH_TO_LABELS = os.path.join(MODEL_DIR, LABELMAP_NAME)

# Load the label map
with open(PATH_TO_LABELS, 'r') as f:
    labels = [line.strip() for line in f.readlines()]

if labels[0] == '???':
    del(labels[0])

# Load the TensorFlow Lite model
interpreter = Interpreter(model_path=PATH_TO_CKPT)
interpreter.allocate_tensors()

input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
height = input_details[0]['shape'][1]
width = input_details[0]['shape'][2]
floating_model = (input_details[0]['dtype'] == np.float32)

input_mean = 127.5
input_std = 127.5

outname = output_details[0]['name']
if ('StatefulPartitionedCall' in outname):
    boxes_idx, classes_idx, scores_idx = 1, 3, 0
else:
    boxes_idx, classes_idx, scores_idx = 0, 1, 2

def perform_detection(image, interpreter, labels):
    imH, imW, _ = image.shape
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image_resized = cv2.resize(image_rgb, (width, height))
    input_data = np.expand_dims(image_resized, axis=0)

    if floating_model:
        input_data = (np.float32(input_data) - input_mean) / input_std

    interpreter.set_tensor(input_details[0]['index'], input_data)
    interpreter.invoke()

    boxes = interpreter.get_tensor(output_details[boxes_idx]['index'])[0]
    classes = interpreter.get_tensor(output_details[classes_idx]['index'])[0]
    scores = interpreter.get_tensor(output_details[scores_idx]['index'])[0]

    detections = []
    for i in range(len(scores)):
        if ((scores[i] > 0.5) and (scores[i] <= 1.0)):
            ymin = int(max(1, (boxes[i][0] * imH)))
            xmin = int(max(1, (boxes[i][1] * imW)))
            ymax = int(min(imH, (boxes[i][2] * imH)))
            xmax = int(min(imW, (boxes[i][3] * imW)))
            
            cv2.rectangle(image, (xmin, ymin), (xmax, ymax), (10, 255, 0), 2)
            object_name = labels[int(classes[i])]
            label = '%s: %d%%' % (object_name, int(scores[i] * 100))
            labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
            label_ymin = max(ymin, labelSize[1] + 10)
            cv2.rectangle(image, (xmin, label_ymin - labelSize[1] - 10), (xmin + labelSize[0], label_ymin + baseLine - 10), (255, 255, 255), cv2.FILLED)
            cv2.putText(image, label, (xmin, label_ymin - 7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2)

            detections.append([object_name, scores[i], xmin, ymin, xmax, ymax])
    return image

def detect_image(input_image):
    image = np.array(input_image)
    result_image = perform_detection(image, interpreter, labels)
    return Image.fromarray(result_image)

def detect_video(input_video):
    cap = cv2.VideoCapture(input_video.name)
    frames = []

    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break

        result_frame = perform_detection(frame, interpreter, labels)
        frames.append(result_frame)

    cap.release()

    height, width, layers = frames[0].shape
    size = (width, height)
    output_video_path = "result_" + input_video.name
    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'DIVX'), 15, size)

    for frame in frames:
        out.write(frame)

    out.release()

    return output_video_path

image_input = gr.inputs.Image(type="pil", label="Upload an image")
image_output = gr.outputs.Image(type="pil", label="Detection Result")

video_input = gr.inputs.Video(type="file", label="Upload a video")
video_output = gr.outputs.Video(label="Detection Result")

app = gr.Interface(
    fn=detect_image,
    inputs=image_input,
    outputs=image_output,
    live=True,
    description="Object Detection on Images"
)

app_video = gr.Interface(
    fn=detect_video,
    inputs=video_input,
    outputs=video_output,
    live=True,
    description="Object Detection on Videos"
)

gr.TabbedInterface([app, app_video], ["Image Detection", "Video Detection"]).launch()