当涉及 YOLO(You Only Look Once)目标检测模型时,其实现涉及复杂的神经网络和预训练模型。因此,我提供一个示例代码,使用 opencv-python
库加载 YOLO 模型并对图像进行目标检测。
首先,确保你已经安装了 opencv-python
库。如果没有安装,可以使用以下命令安装:
import cv2
import numpy as np
# 加载YOLO模型及相关文件
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()]
# 加载测试图像
img = cv2.imread('test_image.jpg')
img = cv2.resize(img, None, fx=0.4, fy=0.4)
height, width, channels = img.shape
# 目标检测
blob = cv2.dnn.blobFromImage(img, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
# 显示检测结果
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:
# 目标检测框坐标
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# 边框的坐标
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
colors = np.random.uniform(0, 255, size=(len(classes), 3))
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = f"{classes[class_ids[i]]}: {confidences[i]:.2f}"
color = colors[class_ids[i]]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(img, label, (x, y + 30), font, 2, color, 2)
# 显示结果
cv2.imshow('Image', img)
cv2.waitKey(0)
cv2.destroyAllWindows()