yolo_object_detection.py

# If you use VSCode
from cv2 import cv2
# else
# import cv2
import numpy as np
import random
import matplotlib.pyplot as plt

# Load Yolo
net = cv2.dnn.readNetFromDarknet("cfg/yolov3_garb_test2.cfg",r"weights/garb.weights")

# Name custom object
classes = open(".names/garb2.names").read().strip().split("\n")


cap = cv2.VideoCapture("assets/plastic-test3.mp4")
print(cap)

layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))


# loop through them cap
while True:
    # Loading frame
    ret, img = cap.read()


    height, width = img.shape[:2]

    # Detecting objects
    blob = cv2.dnn.blobFromImage(img, 1/255.0, (416, 416), swapRB=True, crop=False)
    net.setInput(blob)

    outs = net.forward(output_layers)

    # Showing informations on the screen
    class_ids = []
    confidences = []
    boxes = []

    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.3:
                # Object detected
                print("ID da classe:  ")
                print(class_id)
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                # Rectangle coordinates
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)

                boxes.append([x, y, w, h])
                confidences.append(float(confidence))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
    print("Index: ")
    print(indexes)
    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[class_ids[i]]
            cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
            cv2.putText(img, label, (x, y + 30), font, 3, color, 2)


    cv2.imshow("Frame", img)
    if ord("q") == cv2.waitKey(1):
        break

cap.release()
cv2.destroyAllWindows()