在代码中使用训练好的YOLO各版本的模型

recursive=True&expand=False (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。是 OpenCV（一个开源的计算机视觉库）的一个函数，用于在图像上绘制矩形。

文章共4,189字 · 阅读需要大约14分钟

一键AI生成摘要，助你高效阅读

问答

天宇2323

1556人浏览 · 2023-10-30 22:07:11

天宇2323 · 2023-10-30 22:07:11 发布

方法一、利用YOLO模块加载模型

下载模块

加载权重文件和图片，并进正向推导预测 (文件地址一定要对，最好不要出现中文)

预测摄像头当前拍摄的内容

函数部分的提示：

方法二、利用pytorch加载模型

代码部分（这里加载本地模型，并进行前向传播）

torch.hub.load()函数的使用

方法三（推荐）、利用ultralytics加载

下载模块

注意：这里一共会展示三种方式，推荐第三种方法

方法一、利用YOLO模块加载模型

下载模块

这里拿YOLOv5举例，同样你也可以下载YOLOv8等，如pip install yolov8 等等。

pip install yolov5
pip install opencv-python

加载权重文件和图片，并进正向推导预测 (文件地址一定要对，最好不要出现中文)

import cv2
import yolov5
model = yolov5.load('runs/train/exp/weights/best.pt')
imgPath = 'dataset/test/images/0db77f7288ba94280cfb8fb98d3f56cb.jpg'
results = model(imgPath, augment=True)

img=cv2.imread(imgPath)

#以下可以获取到标签label，以及检测框的左上右下角坐标，并为图画框
for *xyxy, conf, cls in results.xyxy[0]:
    label = f'{model.model.names[int(cls)]} {conf:.2f}'
    cv2.rectangle(img, (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3])), (0, 0, 255), 2)
    cv2.putText(img, label, (int(xyxy[0]), int(xyxy[1]) - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255), 2)
print("label:"+str(label))


# 显示帧
cv2.imshow('YOLOv5 Real-time Object Detection', img)
cv2.waitKey(0)

#如果想保存
 #cv2.imwrite('output.jpg', img)

效果如下

路径地址错误可能会出现如下问题（建议路径不要出现中文，再不想尝试用绝对地址而非相对地址）

requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/weights/yolov5s.pt/tree/main?recursive=True&expand=False (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x0000021B0220D580>: Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))"), '(Request ID: 5d71cb57-14f3-401f-81d1-0e13e48e6f91)')

预测摄像头当前拍摄的内容

import cv2
from yolov5 import YOLOv5

# 加载预训练的YOLOv5模型
model = YOLOv5("F:/File/AI/deepLearn/yolov5-master/weights/yolov5s.pt",device='cpu')  # 选择模型


# 打开摄像头
cap = cv2.VideoCapture(0)

while True:
    # 从摄像头读取帧
    ret, frame = cap.read()

    if not ret:
        break

    # 使用YOLOv5进行目标检测
    results = model.predict(frame)

    # 在帧上绘制检测结果
    #xyxy得到左上右下角点坐标数组，conf代表置信度，cls代表类型名的下标
    for *xyxy, conf, cls in results.xyxy[0]:
        label = f'{model.model.names[int(cls)]} {conf:.2f}'
        cv2.rectangle(frame, (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3])), (0, 0, 255), 2)
        cv2.putText(frame, label, (int(xyxy[0]), int(xyxy[1]) - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, color=(0, 0, 255), thickness=2)

    # 显示帧
    cv2.imshow('YOLOv5 Real-time Object Detection', frame)

    # 按w键退出
    if cv2.waitKey(1) & 0xFF == ord('W'):
        break

# 释放资源并关闭窗口
cap.release()
cv2.destroyAllWindows()

效果

可能会遇到的问题

cv2.error: OpenCV(4.8.0) D:\a\opencv-python\opencv-python\opencv\modules\highgui\src\window.cpp:1272 error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage'

我的用如下方法解决了问题。

pip uninstall opencv-python
pip install opencv-python

函数部分的提示：

  label = f'{model.model.names[int(cls)]} {conf:.2f}'

f '{……}' #表示这是一个格式化字符串。
model.model.names[int(cls)] #获取类型名。
conf:.2f #表示置信值小数位为2

方法二、利用pytorch.hub.load加载模型

注意事项：这里的加载本地模型的代码文件要和YOLO项目的modes文件夹和hubconf.py同一目录，models文件夹存放了配置的yaml文件和Yolo的加载模型权重并进行正向传播的py文件。hubconf.py在联网情况下会自己加载。

hubconf.py文件

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
"""
PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5

Usage:
    import torch
    model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # official model
    model = torch.hub.load('ultralytics/yolov5:master', 'yolov5s')  # from branch
    model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.pt')  # custom/local model
    model = torch.hub.load('.', 'custom', 'yolov5s.pt', source='local')  # local repo
"""

import torch


def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
    """Creates or loads a YOLOv5 model

    Arguments:
        name (str): model name 'yolov5s' or path 'path/to/best.pt'
        pretrained (bool): load pretrained weights into the model
        channels (int): number of input channels
        classes (int): number of model classes
        autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
        verbose (bool): print all information to screen
        device (str, torch.device, None): device to use for model parameters

    Returns:
        YOLOv5 model
    """
    from pathlib import Path

    from models.common import AutoShape, DetectMultiBackend
    from models.experimental import attempt_load
    from models.yolo import ClassificationModel, DetectionModel, SegmentationModel
    from utils.downloads import attempt_download
    from utils.general import LOGGER, ROOT, check_requirements, intersect_dicts, logging
    from utils.torch_utils import select_device

    if not verbose:
        LOGGER.setLevel(logging.WARNING)
    check_requirements(ROOT / 'requirements.txt', exclude=('opencv-python', 'tensorboard', 'thop'))
    name = Path(name)
    path = name.with_suffix('.pt') if name.suffix == '' and not name.is_dir() else name  # checkpoint path
    try:
        device = select_device(device)
        if pretrained and channels == 3 and classes == 80:
            try:
                model = DetectMultiBackend(path, device=device, fuse=autoshape)  # detection model
                if autoshape:
                    if model.pt and isinstance(model.model, ClassificationModel):
                        LOGGER.warning('WARNING ⚠️ YOLOv5 ClassificationModel is not yet AutoShape compatible. '
                                       'You must pass torch tensors in BCHW to this model, i.e. shape(1,3,224,224).')
                    elif model.pt and isinstance(model.model, SegmentationModel):
                        LOGGER.warning('WARNING ⚠️ YOLOv5 SegmentationModel is not yet AutoShape compatible. '
                                       'You will not be able to run inference with this model.')
                    else:
                        model = AutoShape(model)  # for file/URI/PIL/cv2/np inputs and NMS
            except Exception:
                model = attempt_load(path, device=device, fuse=False)  # arbitrary model
        else:
            cfg = list((Path(__file__).parent / 'models').rglob(f'{path.stem}.yaml'))[0]  # model.yaml path
            model = DetectionModel(cfg, channels, classes)  # create model
            if pretrained:
                ckpt = torch.load(attempt_download(path), map_location=device)  # load
                csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
                csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors'])  # intersect
                model.load_state_dict(csd, strict=False)  # load
                if len(ckpt['model'].names) == classes:
                    model.names = ckpt['model'].names  # set class names attribute
        if not verbose:
            LOGGER.setLevel(logging.INFO)  # reset to default
        return model.to(device)

    except Exception as e:
        help_url = 'https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading'
        s = f'{e}. Cache may be out of date, try `force_reload=True` or see {help_url} for help.'
        raise Exception(s) from e


def custom(path='path/to/model.pt', autoshape=True, _verbose=True, device=None):
    # YOLOv5 custom or local model
    return _create(path, autoshape=autoshape, verbose=_verbose, device=device)


def yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-nano model https://github.com/ultralytics/yolov5
    return _create('yolov5n', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-small model https://github.com/ultralytics/yolov5
    return _create('yolov5s', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-medium model https://github.com/ultralytics/yolov5
    return _create('yolov5m', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-large model https://github.com/ultralytics/yolov5
    return _create('yolov5l', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
    return _create('yolov5x', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5
    return _create('yolov5n6', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
    return _create('yolov5s6', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
    return _create('yolov5m6', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
    return _create('yolov5l6', pretrained, channels, classes, autoshape, _verbose, device)


def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, _verbose=True, device=None):
    # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
    return _create('yolov5x6', pretrained, channels, classes, autoshape, _verbose, device)


if __name__ == '__main__':
    import argparse
    from pathlib import Path

    import numpy as np
    from PIL import Image

    from utils.general import cv2, print_args

    # Argparser
    parser = argparse.ArgumentParser()
    parser.add_argument('--model', type=str, default='yolov5s', help='model name')
    opt = parser.parse_args()
    print_args(vars(opt))

    # Model
    model = _create(name=opt.model, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True)
    # model = custom(path='path/to/model.pt')  # custom

    # Images
    imgs = [
        'data/images/zidane.jpg',  # filename
        Path('data/images/zidane.jpg'),  # Path
        'https://ultralytics.com/images/zidane.jpg',  # URI
        cv2.imread('data/images/bus.jpg')[:, :, ::-1],  # OpenCV
        Image.open('data/images/bus.jpg'),  # PIL
        np.zeros((320, 640, 3))]  # numpy

    # Inference
    results = model(imgs, size=320)  # batched inference

    # Results
    results.print()
    results.save()

代码部分（这里加载本地模型，并进行前向传播）

这里还是拿YOLOv5模型举例

import cv2
import torch
import time
import numpy as np

model = torch.hub.load('.', 'custom', path="D:\\file\\test\\yolov5-master\\runs\\train\\exp5\\weights\\best.pt",source='local')
model.conf = 0.4


frame = cv2.imread('D:/file/files/labelsTest/54d8382de683ce00014a2899.jpg')
img_cvt = cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

results = model(img_cvt)

#results_ = results.pandas().xyxy[0].to_numpy()

# 绘制检测结果
for *xyxy, conf, cls in results.xyxy[0]:
    label = f'{model.model.names[int(cls)]} {conf:.2f}'
    cv2.rectangle(frame, (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3])), (0, 0, 255), 2)
    cv2.putText(frame, label, (int(xyxy[0]), int(xyxy[1]) - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255), 2)

# 显示帧
cv2.imshow('YOLOv5 Real-time Object Detection', frame)
cv2.waitKey()

展示效果

torch.hub.load()函数的使用

torch.hub.load是PyTorch中一个方便的API，用于从GitHub上的预训练模型仓库中加载模型。它允许用户在不离开Python环境的情况下，直接从GitHub中下载模型并加载它们。

例如yolov5项目主分支的官方地址https://github.com/ultralytics/yolov5/tree/master ，想加载yolov5模型并使用，可用如下代码。

import torch

# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s")  # or yolov5n - yolov5x6, custom

# Images
img = "https://ultralytics.com/images/zidane.jpg"  # or file, Path, PIL, OpenCV, numpy, list

# Inference
results = model(img)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

第一个参数为可选标签/分支格式的 github 存储库，前面的“https://github.com/”不要加进去，它自己会加，你只要加分支tree前父目录"ultralytics/yolov5"。(目前看来，通过网络下载的情况，参数变动大，建议想联网下载模型时，去读这类项目的readme.md，一般有说明)

函数原型：

torch.hub.load(repo_or_dir, model, *args, source='github', force_reload=False, verbose=True, skip_validation=False, **kwargs)

参数说明：
repo_or_dir ( string ) – 如果source是 ‘github’，这应该对应于repo_owner/repo_name[:tag_name] 方括号表示可选，该参数表示具有可选标签/分支格式的 github 存储库，例如 ‘pytorch/vision:0.10’。如果tag_name未指定，则假定默认分支为main存在，否则为master。如果source是“local”，则它应该是本地目录的路径。

model ( string ) – 在 repo/dir’s 中定义的可调用（入口点）的名称hubconf.py。

*args（可选）– callable 的相应参数model。

source ( string , optional ) – ‘github’ 或 ‘local’。指定如何 repo_or_dir解释。默认为“github”。

force_reload ( bool , optional ) – 是否无条件强制重新下载github repo。如果没有任何影响 source = ‘local’。默认为False

verbose ( bool , optional ) – 如果False，静音有关命中本地缓存的消息。请注意，有关首次下载的消息无法静音。如果source = 'local’没有任何影响。默认为True。

skip_validation ( bool , optional ) – 如果False，torchhub 将检查github参数指定的分支或提交是否正确属于 repo 所有者。这将向 GitHub API 发出请求；您可以通过设置GITHUB_TOKEN环境变量来指定非默认 GitHub 令牌。默认为False。

**kwargs (可选) – callable 的相应 kwargs model。

1、联网

model = torch.hub.load('ultralytics/yolov5', 'yolov5s')

2、加载本地模型

model = torch.hub.load('.', 'custom', path="D:\\file\\test\\yolov5-master\\runs\\train\\exp5\\weights\\best.pt",source='local')

方法三（推荐）、利用ultralytics加载

ultralytics是YOLO官方的组件，它可以加载YOLOv3——YOLOv8版本模型，而且使用相当方便，这也为什么推荐使用这一个。注意：模型需要也是ultralytics工具训练的

下载模块

pip install ultralytics

并建议确保下载

pip install opencv-python

这里继续拿yolov5举例代码部分

from ultralytics import YOLO
import cv2


# 加载一个在COCO数据集上预训练的YOLOv5n模型
model = YOLO('yolov5n.pt')

# 显示模型信息（可选）
model.info()


cap = cv2.VideoCapture(0)



# 循环遍历视频帧
while cap.isOpened():
    # 从视频读取一帧
    success, frame = cap.read()

    if success:
        # 在帧上运行YOLO
        results = model.track(frame, persist=True)

        # 获取框
        boxes = results[0].boxes.xywh.cpu()
        track_ids = results[0].boxes.id.int().cpu().tolist()

        # 在帧上展示结果
        annotated_frame = results[0].plot()

        # 展示带注释的帧
        cv2.imshow("YOLOv8 Tracking", annotated_frame)

        # 如果按下'q'则退出循环
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # 如果视频结束则退出循环
        break

# 释放视频捕获对象并关闭显示窗口
cap.release()
cv2.destroyAllWindows()

展示效果

也可使用YOLOv8模型版本，这里使用方法差不多，如下

记得确保pip install lapx

from collections import defaultdict

import cv2
import numpy as np

from ultralytics import YOLO

# 加载YOLOv8模型
model = YOLO('yolov8n.pt')

# 打开视频文件
#video_path = "path/to/video.mp4"
cap = cv2.VideoCapture(0)

# 存储追踪历史
track_history = defaultdict(lambda: [])

# 循环遍历视频帧
while cap.isOpened():
    # 从视频读取一帧
    success, frame = cap.read()

    if success:
        # 在帧上运行YOLOv8追踪，持续追踪帧间的物体
        results = model.track(frame, persist=True)

        # 获取框和追踪ID
        boxes = results[0].boxes.xywh.cpu()
        track_ids = results[0].boxes.id.int().cpu().tolist()

        # 在帧上展示结果
        annotated_frame = results[0].plot()

        # 绘制追踪路径
        for box, track_id in zip(boxes, track_ids):
            x, y, w, h = box
            track = track_history[track_id]
            track.append((float(x), float(y)))  # x, y中心点
            if len(track) > 30:  # 在90帧中保留90个追踪点
                track.pop(0)

            # 绘制追踪线
            points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
            cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10)

        # 展示带注释的帧
        cv2.imshow("YOLOv8 Tracking", annotated_frame)

        # 如果按下'q'则退出循环
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # 如果视频结束则退出循环
        break

# 释放视频捕获对象并关闭显示窗口
cap.release()
cv2.destroyAllWindows()

展示效果