python api 使用 yolov8预测

首先，你需要安装`yolov5`库。你可以在终端中执行以下命令来安装：

pip install yolov5

接下来，你需要下载`yolov5`的预训练模型。你可以在[yolov5官网](https://github.com/ultralytics/yolov5/releases)下载。

下载完成后，你可以使用以下代码加载模型并进行预测：

import torch
import cv2
from PIL import Image
import numpy as np
from matplotlib import pyplot as plt
from yolov5.models.experimental import attempt_load
from yolov5.utils.general import non_max_suppression, scale_coords
from yolov5.utils.torch_utils import select_device

def predict(image_path):
    # Load the model
    weights = 'path/to/weights.pt'
    device = select_device('cpu')
    model = attempt_load(weights, map_location=device)

    # Load the image
    img = cv2.imread(image_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img = Image.fromarray(img)

    # Make predictions
    img_size = 640
    img = img.resize((img_size, img_size), resample=Image.BILINEAR)
    img = np.array(img).transpose(2, 0, 1)
    img = torch.from_numpy(img).unsqueeze(0).float() / 255.0
    pred = model(img, size=img_size)[0]
    pred = non_max_suppression(pred, conf_thres=0.5, iou_thres=0.5, agnostic=False, classes=None)

    # Process the predictions
    for det in pred:
        if det is not None and len(det):
            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img.shape[2:]).round()
            for *xyxy, conf, cls in det:
                label = f'{model.names[int(cls)]} {conf:.2f}'
                xyxy = [int(x) for x in xyxy]
                cv2.rectangle(img, (xyxy[0], xyxy[1]), (xyxy[2], xyxy[3]), (0, 255, 0), 2)
                cv2.putText(img, label, (xyxy[0], xyxy[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)

    # Display the image
    plt.imshow(img)
    plt.show()

predict('path/to/image.jpg')

在上面的代码中，`weights`变量是你下载的预训练模型的路径。`predict`函数接受一个图像的路径作为输入，然后返回一个带有预测结果的图像。你可以通过调整`conf_thres`和`iou_thres`参数来控制预测的精度和召回率。