OpenCV, Yolov3 이용하여 이미지 속 객체 인식

다음 이미지를 클릭하여
cfg와 weights 파일을 다운받는다. (난 yolo3 608으로 다운받음)
YOLOv3-tiny < YOLOv3-320 < YOLOv3-416 < YOLOv3-608 = YOLOv3-spp
오른쪽으로 갈수록 정확도 높아지지만 속도 느려지고 요구사항 높아야한다.

coco.names는
여기서 다운받을 수 있다

import cv2
import numpy as np

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

#img load
img = cv2.imread("sample.jpg")
img = cv2.resize(img, None, fx=0.4, fy=0.4)
height, width, channels = img.shape

blob = cv2.dnn.blobFromImage(img, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)

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 > 0.5:
            center_x = int(detection[0] * width)
            center_y = int(detection[1] * height)
            w = int(detection[2] * width)
            h = int(detection[3] * height)

            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)

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, 2)
        cv2.putText(img, label, (x, y+30), font, 3, color, 3)

cv2.imshow("Image", img)
cv2.waitKey(0)

cv2.destroyAllWindows()

결과