【学习经验分享NO.14】：Pyqt搭建YOLOv8/v7/v5界面(可凑大论的工作量)_yolov7可视化界面

---

前言

大论文可以写两章关于算法创新模型，最后一章可以写对前两章提出方法进行封装，利用PyQT5搭建YOLOv5可视化界面，并打包成exe程序，构建检测平台实现简单的应用。用来凑大论文的字数和工作量，是简单又快速的方法，希望能帮到毕业党们，可根据个人情况进行定制，需要可以关注私信我。YOLOv7+pyqt链接: https://pan.baidu.com/s/1XWy-gLGnccdNg_daDFa5dg 提取码: 私信获取

---

一、PYQT简介

PyQt是一个GUI小部件工具包。 它是Qt的Python接口， Qt是最强大，最受欢迎的跨平台GUI库之一。 PyQt由RiverBank Computing Ltd.开发。PyQt API是一组包含大量类和函数的模块。 虽然QtCore模块包含用于处理文件和目录等的非GUI功能，但QtGui模块包含所有图形控件。 此外，还有用于处理XML (QtXml) ，SVG (QtSvg)和SQL (QtSql)等的模块。

二、环境搭建

终端在yolov5的环境基础上安装PyQt库

		pip install PyQt5
		pip install PyQt5-tools
1
2

实现检测界面

三、实现代码

实现主程序代码如下，项目具体以及打包方法请关注后私信获取。可实现定制。

# -*- coding: utf-8 -*-

import argparse
import random
# Form implementation generated from reading ui file '.\project.ui'
#
# Created by: PyQt5 UI code generator 5.9.2
#
# WARNING! All changes made in this file will be lost!
import sys

import cv2
import numpy as np
import torch
import torch.backends.cudnn as cudnn
from PyQt5 import QtCore, QtGui, QtWidgets

from models.experimental import attempt_load
from utils.datasets import letterbox
from utils.general import check_img_size, non_max_suppression, scale_coords
from utils.plots import plot_one_box
from utils.torch_utils import select_device


class Ui_MainWindow(QtWidgets.QMainWindow):
    def __init__(self, parent=None):
        super(Ui_MainWindow, self).__init__(parent)
        self.timer_video = QtCore.QTimer()
        self.setupUi(self)
        self.init_logo()
        self.init_slots()
        self.cap = cv2.VideoCapture()
        self.out = None
        # self.out = cv2.VideoWriter('prediction.avi', cv2.VideoWriter_fourcc(*'XVID'), 20.0, (640, 480))

        parser = argparse.ArgumentParser()
        parser.add_argument('--weights', nargs='+', type=str,
                            default='weights/yolov5s.pt', help='model.pt path(s)')
        # file/folder, 0 for webcam
        parser.add_argument('--source', type=str,
                            default='data/images', help='source')
        parser.add_argument('--img-size', type=int,
                            default=640, help='inference size (pixels)')
        parser.add_argument('--conf-thres', type=float,
                            default=0.25, help='object confidence threshold')
        parser.add_argument('--iou-thres', type=float,
                            default=0.45, help='IOU threshold for NMS')
        parser.add_argument('--device', default='cpu',
                            help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
        parser.add_argument(
            '--view-img', action='store_true', help='display results')
        parser.add_argument('--save-txt', action='store_true',
                            help='save results to *.txt')
        parser.add_argument('--save-conf', action='store_true',
                            help='save confidences in --save-txt labels')
        parser.add_argument('--nosave', action='store_true',
                            help='do not save images/videos')
        parser.add_argument('--classes', nargs='+', type=int,
                            help='filter by class: --class 0, or --class 0 2 3')
        parser.add_argument(
            '--agnostic-nms', action='store_true', help='class-agnostic NMS')
        parser.add_argument('--augment', action='store_true',
                            help='augmented inference')
        parser.add_argument('--update', action='store_true',
                            help='update all models')
        parser.add_argument('--project', default='runs/detect',
                            help='save results to project/name')
        parser.add_argument('--name', default='exp',
                            help='save results to project/name')
        parser.add_argument('--exist-ok', action='store_true',
                            help='existing project/name ok, do not increment')
        self.opt = parser.parse_args()
        print(self.opt)

        source, weights, view_img, save_txt, imgsz = self.opt.source, self.opt.weights, self.opt.view_img, self.opt.save_txt, self.opt.img_size

        # self.device = select_device(self.opt.device)
        # # gpu
        # self.device = torch.device('cuda:0')

        # 如果只有cpu的话，就改成
        self.device = torch.device('cpu')

        self.half = self.device.type != 'cpu'  # half precision only supported on CUDA

        cudnn.benchmark = True

        # Load model
        self.model = attempt_load(
            weights, map_location=self.device)  # load FP32 model
        stride = int(self.model.stride.max())  # model stride
        self.imgsz = check_img_size(imgsz, s=stride)  # check img_size
        if self.half:
            self.model.half()  # to FP16

        # Get names and colors
        self.names = self.model.module.names if hasattr(
            self.model, 'module') else self.model.names
        self.colors = [[random.randint(0, 255)
                        for _ in range(3)] for _ in self.names]

    def setupUi(self, MainWindow):
        MainWindow.setObjectName("MainWindow")
        MainWindow.resize(800, 600)
        self.centralwidget = QtWidgets.QWidget(MainWindow)
        self.centralwidget.setObjectName("centralwidget")
        self.horizontalLayout_2 = QtWidgets.QHBoxLayout(self.centralwidget)
        self.horizontalLayout_2.setObjectName("horizontalLayout_2")
        self.horizontalLayout = QtWidgets.QHBoxLayout()
        self.horizontalLayout.setSizeConstraint(
            QtWidgets.QLayout.SetNoConstraint)
        self.horizontalLayout.setObjectName("horizontalLayout")
        self.verticalLayout = QtWidgets.QVBoxLayout()
        self.verticalLayout.setContentsMargins(-1, -1, 0, -1)
        self.verticalLayout.setSpacing(80)
        self.verticalLayout.setObjectName("verticalLayout")
        self.pushButton_img = QtWidgets.QPushButton(self.centralwidget)
        sizePolicy = QtWidgets.QSizePolicy(
            QtWidgets.QSizePolicy.Minimum, QtWidgets.QSizePolicy.MinimumExpanding)
        sizePolicy.setHorizontalStretch(0)
        sizePolicy.setVerticalStretch(0)
        sizePolicy.setHeightForWidth(
            self.pushButton_img.sizePolicy().hasHeightForWidth())
        self.pushButton_img.setSizePolicy(sizePolicy)
        self.pushButton_img.setMinimumSize(QtCore.QSize(150, 100))
        self.pushButton_img.setMaximumSize(QtCore.QSize(150, 100))
        font = QtGui.QFont()
        font.setFamily("Agency FB")
        font.setPointSize(12)
        self.pushButton_img.setFont(font)
        self.pushButton_img.setObjectName("pushButton_img")
        self.verticalLayout.addWidget(
            self.pushButton_img, 0, QtCore.Qt.AlignHCenter)
        self.pushButton_camera = QtWidgets.QPushButton(self.centralwidget)
        sizePolicy = QtWidgets.QSizePolicy(
            QtWidgets.QSizePolicy.Minimum, QtWidgets.QSizePolicy.Expanding)
        sizePolicy.setHorizontalStretch(0)
        sizePolicy.setVerticalStretch(0)
        sizePolicy.setHeightForWidth(
            self.pushButton_camera.sizePolicy().hasHeightForWidth())
        self.pushButton_camera.setSizePolicy(sizePolicy)
        self.pushButton_camera.setMinimumSize(QtCore.QSize(150, 100))
        self.pushButton_camera.setMaximumSize(QtCore.QSize(150, 100))
        font = QtGui.QFont()
        font.setFamily("Agency FB")
        font.setPointSize(12)
        self.pushButton_camera.setFont(font)
        self.pushButton_camera.setObjectName("pushButton_camera")
        self.verticalLayout.addWidget(
            self.pushButton_camera, 0, QtCore.Qt.AlignHCenter)
        self.pushButton_video = QtWidgets.QPushButton(self.centralwidget)
        sizePolicy = QtWidgets.QSizePolicy(
            QtWidgets.QSizePolicy.Minimum, QtWidgets.QSizePolicy.Expanding)
        sizePolicy.setHorizontalStretch(0)
        sizePolicy.setVerticalStretch(0)
        sizePolicy.setHeightForWidth(
            self.pushButton_video.sizePolicy().hasHeightForWidth())
        self.pushButton_video.setSizePolicy(sizePolicy)
        self.pushButton_video.setMinimumSize(QtCore.QSize(150, 100))
        self.pushButton_video.setMaximumSize(QtCore.QSize(150, 100))
        font = QtGui.QFont()
        font.setFamily("Agency FB")
        font.setPointSize(12)
        self.pushButton_video.setFont(font)
        self.pushButton_video.setObjectName("pushButton_video")
        self.verticalLayout.addWidget(
            self.pushButton_video, 0, QtCore.Qt.AlignHCenter)
        self.verticalLayout.setStretch(2, 1)
        self.horizontalLayout.addLayout(self.verticalLayout)
        self.label = QtWidgets.QLabel(self.centralwidget)
        self.label.setObjectName("label")
        self.horizontalLayout.addWidget(self.label)
        self.horizontalLayout.setStretch(0, 1)
        self.horizontalLayout.setStretch(1, 3)
        self.horizontalLayout_2.addLayout(self.horizontalLayout)
        MainWindow.setCentralWidget(self.centralwidget)
        self.menubar = QtWidgets.QMenuBar(MainWindow)
        self.menubar.setGeometry(QtCore.QRect(0, 0, 800, 23))
        self.menubar.setObjectName("menubar")
        MainWindow.setMenuBar(self.menubar)
        self.statusbar = QtWidgets.QStatusBar(MainWindow)
        self.statusbar.setObjectName("statusbar")
        MainWindow.setStatusBar(self.statusbar)

        self.retranslateUi(MainWindow)
        QtCore.QMetaObject.connectSlotsByName(MainWindow)

    def retranslateUi(self, MainWindow):
        _translate = QtCore.QCoreApplication.translate
        MainWindow.setWindowTitle(_translate("MainWindow", "PyQt5+YOLOv5示例"))
        self.pushButton_img.setText(_translate("MainWindow", "图片检测"))
        self.pushButton_camera.setText(_translate("MainWindow", "摄像头检测"))
        self.pushButton_video.setText(_translate("MainWindow", "视频检测"))
        self.label.setText(_translate("MainWindow", "TextLabel"))

    def init_slots(self):
        self.pushButton_img.clicked.connect(self.button_image_open)
        self.pushButton_video.clicked.connect(self.button_video_open)
        self.pushButton_camera.clicked.connect(self.button_camera_open)
        self.timer_video.timeout.connect(self.show_video_frame)

    def init_logo(self):
        pix = QtGui.QPixmap('wechat.jpg')
        self.label.setScaledContents(True)
        self.label.setPixmap(pix)

    def button_image_open(self):
        print('button_image_open')
        name_list = []

        img_name, _ = QtWidgets.QFileDialog.getOpenFileName(
            self, "打开图片", "", "*.jpg;;*.png;;All Files(*)")
        if not img_name:
            return

        img = cv2.imread(img_name)
        print(img_name)
        showimg = img
        with torch.no_grad():
            img = letterbox(img, new_shape=self.opt.img_size)[0]
            # Convert
            # BGR to RGB, to 3x416x416
            img = img[:, :, ::-1].transpose(2, 0, 1)
            img = np.ascontiguousarray(img)
            img = torch.from_numpy(img).to(self.device)
            img = img.half() if self.half else img.float()  # uint8 to fp16/32
            img /= 255.0  # 0 - 255 to 0.0 - 1.0
            if img.ndimension() == 3:
                img = img.unsqueeze(0)
            # Inference
            pred = self.model(img, augment=self.opt.augment)[0]
            # Apply NMS
            pred = non_max_suppression(pred, self.opt.conf_thres, self.opt.iou_thres, classes=self.opt.classes,
                                       agnostic=self.opt.agnostic_nms)
            print(pred)
            # Process detections
            for i, det in enumerate(pred):
                if det is not None and len(det):
                    # Rescale boxes from img_size to im0 size
                    det[:, :4] = scale_coords(
                        img.shape[2:], det[:, :4], showimg.shape).round()

                    for *xyxy, conf, cls in reversed(det):
                        label = '%s %.2f' % (self.names[int(cls)], conf)
                        name_list.append(self.names[int(cls)])
                        plot_one_box(xyxy, showimg, label=label,
                                     color=self.colors[int(cls)], line_thickness=2)

        cv2.imwrite('prediction.jpg', showimg)
        self.result = cv2.cvtColor(showimg, cv2.COLOR_BGR2BGRA)
        self.result = cv2.resize(
            self.result, (640, 480), interpolation=cv2.INTER_AREA)
        self.QtImg = QtGui.QImage(
            self.result.data, self.result.shape[1], self.result.shape[0], QtGui.QImage.Format_RGB32)
        self.label.setPixmap(QtGui.QPixmap.fromImage(self.QtImg))

    def button_video_open(self):
        video_name, _ = QtWidgets.QFileDialog.getOpenFileName(
            self, "打开视频", "", "*.mp4;;*.avi;;All Files(*)")

        if not video_name:
            return

        flag = self.cap.open(video_name)
        if flag == False:
            QtWidgets.QMessageBox.warning(
                self, u"Warning", u"打开视频失败", buttons=QtWidgets.QMessageBox.Ok, defaultButton=QtWidgets.QMessageBox.Ok)
        else:
            self.out = cv2.VideoWriter('prediction.avi', cv2.VideoWriter_fourcc(
                *'MJPG'), 20, (int(self.cap.get(3)), int(self.cap.get(4))))
            self.timer_video.start(30)
            self.pushButton_video.setDisabled(True)
            self.pushButton_img.setDisabled(True)
            self.pushButton_camera.setDisabled(True)

    def button_camera_open(self):
        if not self.timer_video.isActive():
            # 默认使用第一个本地camera
            flag = self.cap.open(0)
            if flag == False:
                QtWidgets.QMessageBox.warning(
                    self, u"Warning", u"打开摄像头失败", buttons=QtWidgets.QMessageBox.Ok, defaultButton=QtWidgets.QMessageBox.Ok)
            else:
                self.out = cv2.VideoWriter('prediction.avi', cv2.VideoWriter_fourcc(
                    *'MJPG'), 20, (int(self.cap.get(3)), int(self.cap.get(4))))
                self.timer_video.start(30)
                self.pushButton_video.setDisabled(True)
                self.pushButton_img.setDisabled(True)
                self.pushButton_camera.setText(u"关闭摄像头")
        else:
            self.timer_video.stop()
            self.cap.release()
            self.out.release()
            self.label.clear()
            self.init_logo()
            self.pushButton_video.setDisabled(False)
            self.pushButton_img.setDisabled(False)
            self.pushButton_camera.setText(u"摄像头检测")

    def show_video_frame(self):
        name_list = []

        flag, img = self.cap.read()
        if img is not None:
            showimg = img
            with torch.no_grad():
                img = letterbox(img, new_shape=self.opt.img_size)[0]
                # Convert
                # BGR to RGB, to 3x416x416
                img = img[:, :, ::-1].transpose(2, 0, 1)
                img = np.ascontiguousarray(img)
                img = torch.from_numpy(img).to(self.device)
                img = img.half() if self.half else img.float()  # uint8 to fp16/32
                img /= 255.0  # 0 - 255 to 0.0 - 1.0
                if img.ndimension() == 3:
                    img = img.unsqueeze(0)
                # Inference
                pred = self.model(img, augment=self.opt.augment)[0]

                # Apply NMS
                pred = non_max_suppression(pred, self.opt.conf_thres, self.opt.iou_thres, classes=self.opt.classes,
                                           agnostic=self.opt.agnostic_nms)
                # Process detections
                for i, det in enumerate(pred):  # detections per image
                    if det is not None and len(det):
                        # Rescale boxes from img_size to im0 size
                        det[:, :4] = scale_coords(
                            img.shape[2:], det[:, :4], showimg.shape).round()
                        # Write results
                        for *xyxy, conf, cls in reversed(det):
                            label = '%s %.2f' % (self.names[int(cls)], conf)
                            name_list.append(self.names[int(cls)])
                            print(label)
                            plot_one_box(
                                xyxy, showimg, label=label, color=self.colors[int(cls)], line_thickness=2)

            self.out.write(showimg)
            show = cv2.resize(showimg, (640, 480))
            self.result = cv2.cvtColor(show, cv2.COLOR_BGR2RGB)
            showImage = QtGui.QImage(self.result.data, self.result.shape[1], self.result.shape[0],
                                     QtGui.QImage.Format_RGB888)
            self.label.setPixmap(QtGui.QPixmap.fromImage(showImage))

        else:
            self.timer_video.stop()
            self.cap.release()
            self.out.release()
            self.label.clear()
            self.pushButton_video.setDisabled(False)
            self.pushButton_img.setDisabled(False)
            self.pushButton_camera.setDisabled(False)
            self.init_logo()


if __name__ == '__main__':
    app = QtWidgets.QApplication(sys.argv)
    ui = Ui_MainWindow()
    ui.show()
    sys.exit(app.exec_())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360

总结

本文介绍了PyQt与yolov5结合，构建GUI界面，便于将yolov5算法进行实际应用，可实现个人实际定制。关注即免费获取大量人工智能学习资料。