加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
main.py 15.98 KB
一键复制 编辑 原始数据 按行查看 历史
xugaoxiang 提交于 2021-10-26 15:11 . exception
# -*- coding: utf-8 -*-
# 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 argparse
import random
import torch
import numpy as np
import torch.backends.cudnn as cudnn
from PyQt5 import QtCore, QtGui, QtWidgets
from utils.torch_utils import select_device
from models.experimental import attempt_load
from utils.general import check_img_size, non_max_suppression, scale_coords
from utils.datasets import letterbox
from utils.plots import plot_one_box
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='',
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)
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_())
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化