learnopencv/Integrating-Gradio-with-OpenCV-DNN/yolov3.py

import cv2
import numpy as np


# Load yolo
def load_yolo():
    net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
    classes = []
    with open("coco.names", "r") as f:
        classes = [line.strip() for line in f.readlines()]

    output_layers = [layer_name for layer_name in net.getUnconnectedOutLayersNames()]
    colors = np.random.uniform(0, 255, size=(len(classes), 3))
    return net, classes, colors, output_layers


def load_image(img_path):
    # image loading
    img = cv2.imread(img_path)
    img = cv2.resize(img, None, fx=0.4, fy=0.4)
    height, width, channels = img.shape
    return img, height, width, channels


def start_webcam():
    cap = cv2.VideoCapture(0)

    return cap


def display_blob(blob):
    """
    Three images each for RED, GREEN, BLUE channel
    """
    for b in blob:
        for n, imgb in enumerate(b):
            cv2.imshow(str(n), imgb)


def detect_objects_yolo(img, net, outputLayers):
    blob = cv2.dnn.blobFromImage(img, scalefactor=0.00392, size=(320, 320), mean=(0, 0, 0), swapRB=True, crop=False)
    net.setInput(blob)
    outputs = net.forward(outputLayers)
    # print(outputs)
    # for i, out in enumerate(outputs):
    # 	print(i, np.array(out).shape)
    return blob, outputs


def get_box_dimensions_yolo(outputs, height, width):
    boxes = []
    confs = []
    class_ids = []
    for output in outputs:
        for detect in output:
            scores = detect[5:]
            # print('detect', scores)
            class_id = np.argmax(scores)
            conf = scores[class_id]
            if conf > 0.3:
                center_x = int(detect[0] * width)
                center_y = int(detect[1] * height)
                w = int(detect[2] * width)
                h = int(detect[3] * height)
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)
                boxes.append([x, y, w, h])
                # print(boxes)
                confs.append(float(conf))
                class_ids.append(class_id)
    return boxes, confs, class_ids


def draw_labels_yolo(boxes, confs, colors, class_ids, classes, img):
    indexes = cv2.dnn.NMSBoxes(boxes, confs, 0.5, 0.4)
    font = cv2.FONT_HERSHEY_PLAIN
    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            color = colors[i]
            cv2.rectangle(img, (x, y), (x + w, y + h), color, 5)
            cv2.putText(img, label, (x, y - 5), font, 5, color, 5)
    return img


def image_detect_yolo(img_path):
    model, classes, colors, output_layers = load_yolo()
    image, height, width, channels = load_image(img_path)
    blob, outputs = detect_objects_yolo(image, model, output_layers)
    # print(outputs)
    boxes, confs, class_ids = get_box_dimensions_yolo(outputs, height, width)
    image = draw_labels_yolo(boxes, confs, colors, class_ids, classes, image)
    return image


cv2.destroyAllWindows()