第五天学 pyside2

经过5天的学习，我做了一个界面。

我称它为 yolox-qt 1.0

下面看下界面

来测一下功能

 

 

 

 训练完成自动删除路径

 

 

 功能基本成功

在测试中发现了一个问题将是在显示图片的时候

我写死了，你们可以自己改进一下。

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

# Form implementation generated from reading ui file '1.ui'
#
# Created by: PyQt5 UI code generator 5.15.6
#
# WARNING: Any manual changes made to this file will be lost when pyuic5 is
# run again.  Do not edit this file unless you know what you are doing.
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# Copyright (c) Megvii, Inc. and its affiliates.
# coding=utf-8
import pyautogui
import os
import time
import pyperclip
import os
from yolox.exp import get_exp
import cv2
import torch
from yolox.data.data_augment import ValTransform
from yolox.utils import fuse_model, get_model_info, postprocess, vis

IMAGE_EXT = [".jpg", ".jpeg", ".webp", ".bmp", ".png"]
from PySide2.QtWidgets import QMessageBox

from PyQt5 import QtCore, QtWidgets ,QtGui
import sys
from 学生系统 import demo


class Ui_Form(object):
    def setupUi(self, Form):
        Form.setObjectName("Form")
        Form.resize(716, 598)
        self.plainTextEdit = QtWidgets.QPlainTextEdit(Form)
        self.plainTextEdit.setGeometry(QtCore.QRect(180, 110, 381, 31))
        self.plainTextEdit.setObjectName("plainTextEdit")
        self.label = QtWidgets.QLabel(Form)
        self.label.setGeometry(QtCore.QRect(10, 110, 181, 20))
        self.label.setObjectName("label")
        self.label_2 = QtWidgets.QLabel(Form)
        self.label_2.setGeometry(QtCore.QRect(160, 0, 251, 61))
        self.label_2.setAlignment(QtCore.Qt.AlignLeading|QtCore.Qt.AlignLeft|QtCore.Qt.AlignVCenter)
        self.label_2.setObjectName("label_2")
        self.label_3 = QtWidgets.QLabel(Form)
        self.label_3.setGeometry(QtCore.QRect(50, 310, 471, 231))
        self.label_3.setObjectName("label_3")
        self.widget = QtWidgets.QWidget(Form)
        self.widget.setGeometry(QtCore.QRect(40, 170, 341, 43))
        self.widget.setObjectName("widget")
        self.horizontalLayout = QtWidgets.QHBoxLayout(self.widget)
        self.horizontalLayout.setContentsMargins(0, 0, 0, 0)
        self.horizontalLayout.setObjectName("horizontalLayout")
        self.radioButton = QtWidgets.QRadioButton(self.widget)
        self.radioButton.setMinimumSize(QtCore.QSize(91, 41))
        self.radioButton.setObjectName("radioButton")
        self.buttonGroup = QtWidgets.QButtonGroup(Form)
        self.buttonGroup.setObjectName("buttonGroup")
        self.buttonGroup.addButton(self.radioButton)
        self.horizontalLayout.addWidget(self.radioButton)
        self.radioButton_2 = QtWidgets.QRadioButton(self.widget)
        self.radioButton_2.setObjectName("radioButton_2")
        self.buttonGroup.addButton(self.radioButton_2)
        self.horizontalLayout.addWidget(self.radioButton_2)
        self.widget1 = QtWidgets.QWidget(Form)
        self.widget1.setGeometry(QtCore.QRect(40, 220, 401, 71))
        self.widget1.setObjectName("widget1")
        self.horizontalLayout_2 = QtWidgets.QHBoxLayout(self.widget1)
        self.horizontalLayout_2.setContentsMargins(0, 0, 0, 0)
        self.horizontalLayout_2.setObjectName("horizontalLayout_2")
        self.pushButton = QtWidgets.QPushButton(self.widget1)
        self.pushButton.setObjectName("pushButton")
        self.horizontalLayout_2.addWidget(self.pushButton)
        self.pushButton_2 = QtWidgets.QPushButton(self.widget1)
        self.pushButton_2.setObjectName("pushButton_2")
        self.horizontalLayout_2.addWidget(self.pushButton_2)
        self.pushButton_3 = QtWidgets.QPushButton(self.widget1)
        self.pushButton_3.setObjectName("pushButton_3")
        self.horizontalLayout_2.addWidget(self.pushButton_3)


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

    def retranslateUi(self, Form):
        _translate = QtCore.QCoreApplication.translate
        Form.setWindowTitle(_translate("Form", "Form"))
        self.label.setText(_translate("Form", "请输入  图片  的  路径"))
        self.label_2.setText(_translate("Form", "       yolox     可视化    界面 "))
        self.label_3.setText(_translate("Form", "                           显示界面中"))
        self.radioButton.setText(_translate("Form", "yolox_s"))
        self.radioButton_2.setText(_translate("Form", "yolox_m"))
        self.buttonGroup.buttonClicked.connect(self.qz)

        self.pushButton.setText(_translate("Form", "测试"))
        self.pushButton.clicked.connect(self.ceshi)

        self.pushButton_2.setText(_translate("Form", "显示"))
        self.pushButton_2.clicked.connect(self.xianshi)

        self.pushButton_3.setText(_translate("Form", "关闭软件"))
        self.pushButton_3.clicked.connect(self.guanbi)

    def ceshi(self):
        global a,c
        self.pushButton.setEnabled(False)
        print("测试中")
        app_dir = "C:\Windows\system32\cmd.exe"
        b=self.plainTextEdit.toPlainText()
        # C:/Users/pc/Desktop/new/qt/yolox/dog.jpg
        # 执行命令列表
        if a==1:
            cmds = ["python demo.py image -n yolox-s -c C:/Users/pc/Desktop/new/qt/yolox/w/yolox_s.pth --path "+b+" --conf 0.25 --nms 0.45 --tsize 320 --save_result --device gpu "
        ]
        elif a==2:
            cmds = [
                "python demo.py image -n yolox-m -c C:/Users/pc/Desktop/new/qt/yolox/w/yolox_m.pth --path "+b+" --conf 0.25 --nms 0.45 --tsize 640 --save_result --device gpu"]



        # 打开windows应用
        time.sleep(5)
        os.startfile(app_dir)


        # 自动跑输入命令
        pyautogui.typewrite(["enter"], '0.25')

        # 暂停5秒，定位应用界面

        # time.sleep(3)

        # 获取应用坐标，通过鼠标位置获取python demo.py image -n yolox-m -c C:/Users/pc/Desktop/new/qt/yolox/w/yolox_m.pth --path C:/Users/pc/Desktop/new/qt/yolox/dog.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device gpu
        # 获取鼠标位置
        x, y = pyautogui.position()
        # 输入命令
        for i in cmds:
            """
             解决CMD中中文不可用情况，使用右键复制
            """
            # 放置到剪贴板
            pyperclip.copy(i)
            # 右键粘贴命令
            pyautogui.click(x=x, y=y, button='right')
            time.sleep(0.5)
            # pyautogui.typewrite([x for x in i], '0.25')
            pyautogui.typewrite(["enter"], '0.25')
        os.system("taskkill /f /im cmd.exe")
        self.plainTextEdit.clear()
        c=1
        self.pushButton.setEnabled(True)
        print("训练完成")
        return  c

    def xianshi(self):
        global a, c
        print("显示")
        if c==1:
            if a==1:
                print("显示s")
                jpg = QtGui.QPixmap("C:\\Users\\31319\\Desktop\\qt\\yolox\\YOLOX_outputs\\yolox_s\\vis_res\\2022\\dog.jpg").scaled(310, 200)
                self.label_3.setPixmap(jpg)
            elif a==2:
                print("显示m")
                jpg = QtGui.QPixmap(
                    "C:\\Users\\31319\\Desktop\\qt\\yolox\\YOLOX_outputs\\yolox_m\\vis_res\\2022\\dog.jpg").scaled(310,
                                                                                                                   200)
                self.label_3.setPixmap(jpg)
        else:

            QtWidgets.QMessageBox.critical(widget, "错误", "你还没有测试")





    def guanbi(self):
        print("软件已关闭")
        exit(0)
    def qz(self):
        global a
        self.neir = self.buttonGroup.checkedButton().text()
        print("你选择的模型是")
        print(self.neir)

        if self.neir == 'yolox_s':
            a=1


        elif self.neir == 'yolox_m':
            a = 2
        return a












if __name__ == "__main__":
    c=0
    a=3
    app = QtWidgets.QApplication(sys.argv)
    widget = QtWidgets.QWidget()
    ui = Ui_Form()
    ui.setupUi(widget)

    widget.show()
    sys.exit(app.exec_())

#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# Copyright (c) Megvii, Inc. and its affiliates.


import argparse

import os
import time
from loguru import logger

import cv2


import torch

from yolox.data.data_augment import ValTransform
from yolox.data.datasets import COCO_CLASSES
from yolox.exp import get_exp
from yolox.utils import fuse_model, get_model_info, postprocess, vis

IMAGE_EXT = [".jpg", ".jpeg", ".webp", ".bmp", ".png"]


def make_parser():
    parser = argparse.ArgumentParser("YOLOX Demo!")
    parser.add_argument(
        "demo", default="image", help="demo type, eg. image, video and webcam"
    )
    parser.add_argument("-expn", "--experiment-name", type=str, default=None)
    parser.add_argument("-n", "--name", type=str, default=None, help="model name")

    parser.add_argument(
    "--path", default="./assets/dog.jpg",help="path to images or video"
    )
    parser.add_argument("--camid", type=int, default=0, help="webcam demo camera id")
    parser.add_argument(
        "--save_result",
        action="store_true",
        help="whether to save the inference result of image/video",
    )

    # exp file
    parser.add_argument(
        "-f",
        "--exp_file",
        default=None,
        type=str,
        help="pls input your experiment description file",
    )
    parser.add_argument("-c", "--ckpt", default=None, type=str, help="ckpt for eval")
    parser.add_argument(
        "--device",
        default="cpu",
        type=str,
        help="device to run our model, can either be cpu or gpu",
    )
    parser.add_argument("--conf", default=0.3, type=float, help="test conf")
    parser.add_argument("--nms", default=0.3, type=float, help="test nms threshold")
    parser.add_argument("--tsize", default=None, type=int, help="test img size")
    parser.add_argument(
        "--fp16",
        dest="fp16",
        default=False,
        action="store_true",
        help="Adopting mix precision evaluating.",
    )
    parser.add_argument(
        "--legacy",
        dest="legacy",
        default=False,
        action="store_true",
        help="To be compatible with older versions",
    )
    parser.add_argument(
        "--fuse",
        dest="fuse",
        default=False,
        action="store_true",
        help="Fuse conv and bn for testing.",
    )
    parser.add_argument(
        "--trt",
        dest="trt",
        default=False,
        action="store_true",
        help="Using TensorRT model for testing.",
    )
    return parser


def get_image_list(path):
    image_names = []
    for maindir, subdir, file_name_list in os.walk(path):
        for filename in file_name_list:
            apath = os.path.join(maindir, filename)
            ext = os.path.splitext(apath)[1]
            if ext in IMAGE_EXT:
                image_names.append(apath)
    return image_names


class Predictor(object):
    def __init__(
        self,
        model,
        exp,
        cls_names=COCO_CLASSES,
        trt_file=None,
        decoder=None,
        device="cpu",
        fp16=False,
        legacy=False,
    ):
        self.model = model
        self.cls_names = cls_names
        self.decoder = decoder
        self.num_classes = exp.num_classes
        self.confthre = exp.test_conf
        self.nmsthre = exp.nmsthre
        self.test_size = exp.test_size
        self.device = device
        self.fp16 = fp16
        self.preproc = ValTransform(legacy=legacy)
        if trt_file is not None:
            from torch2trt import TRTModule

            model_trt = TRTModule()
            model_trt.load_state_dict(torch.load(trt_file))

            x = torch.ones(1, 3, exp.test_size[0], exp.test_size[1]).cuda()
            self.model(x)
            self.model = model_trt

    def inference(self, img):
        img_info = {"id": 0}
        if isinstance(img, str):
            img_info["file_name"] = os.path.basename(img)
            img = cv2.imread(img)
        else:
            img_info["file_name"] = None

        height, width = img.shape[:2]
        img_info["height"] = height
        img_info["width"] = width
        img_info["raw_img"] = img

        ratio = min(self.test_size[0] / img.shape[0], self.test_size[1] / img.shape[1])
        img_info["ratio"] = ratio

        img, _ = self.preproc(img, None, self.test_size)
        img = torch.from_numpy(img).unsqueeze(0)
        img = img.float()
        if self.device == "gpu":
            img = img.cuda()
            if self.fp16:
                img = img.half()  # to FP16

        with torch.no_grad():
            t0 = time.time()
            outputs = self.model(img)
            if self.decoder is not None:
                outputs = self.decoder(outputs, dtype=outputs.type())
            outputs = postprocess(
                outputs, self.num_classes, self.confthre,
                self.nmsthre, class_agnostic=True
            )
            logger.info("Infer time: {:.4f}s".format(time.time() - t0))
        return outputs, img_info

    def visual(self, output, img_info, cls_conf=0.35):
        ratio = img_info["ratio"]
        img = img_info["raw_img"]
        if output is None:
            return img
        output = output.cpu()

        bboxes = output[:, 0:4]

        # preprocessing: resize
        bboxes /= ratio

        cls = output[:, 6]
        scores = output[:, 4] * output[:, 5]

        vis_res = vis(img, bboxes, scores, cls, cls_conf, self.cls_names)
        return vis_res


def image_demo(predictor, vis_folder, path, current_time, save_result):
    if os.path.isdir(path):
        files = get_image_list(path)
    else:
        files = [path]
    files.sort()
    for image_name in files:
        outputs, img_info = predictor.inference(image_name)
        result_image = predictor.visual(outputs[0], img_info, predictor.confthre)
        if save_result:
            save_folder = os.path.join(
                vis_folder, time.strftime("%Y", current_time)
            )
            os.makedirs(save_folder, exist_ok=True)
            save_file_name = os.path.join(save_folder, os.path.basename(image_name))
            logger.info("Saving detection result in {}".format(save_file_name))
            cv2.imwrite(save_file_name, result_image)
        ch = cv2.waitKey(0)
        if ch == 27 or ch == ord("q") or ch == ord("Q"):
            break


def imageflow_demo(predictor, vis_folder, current_time, args):
    cap = cv2.VideoCapture(args.path if args.demo == "video" else args.camid)
    width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)  # float
    height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)  # float
    fps = cap.get(cv2.CAP_PROP_FPS)
    save_folder = os.path.join(
        vis_folder, time.strftime("%Y_%m_%d", current_time)
    )
    os.makedirs(save_folder, exist_ok=True)
    if args.demo == "video":
        save_path = os.path.join(save_folder, args.path.split("/")[-1])
    else:
        save_path = os.path.join(save_folder, "camera.mp4")
    logger.info(f"video save_path is {save_path}")
    vid_writer = cv2.VideoWriter(
        save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (int(width), int(height))
    )
    while True:
        ret_val, frame = cap.read()
        if ret_val:
            outputs, img_info = predictor.inference(frame)
            result_frame = predictor.visual(outputs[0], img_info, predictor.confthre)
            if args.save_result:
                vid_writer.write(result_frame)
            ch = cv2.waitKey(1)
            if ch == 27 or ch == ord("q") or ch == ord("Q"):
                break
        else:
            break


def main(exp, args):
    if not args.experiment_name:
        args.experiment_name = exp.exp_name

    file_name = os.path.join(exp.output_dir, args.experiment_name)
    os.makedirs(file_name, exist_ok=True)

    vis_folder = None
    if args.save_result:
        vis_folder = os.path.join(file_name, "vis_res")
        os.makedirs(vis_folder, exist_ok=True)

    if args.trt:
        args.device = "gpu"

    logger.info("Args: {}".format(args))

    if args.conf is not None:
        exp.test_conf = args.conf
    if args.nms is not None:
        exp.nmsthre = args.nms
    if args.tsize is not None:
        exp.test_size = (args.tsize, args.tsize)

    model = exp.get_model()
    logger.info("Model Summary: {}".format(get_model_info(model, exp.test_size)))

    if args.device == "gpu":
        model.cuda()
        if args.fp16:
            model.half()  # to FP16
    model.eval()

    if not args.trt:
        if args.ckpt is None:
            ckpt_file = os.path.join(file_name, "best_ckpt.pth")
        else:
            ckpt_file = args.ckpt
        logger.info("loading checkpoint")
        ckpt = torch.load(ckpt_file, map_location="cpu")
        # load the model state dict
        model.load_state_dict(ckpt["model"])
        logger.info("loaded checkpoint done.")

    if args.fuse:
        logger.info("\tFusing model...")
        model = fuse_model(model)

    if args.trt:
        assert not args.fuse, "TensorRT model is not support model fusing!"
        trt_file = os.path.join(file_name, "model_trt.pth")
        assert os.path.exists(
            trt_file
        ), "TensorRT model is not found!\n Run python3 tools/trt.py first!"
        model.head.decode_in_inference = False
        decoder = model.head.decode_outputs
        logger.info("Using TensorRT to inference")
    else:
        trt_file = None
        decoder = None

    predictor = Predictor(
        model, exp, COCO_CLASSES, trt_file, decoder,
        args.device, args.fp16, args.legacy,
    )
    current_time = time.localtime()
    if args.demo == "image":
        image_demo(predictor, vis_folder, args.path, current_time, args.save_result)
    elif args.demo == "video" or args.demo == "webcam":
        imageflow_demo(predictor, vis_folder, current_time, args)


if __name__ == '__main__':
    args = make_parser().parse_args()
    exp = get_exp(args.exp_file, args.name)

    main(exp, args)

链接：https://pan.baidu.com/s/1Z08uL6-sRe-VX-1GywCT8w 
提取码：gope

环境