最新yolov5入门级教程，yolov5+pytorch训练自己的pvz数据并使用 自动锤僵尸

D:\Projects\Python_Machine_vision\yolov5+pvz

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

pip install (下载的离线资源的绝对地址)

pip install --no-deps (离线资源的绝对地址)

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

import cv2
import osdef mp42pic():video_path = r'D:/Projects/Python_Machine_vision/yolov5+pvz/dataset/train_mp4/pvz.mp4'  # 视频地址  自行更改out_path = r'D:/Projects/Python_Machine_vision/yolov5+pvz/dataset/data/pic/'  # 输出文件夹   自行更改interval = 10  # 每间隔10帧取一张图片,可以自行更改num = 1video = cv2.VideoCapture(video_path)# 帧率(frames per second)fps = video.get(cv2.CAP_PROP_FPS)# 总帧数(frames)frames = video.get(cv2.CAP_PROP_FRAME_COUNT)print("总帧数：" + str(frames))while video.isOpened():is_read, frame = video.read()if is_read:if num % interval == 1:file_name = '%05d' % numcv2.imwrite(out_path + str(file_name) + '.jpg', frame)cv2.waitKey(1)num += 1else:breakdef pic2mp4():print()fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')  # 设置输出视频为mp4格式# cap_fps是帧率，可自行更改cap_fps = 10# size要和图片的size一样size = (806, 640)video = cv2.VideoWriter('./self_data/result.mp4', fourcc, cap_fps, size)path = './runs/detect/exp19/'  # 图片所存放的文件夹的地址   根据自己的位置自行更改  后面要加个 /file_lst = os.listdir(path)print(len(file_lst))for i in range(len(file_lst)):img = cv2.imread(path + str(i+1) + '.jpg')video.write(img)if __name__ == '__main__':mp42pic()pic2mp4()

pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple

pip install PyQt5 -i https://pypi.tuna.tsinghua.edu.cn/simplepip install pyqt5-tools -i https://pypi.tuna.tsinghua.edu.cn/simplepip install lxml -i https://pypi.tuna.tsinghua.edu.cn/simple

import os
import shutil
import randomrandom.seed(0)def split_data(file_path, label_path, new_file_path, train_rate, val_rate, test_rate):each_class_image = []each_class_label = []for image in os.listdir(file_path):each_class_image.append(image)for label in os.listdir(label_path):each_class_label.append(label)data=list(zip(each_class_image,each_class_label))total = len(each_class_image)random.shuffle(data)each_class_image,each_class_label = zip(*data)train_images = each_class_image[0:int(train_rate * total)]val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]test_images = each_class_image[int((train_rate + val_rate) * total):]train_labels = each_class_label[0:int(train_rate * total)]val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]test_labels = each_class_label[int((train_rate + val_rate) * total):]for image in train_images:print(image)old_path = file_path + '/' + imagenew_path1 = new_file_path + '/' + 'images' + '/' + 'train'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + imageshutil.copy(old_path, new_path)for label in train_labels:print(label)old_path = label_path + '/' + labelnew_path1 = new_file_path + '/' + 'labels' + '/' + 'train'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + labelshutil.copy(old_path, new_path)for image in val_images:old_path = file_path + '/' + imagenew_path1 = new_file_path + '/' + 'images' + '/' + 'val'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + imageshutil.copy(old_path, new_path)for label in val_labels:old_path = label_path + '/' + labelnew_path1 = new_file_path + '/' + 'labels' + '/' + 'val'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + labelshutil.copy(old_path, new_path)for image in test_images:old_path = file_path + '/' + imagenew_path1 = new_file_path + '/' + 'images' + '/' + 'test'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + imageshutil.copy(old_path, new_path)for label in test_labels:old_path = label_path + '/' + labelnew_path1 = new_file_path + '/' + 'labels' + '/' + 'test'if not os.path.exists(new_path1):os.makedirs(new_path1)new_path = new_path1 + '/' + labelshutil.copy(old_path, new_path)if __name__ == '__main__':file_path = r"D:\Projects\Python_Machine_vision\yolov5+pvz\dataset\data\pic"    # 图片位置label_path = r'D:\Projects\Python_Machine_vision\yolov5+pvz\dataset\data\labels'   # 标注的TXT位置new_file_path = r"D:\Projects\Python_Machine_vision\yolov5+pvz\dataset"    #随机分配的位置split_data(file_path, label_path, new_file_path, train_rate=0.8, val_rate=0.2, test_rate=0)   # 各部分占的比例，由于我们没有测试集，所以为0

win32gui, win32con, win32com.client

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
"""
Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.Usage - sources:$ python detect.py --weights yolov5s.pt --source 0                               # webcamimg.jpg                         # imagevid.mp4                         # videoscreen                          # screenshotpath/                           # directorylist.txt                        # list of imageslist.streams                    # list of streams'path/*.jpg'                    # glob'https://youtu.be/LNwODJXcvt4'  # YouTube'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streamUsage - formats:$ python detect.py --weights yolov5s.pt                 # PyTorchyolov5s.torchscript        # TorchScriptyolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnnyolov5s_openvino_model     # OpenVINOyolov5s.engine             # TensorRTyolov5s.mlmodel            # CoreML (macOS-only)yolov5s_saved_model        # TensorFlow SavedModelyolov5s.pb                 # TensorFlow GraphDefyolov5s.tflite             # TensorFlow Liteyolov5s_edgetpu.tflite     # TensorFlow Edge TPUyolov5s_paddle_model       # PaddlePaddle
"""import argparse
import csv
import os
import platform
import sys
from pathlib import Pathimport torchFILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relativefrom ultralytics.utils.plotting import Annotator, colors, save_one_boxfrom models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
from utils.torch_utils import select_device, smart_inference_mode# pvz点击
from ctypes import *
import pyautogui
from PIL import ImageGrab
import win32gui, win32con, win32com.client
import numpy as np
import timedef cilck_init():        # 这个函数经常出错，是win32gui的原因，如果发现截图的区域与游戏画面区域不相符时可手动测量游戏画面所在的区域，放入box即可hwnd = win32gui.FindWindow(None, '植物大战僵尸中文版')print(hwnd)# 发送一个事件，防止窗口无法被放到前台shell = win32com.client.Dispatch("WScript.Shell")shell.SendKeys('%')win32gui.SetForegroundWindow(hwnd)window_x, window_y, right, bottom = win32gui.GetWindowRect(hwnd)box = (window_x, window_y, right, bottom)print(box)click_test = CDLL("pro1/Click.dll")return box, click_test@smart_inference_mode()
def run(weights=ROOT / 'runs/train/exp6/weights/best.pt',  # model path or triton URLsource=ROOT / 'self_data/pvz',  # file/dir/URL/glob/screen/0(webcam)data=ROOT / 'data/pvz.yaml',  # dataset.yaml pathimgsz=(640, 640),  # inference size (height, width)conf_thres=0.25,  # confidence thresholdiou_thres=0.45,  # NMS IOU thresholdmax_det=1000,  # maximum detections per imagedevice='0',  # cuda device, i.e. 0 or 0,1,2,3 or cpuview_img=False,  # show resultssave_txt=False,  # save results to *.txtsave_csv=False,  # save results in CSV formatsave_conf=False,  # save confidences in --save-txt labelssave_crop=False,  # save cropped prediction boxesnosave=False,  # do not save images/videosclasses=None,  # filter by class: --class 0, or --class 0 2 3agnostic_nms=False,  # class-agnostic NMSaugment=False,  # augmented inferencevisualize=False,  # visualize featuresupdate=False,  # update all modelsproject=ROOT / 'runs/detect',  # save results to project/namename='exp',  # save results to project/nameexist_ok=False,  # existing project/name ok, do not incrementline_thickness=3,  # bounding box thickness (pixels)hide_labels=False,  # hide labelshide_conf=False,  # hide confidenceshalf=False,  # use FP16 half-precision inferencednn=False,  # use OpenCV DNN for ONNX inferencevid_stride=1,  # video frame-rate stride
):source = str(source)save_img = not nosave and not source.endswith('.txt')  # save inference imagesis_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)screenshot = source.lower().startswith('screen')if is_url and is_file:source = check_file(source)  # download# Directoriessave_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir# Load modeldevice = select_device(device)model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)stride, names, pt = model.stride, model.names, model.ptimgsz = check_img_size(imgsz, s=stride)  # check image size# Dataloaderbs = 1  # batch_sizeif webcam:view_img = check_imshow(warn=True)dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)bs = len(dataset)elif screenshot:dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)else:dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)vid_path, vid_writer = [None] * bs, [None] * bs# Run inferencemodel.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmupseen, windows, dt = 0, [], (Profile(), Profile(), Profile())num_pic = 1while num_pic:background_bgr = np.array(ImageGrab.grab(box))background = background_bgr[:, :, [2, 1, 0]]   # bgr图片转为rgbcv2.imwrite('dataset/data/pvz/pvx.jpg', background)for path, im, im0s, vid_cap, s in dataset:with dt[0]:im = torch.from_numpy(im).to(model.device)im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32im /= 255  # 0 - 255 to 0.0 - 1.0if len(im.shape) == 3:im = im[None]  # expand for batch dim# Inferencewith dt[1]:visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else Falsepred = model(im, augment=augment, visualize=visualize)# NMSwith dt[2]:pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)# Second-stage classifier (optional)# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)# Define the path for the CSV filecsv_path = save_dir / 'predictions.csv'# Create or append to the CSV filedef write_to_csv(image_name, prediction, confidence):data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence}with open(csv_path, mode='a', newline='') as f:writer = csv.DictWriter(f, fieldnames=data.keys())if not csv_path.is_file():writer.writeheader()writer.writerow(data)# Process predictionsfor i, det in enumerate(pred):  # per imageseen += 1if webcam:  # batch_size >= 1p, im0, frame = path[i], im0s[i].copy(), dataset.counts += f'{i}: 'else:p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)p = Path(p)  # to Pathsave_path = str(save_dir / p.name)  # im.jpg# save_path = str(save_dir / str(num_pic)) + '.jpg'num_pic += 1txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txts += '%gx%g ' % im.shape[2:]  # print stringgn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwhimc = im0.copy() if save_crop else im0  # for save_cropannotator = Annotator(im0, line_width=line_thickness, example=str(names))if len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()# Print resultsfor c in det[:, 5].unique():n = (det[:, 5] == c).sum()  # detections per classs += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string# Write resultsxy_list = list()for *xyxy, conf, cls in reversed(det):xy = torch.tensor(xyxy).view(1, 4).tolist()[0]print(xy)# xy_list.append(xy)# for xy in xy_list:click_test.click(box[0]+int(xy[0]), box[1]+int(xy[1])+20)c = int(cls)  # integer classlabel = names[c] if hide_conf else f'{names[c]}'confidence = float(conf)confidence_str = f'{confidence:.2f}'if save_csv:write_to_csv(p.name, label, confidence_str)if save_txt:  # Write to filexywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywhline = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label formatwith open(f'{txt_path}.txt', 'a') as f:f.write(('%g ' * len(line)).rstrip() % line + '\n')if save_img or save_crop or view_img:  # Add bbox to imagec = int(cls)  # integer classlabel = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')annotator.box_label(xyxy, label, color=colors(c, True))if save_crop:save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)# Stream resultsim0 = annotator.result()if view_img:if platform.system() == 'Linux' and p not in windows:windows.append(p)cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])cv2.imshow(str(p), im0)cv2.waitKey(1)  # 1 millisecond# Save results (image with detections)if save_img:if dataset.mode == 'image':cv2.imwrite(save_path, im0)else:  # 'video' or 'stream'if vid_path[i] != save_path:  # new videovid_path[i] = save_pathif isinstance(vid_writer[i], cv2.VideoWriter):vid_writer[i].release()  # release previous video writerif vid_cap:  # videofps = vid_cap.get(cv2.CAP_PROP_FPS)w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))else:  # streamfps, w, h = 30, im0.shape[1], im0.shape[0]save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videosvid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))vid_writer[i].write(im0)# Print time (inference-only)LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")# Print resultst = tuple(x.t / seen * 1E3 for x in dt)  # speeds per imageLOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)if save_txt or save_img:s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")if update:strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)def parse_opt():parser = argparse.ArgumentParser()parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'runs/train/exp6/weights/best.pt', help='model path or triton URL')parser.add_argument('--source', type=str, default=ROOT / 'dataset/data/pvz', help='file/dir/URL/glob/screen/0(webcam)')parser.add_argument('--data', type=str, default=ROOT / 'data/pvz.yaml', help='(optional) dataset.yaml path')parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')parser.add_argument('--view-img', action='store_true', help='show results')parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')parser.add_argument('--save-csv', action='store_true', help='save results in CSV format')parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')parser.add_argument('--nosave', action='store_true', help='do not save images/videos')parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features')parser.add_argument('--update', action='store_true', help='update all models')parser.add_argument('--project', default=ROOT / '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')parser.add_argument('--line-thickness', default=2, type=int, help='bounding box thickness (pixels)')parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')opt = parser.parse_args()opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expandprint_args(vars(opt))return optdef main(opt):check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))run(**vars(opt))if __name__ == '__main__':box, click_test = cilck_init()background_bgr = np.array(ImageGrab.grab(box))cv2.imwrite('dataset/data/pvz/pvx.jpg', background_bgr)    # 先在里面任意存一张图片，否则执行代码时无法判断数据类型，我们的数据类型是JPGopt = parse_opt()main(opt)

save_path = str(save_dir / p.name)  # im.jpg
# save_path = str(save_dir / str(num_pic)) + '.jpg'