使用OpenCV、ONNXRuntime部署YOLOV7实时目标检测的代码

好的，下面是使用OpenCV和ONNXRuntime来部署YOLOV7实时目标检测的代码：

import cv2
import numpy as np
import onnxruntime as ort

# 加载模型
model_path = "yolov7.onnx"
session = ort.InferenceSession(model_path)

# 输入、输出名
input_name = session.get_inputs()[0].name
output_names = [session.get_outputs()[i].name for i in range(len(session.get_outputs()))]

# 类别名称
class_names = ["person", "car", "truck", "bus"]

# 预处理函数
def preprocess(image, target_shape):
    # 图像缩放
    h, w = image.shape[:2]
    scale = min(target_shape[0] / h, target_shape[1] / w)
    new_h, new_w = int(h * scale), int(w * scale)
    image_resized = cv2.resize(image, (new_w, new_h))

    # 图像填充
    pad_h = target_shape[0] - new_h
    pad_w = target_shape[1] - new_w
    top, bottom = pad_h // 2, pad_h - pad_h // 2
    left, right = pad_w // 2, pad_w - pad_w // 2
    image_padded = cv2.copyMakeBorder(image_resized, top, bottom, left, right, cv2.BORDER_CONSTANT)

    # 图像归一化
    image_scaled = image_padded / 255.0
    image_normalized = (image_scaled - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]
    image_transposed = np.transpose(image_normalized, [2, 0, 1])
    image_batched = np.expand_dims(image_transposed, axis=0)

    return image_batched

# 后处理函数
def postprocess(outputs, conf_threshold, iou_threshold):
    # 输出解码
    objects = []
    for i, output in enumerate(outputs):
        grid_size = output.shape[2]
        anchor_size = 3
        num_classes = output.shape[1] - 5

        boxes = output.reshape([-1, 5 + num_classes])
        boxes[:, 0:2] = (boxes[:, 0:2] + np.arange(grid_size).reshape([1, -1, 1])) / grid_size
        boxes[:, 2:4] = np.exp(boxes[:, 2:4]) * anchor_size / grid_size
        boxes[:, 4:] = np.exp(boxes[:, 4:]) / (1 + np.exp(-boxes[:, 4:]))
        boxes[:, 5:] = boxes[:, 4:5] * boxes[:, 5:]

        mask = boxes[:, 4] > conf_threshold
        boxes = boxes[mask]

        classes = np.argmax(boxes[:, 5:], axis=-1)
        scores = boxes[:, 4] * boxes[:, 5 + classes]
        mask = scores > conf_threshold
        boxes = boxes[mask]
        classes = classes[mask]
        scores = scores[mask]

        for cls, score, box in zip(classes, scores, boxes):
            if cls >= num_classes:
                continue
            x, y, w, h = box[:4]
            x1, y1, x2, y2 = x - w / 2, y - h / 2, x + w / 2, y + h / 2
            objects.append([x1, y1, x2, y2, score, class_names[cls]])

    # 非极大抑制
    objects = sorted(objects, key=lambda x: x[4], reverse=True)
    for i in range(len(objects)):
        if objects[i][4] == 0:
            continue
        for j in range(i + 1, len(objects)):
            if iou(objects[i][:4], objects[j][:4]) > iou_threshold:
                objects[j][4] = 0

    # 输出筛选
    objects = [obj for obj in objects if obj[4] > conf_threshold]

    return objects

# IOU计算函数
def iou(box1, box2):
    x1, y1, x2, y2 = box1
    x3, y3, x4, y4 = box2
    left = max(x1, x3)
    top = max(y1, y3)
    right = min(x2, x4)
    bottom = min(y2, y4)
    intersection = max(0, right - left) * max(0, bottom - top)
    area1 = (x2 - x1) * (y2 - y1)
    area2 = (x4 - x3) * (y4 - y3)
    union = area1 + area2 - intersection
    return intersection / (union + 1e-6)

# 摄像头读取
cap = cv2.VideoCapture(0)

while True:
    # 读取帧
    ret, frame = cap.read()

    # 预处理
    image = preprocess(frame, (416, 416))

    # 推理
    outputs = session.run(output_names, {input_name: image})

    # 后处理
    objects = postprocess(outputs, conf_threshold=0.5, iou_threshold=0.5)

    # 可视化
    for obj in objects:
        x1, y1, x2, y2, score, class_name = obj
        cv2.rectangle(frame, (int(x1 * frame.shape[1]), int(y1 * frame.shape[0])),
                      (int(x2 * frame.shape[1]), int(y2 * frame.shape[0])), (0, 255, 0), 2)
        cv2.putText(frame, class_name + ": " + str(round(score, 2)), (int(x1 * frame.shape[1]), int(y1 * frame.shape[0]) - 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)

    # 显示结果
    cv2.imshow("YOLOV7", frame)

    # 退出
    if cv2.waitKey(1) == ord("q"):
        break

# 释放资源
cap.release()
cv2.destroyAllWindows()

这段代码通过摄像头实时读取视频流，对每一帧进行目标检测，并将检测结果可视化显示在窗口中。在代码中，我们首先加载了YOLOV7模型，并定义了输入、输出名和类别名称。接着，我们定义了预处理函数和后处理函数，用于对输入图像进行预处理和输出结果进行解码、筛选和可视化。最后，我们通过OpenCV读取摄像头视频流，对每一帧进行目标检测并实时显示在窗口中，直到按下“q”键退出程序。