# 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 # webcam img.jpg # image vid.mp4 # video screen # screenshot path/ # directory list.txt # list of images list.streams # list of streams 'path/*.jpg' # glob 'https://youtu.be/Zgi9g1ksQHc' # YouTube 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream Usage - formats: $ python detect.py --weights yolov5s.pt # PyTorch yolov5s.torchscript # TorchScript yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn yolov5s_openvino_model # OpenVINO yolov5s.engine # TensorRT yolov5s.mlmodel # CoreML (macOS-only) yolov5s_saved_model # TensorFlow SavedModel yolov5s.pb # TensorFlow GraphDef yolov5s.tflite # TensorFlow Lite yolov5s_edgetpu.tflite # TensorFlow Edge TPU yolov5s_paddle_model # PaddlePaddle """ import matplotlib.path as mat import requests import argparse import os import platform import sqlite3 import sys import threading import time from pathlib import Path import signal import torch from concurrent.futures import ThreadPoolExecutor from concurrent.futures import ProcessPoolExecutor from multiprocessing import Process,Manager,Value from multiprocessing import Queue from multiprocessing import set_start_method import multiprocessing import multiprocessing as mp import numpy as np from torchvision import transforms FILE = 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())) # relative from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages,LoadStreams, LoadStreamsSQLNEWN,LoadStreamsSQL,LoadStreamsSQLNRERT,LoadStreamsVEight,LoadStreamsSQLT,LoadStreamsSQLTN 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,strtolst,apply_classifier1,apply_classifieruniform,compute_IOU,task,apply_classifierarm) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import select_device, smart_inference_mode from utils.renwu import newHelmet,newUniform,Fall,Personcount,Arm,Bag,Cross,Extinguisher,Persontre,Bag,Danager from transformers import AutoProcessor, AutoModelForVision2Seq #from testpool import func1,TestA # def my_handler(signum, frame): # exit(0) #url = "http://36.7.84.146:18802/ai-service/open/api/operate/upload" url = "http://172.19.152.231/open/api/operate/upload" urlrtsp = "http://172.19.152.231/open/api/operate/previewURLs" urlt = "http://172.19.152.231/open/api/operate/taskList" urla = "http://172.19.152.231/open/api/operate/algorithmList" urlele = "http://172.19.152.231/open/api/operate/fence" urltime = "http://172.19.152.231/open/api/operate/getTime" urlperson = "http://172.19.152.231/open/api/operate/getPersonLimitNum" #modellabeldir = {'0':'head','8':'person','10':'other','14':'smoke','16':'fire','21':'cross','25':'fall','29':'car','30':'liquid','31':'pressure','32':'sleep','33':'conveyor','34':'personcount','35':'gloves','36':'sit','37':'other','38':'person','98':'face','51':'person'} #algmodel = {'helmet': '0','danager': '8','uniform': '10','smoke': '14','fire': '16','cross': '21','fall': '25','occupancy': '29','liquid': '30','pressure': '31','sleep': '32','conveyor': '33','personcount': '34','gloves': '35','sit': '36','other': '37','duty': '38','face': '98','run': '51'} modelnamedir = {'0':'helmet','8':'danager','10':'uniform','14':'smoke','16':'fire','21':'cross','25':'fall','29':'occupancy','30':'liquid','31':'pressure','32':'sleep','34':'personcount','37':'other','38':'duty','98':'face','55':'oil','52':'jingdian','53':'rope','54':'personcar','39':'inspection','11':'reflective','12':'phone','66':'extinguisher','67':'tizi','68':'menjin','35':'arm','36':'persontre','33':'bag'} modellabeldir = {'0':'head,person','8':'person','10':'black_work_clothes,blue_work_clothes,person','14':'smoke','16':'fire','21':'cross','25':'fall','29':'car','30':'liquid','31':'pressure','32':'sleep','34':'personcount','37':'other','38':'person','98':'face','55':'oil','52':'person,hand,ball','53':'rope','54':'person','39':'person','11':'blue,greent,whitet,bluecoat,whitebarcoat,graycoat,baoan,chenyi,other','12':'phone','66':'extinguisher','67':'person,tizi','68':'person','35':'barearm,arm','36':'person,foot,cart,bag,box','33':'handbox,handbag'} modelalgdir = {} personcountdir = {} for key,value in modelnamedir.items(): modelalgdir[value] = key taskmap = {'helmet':newHelmet,'uniform':newUniform,'fall':Fall,'personcount':Personcount,'arm':Arm,'bag':Bag,'cross':Cross,'extinguisher':Extinguisher,'persontre':Persontre,'bag':Bag,'danager':Danager} mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225] test = transforms.Compose([transforms.Resize((224,224)), #transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=mean, std=std) ]) def clapre(modelcla,claimg,clapoint): imgten = torch.stack(claimg,dim=0) clapoint = torch.stack(clapoint,dim=0) imgten = imgten.to(0) result = modelcla(imgten) result = F.softmax(result) print(result) index = result.argmax(1) index = index.cpu().numpy() index = np.argwhere(index<5) index = index.reshape(-1) print(index) if len(index)>0: print(clapoint[index]) return clapoint[index] else: return None class YoloOpt: def __init__(self, weights=ROOT / 'yolov5s.pt',source=ROOT / 'data/images',data=ROOT / 'data/coco128.yaml', imgsz=(640,640), conf_thres=0.25, iou_thres=0.45, max_det=1000, device='', view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=True, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=ROOT / 'runs/detect', name='exp', exist_ok=False, line_thickness=1, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=10, classify=False, v8=False): self.weights = weights # 权重文件地址 self.source = source # 待识别的图像 self.data = data if imgsz is None: self.imgsz = (640, 640) self.imgsz = imgsz # 输入图片的大小，默认 (640,640) self.conf_thres = conf_thres # object置信度阈值 默认0.25 用在nms中 self.iou_thres = iou_thres # 做nms的iou阈值 默认0.45 用在nms中 self.device = device # 执行代码的设备，由于项目只能用 CPU，这里只封装了 CPU 的方法 self.view_img = view_img # 是否展示预测之后的图片或视频 默认False self.classes = classes # 只保留一部分的类别，默认是全部保留 self.agnostic_nms = agnostic_nms # 进行NMS去除不同类别之间的框, 默认False self.augment = augment # augmented inference TTA测试时增强/多尺度预测，可以提分 self.update = update # 如果为True,则对所有模型进行strip_optimizer操作,去除pt文件中的优化器等信息,默认为False self.exist_ok = exist_ok # 如果为True,则对所有模型进行strip_optimizer操作,去除pt文件中的优化器等信息,默认为False self.project = project # 保存测试日志的参数，本程序没有用到 self.name = name # 每次实验的名称，本程序也没有用到 self.max_det = max_det self.save_txt = save_txt self.save_conf= save_conf self.save_crop= save_crop self.nosave = nosave self.visualize = visualize self.line_thickness = line_thickness self.hide_labels = hide_labels self.hide_conf = hide_conf self.half = half self.dnn = dnn self.vid_stride = vid_stride self.classify = classify self.v8 = v8 class Detect: def __init__(self, weights = ROOT / 'yolov5s.pt' , imgsz=(640,640),source="changshusql1103.db",classes=None,device=None,classify=False,conf_thres=0.25,v8=False): print(f'detectweights = {weights}') if v8: from ultralytics.nn.autobackend import AutoBackend from ultralytics.utils.ops import non_max_suppression else: from utils.general import non_max_suppression self.opt = YoloOpt(weights=weights, imgsz=imgsz,source=source,classes=classes,device=device,classify=classify,conf_thres=conf_thres,v8=v8) self.source = str(self.opt.source) self.save_img = not self.opt.nosave and not source.endswith('.txt') # save inference images is_file = Path(self.source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) is_url = self.source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) self.webcam = self.source.isnumeric() or source.endswith('.db') or (is_url and not is_file) screenshot = self.source.lower().startswith('screen') if is_url and is_file: self.source = check_file(self.source) # download self.save_dir = increment_path(Path(self.opt.project) / self.opt.name, exist_ok=self.opt.exist_ok) # increment run #self.save_dir = self.save_dir / Path(self.opt.weights).stem #self.save_dir.mkdir(parents=True, exist_ok=True) (self.save_dir / 'labels' if self.opt.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True) # make dir print(f'device = {self.opt.device}') device = select_device(self.opt.device) if v8: self.model = AutoBackend(self.opt.weights, device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) if Path(weights).stem in ['arm', 'uniform']: if Path(weights).stem == 'arm': self.personmodel = AutoBackend('yolov8m.pt', device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) elif Path(weights).stem == 'uniform': self.personmodel = AutoBackend('yolo11m.pt', device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) else: self.model = DetectMultiBackend(self.opt.weights, device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) if Path(weights).stem in ['helmet','arm']: self.personmodel = DetectMultiBackend('personcount.pt', device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) self.stride, self.names, self.pt = self.model.stride, self.model.names, self.model.pt self.classify = classify if self.classify: #if Path(weights).stem =='uniform': # self.classifier_model = AutoBackend(f"{Path(weights).stem}cls.pt",device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) #else: if Path(weights).stem != "arm": classifier_model = torch.load(f"{Path(weights).stem}cls.pt") self.classifier_model = classifier_model.to(device) self.classifier_model.eval() else: self.classifier_model = AutoBackend(f"{Path(weights).stem}cls.pt",device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) self.imgsz = check_img_size(self.opt.imgsz, s=self.stride) self.model.warmup(imgsz=(1 , 3, *self.imgsz)) self.readpoint() print(self.imgsz) self.updatetime = time.time() self.updatemtime = time.time() self.filetime = os.path.getmtime(self.opt.weights) self.taskname = taskmap[Path(self.opt.weights).stem]() bs = 1 # batch_size if self.webcam: #self.view_img = check_imshow(warn=True) self.view_img = False # dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) # bs = len(dataset) elif screenshot: dataset = LoadScreenshots(self.source, img_size=self.imgsz, stride=self.stride, auto=self.pt) else: dataset = LoadImages(self.source, img_size=self.imgsz, stride=self.stride, auto=self.pt, vid_stride=self.opt.vid_stride) t1 = threading.Thread(target=self.load,daemon=True) t1.start() @smart_inference_mode() def infer(self,queue,runmodel): pretime = time.time() seen, windows, self.dt = 0, [], (Profile(), Profile(), Profile()) # # print ("数据库打开成功") while True: if time.localtime().tm_hour not in range(7,20): time.sleep(30) continue #print('aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa') if time.time()-pretime>300: ret = self.readpoint() pretime = time.time() if not ret: print(f'{Path(self.opt.weights).stem} {runmodel}') runmodel.pop(Path(self.opt.weights).stem) print(f'{Path(self.opt.weights).stem} {runmodel}') break print(f'queuelen = {len(queue)}') for que in queue: if que.qsize() == 0: print('queuezero') time.sleep(0.01) if que.qsize() > 0: #if time.time()-pretime>300: # ret = self.readpoint() # pretime = time.time() # if not ret: # print(f'{Path(self.opt.weights).stem} {runmodel}') # runmodel.pop(Path(self.opt.weights).stem) # print(f'{Path(self.opt.weights).stem} {runmodel}') # break setframe = que.get() # print('bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb') #if setframe is not None path, im, im0s, vid_cap, s, videotime ,channels = setframe algchannel = list(self.dirmodel.keys()) print(algchannel) print(path) algchannel = np.array(algchannel) channelsnp = np.array(channels) algindex = np.where(np.in1d(channelsnp, algchannel))[0] algindex = list(algindex) path = np.array(path) path = path[algindex] path = path.tolist() channels = np.array(channels) channels = channels[algindex] channels = channels.tolist() # print(algindex) if len(algindex)==0: continue #for ia in algindex: # print(type(im0s[ia])) # print(im0s[ia].shape) im = im[algindex] #for ia in algindex: # print(type(ia)) try: im0s = np.asarray(im0s) except Exception: im0s = np.asarray(im0s,dtype=object) print(im0s.shape) im0s = im0s[algindex] # im0s = im0s.tolist() print(f'algindex = {algindex}') print(f'im0s ={im0s[0].shape}') videotime = np.array(videotime) videotime = videotime[algindex] videotime = tuple(map(tuple, videotime)) # global tag # if self.contentid[0][3] == 1 : # dataset.close() # print('newstreaming=', self.contentid[0][3]) # conn = sqlite3.connect(self.source) # c = conn.cursor() # c.execute("UPDATE CHANGESTREAM set streamimg = 0 , addstream=0,delstream=0 where modelname= (?)",(Path(self.opt.weights).stem,)) # print(123) # conn.commit() # c.close() # conn.close() # print('opencv1') # cv2.destroyAllWindows() # print('opencv') # break # else: # print('nonewstreaming=', self.contentid[0][3]) with self.dt[0]: im = torch.from_numpy(im).to(self.model.device) im = im.half() if self.model.fp16 else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 if len(im.shape) == 3: im = im[None] # expand for batch dim # Inference with self.dt[1]: visualize = increment_path(self.save_dir / Path(path).stem, mkdir=True) if self.opt.visualize else False #print('error') # print(self.model) pred = self.model(im, augment=self.opt.augment, visualize=visualize) self.postprocess(pred, path, im0s, im, s, videotime,channels) # print(f'predshape= {') # NMS #processlist = [] #for i in range(3): # process = Process(target=self.postprocess,args=(pred[i::3],path[i::3],im0s[i::3],dataset,im[i::3],s)) # process = Process(target=self.preprocess) # process.start() # processlist.append(process) #for j in processlist: # j.join() #with ProcessPoolExecutor(3) as ppool: #for i in range(3): # print('hello') #ppool.submit(self.postprocess,pred[i::3],path[i::3],im0s[i::3],dataset,im[i::3],s) #ppool.submit(func1, '张三', i) #ppool.submit(self.preprocess) #self.postprocess(pred, path, im0s, dataset, im, s) #process = Process(target=self.postprocess, args=(pred, path, im0s, dataset, im, s)) #self.postprocess(pred, path, im0s, im, s,videotime) #process.start() #def preprocess(self): # print('preprocess-----------------------------------------------') def postprocess(self, pred, path, im0s, im, s,videotime,channels): if time.time()-self.updatemtime>300: if self.filetime !=os.path.getmtime(self.opt.weights): device = select_device(self.opt.device) print("load new load") self.model = DetectMultiBackend(self.opt.weights, device=device, dnn=self.opt.dnn, data=self.opt.data, fp16=self.opt.half) self.stride, self.names, self.pt = self.model.stride, self.model.names, self.model.pt self.filetime = os.path.getmtime(self.opt.weights) #try: #if modelalgdir[Path(self.opt.weights).stem]!='0': print(modelalgdir[Path(self.opt.weights).stem]) try: rea = requests.post(url=urla,data={'algorithmCode':modelalgdir[Path(self.opt.weights).stem]}).json()['data'] con = rea[0]['confidence'] self.opt.conf_thres = con except Exception: print('error') #else: # self.opt.conf_thres = 0.25 #except Exception: #print('posturlaerror') self.updatemtime = time.time() seen = 0 # dt = (Profile(), Profile(), Profile()) print(f'senn = {seen}') windows = [] if Path(self.opt.weights).stem: labelnamelist = [] with self.dt[2]: #print(f'cropshape={pred.shape}') if self.opt.v8: from ultralytics.utils.ops import non_max_suppression else: from utils.general import non_max_suppression pred = non_max_suppression(pred, self.opt.conf_thres, self.opt.iou_thres, self.opt.classes, self.opt.agnostic_nms, max_det=self.opt.max_det) # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) if self.classify and Path(self.opt.weights).stem!='persontre': if Path(self.opt.weights).stem == 'arm': pred = apply_classifierarm(pred,self.classifier_model,im,im0s,Path(self.opt.weights).stem) else: pred = apply_classifier1(pred,self.classifier_model,im,im0s,Path(self.opt.weights).stem) # Process predictions #print(f'predshape={pred.shape}') for i, det in enumerate(pred): # per image if time.time()-self.updatetime>300: dataele = { "algorithmCode": self.dirmodel[channels[i]]['classindex'], "algorithmIp":self.dirmodel[channels[i]]['algip'], "channel":self.dirmodel[channels[i]]['channel'] } try: resultele = requests.post(url=urlele,data=dataele).json()['data']['pointCollections'] resultele = resultele.split(',||') resultele = tuple(resultele) point = '%s:'*len(resultele) %resultele if len(point[:-2])>1: self.dirmodel[channels[i]]['point'] = point[:-2] except Exception: print('post error') if Path(self.opt.weights).stem == 'personcount': try: resultper = requests.post(url=urlperson,data=dataele).json()['data'] personcountdir[channels[i]] = int(resultper) except Exception: print('urlpersonerror') if Path(self.opt.weights).stem == 'sleep' or Path(self.opt.weights).stem == 'duty' : datatime= { "algorithmCode": self.dirmodel[channels[i]]['classindex'], "algorithmIp":self.dirmodel[channels[i]]['algip'], "channel":self.dirmodel[channels[i]]['channel'] } try: resulttime = requests.post(url=urltime,data=dataele).json()['data'] self.dirmodel[channel]['durtime'] = int(resulttime) except Exception: print('posttime error') self.updatetime = time.time() seen += 1 if self.webcam: # batch_size >= 1 p, im0 = path[i], im0s[i].copy() s += f'{i}: ' else: p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) p = Path(p) # to Path save_path = str(self.save_dir / p.name) # im.jpg #txt_path = str(self.save_dir / 'labels' / p.stem) + ( # '' #if dataset.mode == 'image' else f'_{frame}') # im.txt s += '%gx%g ' % im.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh imc = im0.copy() # for save_crop annotator = Annotator(im0, line_width=self.opt.line_thickness, example=str(self.names)) flag = False if len(det) and Path(self.opt.weights).stem != 'duty': #flag = True # Rescale boxes from img_size to im0 size det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # Print results for c in det[:, 5].unique(): n = (det[:, 5] == c).sum() # detections per class s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string # Write results if Path(self.opt.weights).stem in ['arm', 'uniform']: personpred = self.personmodel(im[i][None], None, None) personpred = non_max_suppression(personpred, 0.7, self.opt.iou_thres, 0, self.opt.agnostic_nms, max_det=self.opt.max_det) if len(personpred[0])==0: flag = False elif Path(self.opt.weights).stem == 'other': persondet = [] personpred = personpred[0] personpred[:, :4] = scale_boxes(im.shape[2:], personpred[:, :4], im0.shape).round() for *perxyxy,conf,cls in reversed(personpred): print(perxyxy) x1,y1,x3,y3 = perxyxy x1,y1,x3,y3 = int(x1),int(y1),int(x3),int(y3) x2,y2 = x3,y1 x4,y4 = x1,y3 flag = self.taskname.getflag(det, persondet,annotator, self.dirmodel[channels[i]]['fence'], self.dirmodel[channels[i]]['point'], self.names, self.dirmodel[channels[i]]['label']) else: persondet = [] personpred = personpred[0] personpred[:, :4] = scale_boxes(im.shape[2:], personpred[:, :4], im0.shape).round() for *perxyxy,conf,cls in reversed(personpred): print(perxyxy) if conf<0.8: continue x1,y1,x3,y3 = perxyxy x1,y1,x3,y3 = int(x1),int(y1),int(x3),int(y3) x2,y2 = x3,y1 x4,y4 = x1,y3 persondet.append([x1,y1,x2,y2,x3,y3,x4,y4]) flag = self.taskname.getflag(det,persondet,annotator,self.dirmodel[channels[i]]['fence'],self.dirmodel[channels[i]]['point'],self.names,self.dirmodel[channels[i]]['label']) else: if Path(self.opt.weights).stem in ['personcount']: flag = self.taskname.getflag(det, None,annotator, self.dirmodel[channels[i]]['fence'], self.dirmodel[channels[i]]['point'], self.names, self.dirmodel[channels[i]]['label'],personcountdir[channels[i]]) elif Path(self.opt.weights).stem in ['persontre']: flag = self.taskname.getflag(det, None,annotator, self.dirmodel[channels[i]]['fence'], self.dirmodel[channels[i]]['point'], self.names, self.dirmodel[channels[i]]['label'],1,imc) else: flag = self.taskname.getflag(det, None,annotator, self.dirmodel[channels[i]]['fence'], self.dirmodel[channels[i]]['point'], self.names, self.dirmodel[channels[i]]['label']) if flag: #if self.dirmodel[channels[i]]['imgtime'] != videotime[i]: self.dirmodel[channels[i]]['detframe'].pop(0) self.dirmodel[channels[i]]['detframe'].append(1) self.dirmodel[channels[i]]['preim'] = annotator.result() self.dirmodel[channels[i]]['oripreim'] = imc self.dirmodel[channels[i]]['posttime'] = videotime[i] print(self.dirmodel[channels[i]]['detframe']) #self.dirmodel[channels[i]]['imgtime'] = videotime[i] else: #print(f'deti= {i}') #print(detframe[i]) #if self.dirmodel[channels[i]]['imgtime'] != videotime[i]: self.dirmodel[channels[i]]['detframe'].pop(0) self.dirmodel[channels[i]]['detframe'].append(0) print(self.dirmodel[channels[i]]['detframe']) #self.dirmodel[channels[i]]['imgtime'] = videotime[i] #print(detframe[i]) # Stream results #im0 = annotator.result() #print(f'i = {i}') #print(channels[i]) #print(postpretime[i]) #print(detframe[i]) if not self.dirmodel[channels[i]]['detflag'] and self.dirmodel[channels[i]]['detframe'].count(1)>=1: self.dirmodel[channels[i]]['detflag'] = True self.dirmodel[channels[i]]['detpretime'] = time.time() elif self.dirmodel[channels[i]]['detframe'].count(1)==0 : self.dirmodel[channels[i]]['detflag'] = False self.dirmodel[channels[i]]['detpretime'] = float('inf') # Stream results #im0 = annotator.result() if time.time() - self.dirmodel[channels[i]]['postpretime'] >30 and time.time() - self.dirmodel[channels[i]]['detpretime'] > self.dirmodel[channels[i]]['durtime'] and self.dirmodel[channels[i]]['detflag']: #print() #if time.time() - self.dirmodel[channels[i]]['postpretime'] >30 and self.dirmodel[channels[i]]['detflag']: #print(time.time() - self.dirmodel[channels[i]]['detpretime']) #print(self.dirmodel[channels[i]]['detflag']) print('post-------------------------------------------------------------------------') #time.sleep(30) #print(time.time() - postpretime[i]) #print('111111111111111111111111111111111111111111111111') #print(dirmodel[channels[i]]['preim'].shape) success, encoded_image = cv2.imencode('.jpg', self.dirmodel[channels[i]]['preim']) content = encoded_image.tobytes() successori, encoded_imageori = cv2.imencode('.jpg', self.dirmodel[channels[i]]['oripreim']) contentori = encoded_imageori.tobytes() filename = f'{p.stem}_{int(time.time())}.jpg' filenameori = f'ori{p.stem}_{int(time.time())}.jpg' print(f'str(p) {p.name}') print(channels[i]) payload = {'channel': self.dirmodel[channels[i]]['channel'], 'classIndex': self.dirmodel[channels[i]]['classindex'], 'ip': self.dirmodel[channels[i]]['algip'], 'videoTime': time.strftime('%Y-%m-%d %H:%M:%S', self.dirmodel[channels[i]]['posttime']), 'videoUrl': channels[i]} files = [ ('file', (filename, content, 'image/jpeg')), ('oldFile', (filenameori, contentori, 'image/jpeg')), ] try: result = requests.post(url, data=payload, files=files) print(result) except Exception: print('posterror') #time.sleep(3000) self.dirmodel[channels[i]]['postpretime'] = time.time() self.dirmodel[channels[i]]['detflag'] = False timesave = time.strftime('%Y-%m-%d-%H:%M:%S', self.dirmodel[channels[i]]['posttime']) year = time.strftime('%Y',time.localtime(time.time())) month = time.strftime('%m',time.localtime(time.time())) day = time.strftime('%d',time.localtime(time.time())) savefold = f'/mnt/project/images/{Path(self.opt.weights).stem}/{year}/{month}/{day}' savefold = Path(savefold) savefold.mkdir(parents=True,exist_ok=True) detsavefold = f'/mnt/project/detimages/{Path(self.opt.weights).stem}/{year}/{month}/{day}' detsavefold = Path(detsavefold) detsavefold.mkdir(parents=True,exist_ok=True) cv2.imwrite(f'{savefold}/{timesave}.jpg',self.dirmodel[channels[i]]['oripreim']) cv2.imwrite(f'{detsavefold}/{timesave}det.jpg',self.dirmodel[channels[i]]['preim']) #if self.dirmodel[channels[i]]['detframe'].count(1)==0: # self.dirmodel[channels[i]]['detflag'] = False #time.sleep(1) self.view_img = False if self.view_img: if platform.system() == 'Linux' and p not in windows: windows.append(p) cv2.namedWindow(f'{str(p)}-{Path(self.opt.weights).stem}', cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(f'{str(p)}-{Path(self.opt.weights).stem}', im0.shape[1], im0.shape[0]) im1 = cv2.resize(im0, (1280, 720)) cv2.imshow(f'{str(p)}-{Path(self.opt.weights).stem}', im1) cv2.waitKey(1) # 1 millisecond # Save results (image with detections) # Print time (inference-only) print(f'channels[i]={channels[i]}') LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{self.dt[1].dt * 1E3:.1f}ms {str(p)}-{Path(self.opt.weights).stem}") def load(self): conn = sqlite3.connect(self.source) c = conn.cursor() while True: # # print ("数据库打开成功") cursor = c.execute( "SELECT modelname, addstream,delstream,streaming from CHANGESTREAM WHERE modelname= (?)",(Path(self.opt.weights).stem,)) # content = cursor.fetchall() # if content[0][1] ==1 or content[0][2] ==1: # c.execute("UPDATE CHANGESTREAM set streamimg = 1 where modelname='yolov5s'") # print("updata changestream") # conn.commit() # cursor = c.execute( # "SELECT modelname, addstream,delstream,streamimg from CHANGESTREAM WHERE modelname='yolov5s'") self.contentid = cursor.fetchall() #global tag #tag = Value('i', self.contentid[0][3]) #print(tag.value==1) print(f'loadcontent={self.contentid[0][3]}') time.sleep(3) c.close() conn.close() def readpoint(self): data = { "algorithmCode": modelalgdir[Path(self.opt.weights).stem], "deviceIp":None, 'fwqCode':None } self.dirmodel = {} result = requests.post(url=urlt,data=data).json()['data'] channell=[] for info in result: #content = cursor.fetchall() #self.dirmodel = {} #for address,fence,point,channel,classindex,ip ,algip,label,durtime in content: #address = f'{address[:-1]}0' channel = info["deviceChannel"] if Path(self.opt.weights).stem == "danager" and channel =='45': continue channell.append(channel) self.dirmodel[channel] = {} self.dirmodel[channel]['fence'] = 1 if len(info["electricFence"])>0 else 0 if Path(self.opt.weights).stem == "uniform": self.dirmodel[channel]['fence'] = 1 #self.dirmodel[channel]['point'] = point self.dirmodel[channel]['channel'] = info['deviceChannel'] self.dirmodel[channel]['classindex'] = info['algorithmCode'] self.dirmodel[channel]['ip'] = info['deviceIp'] self.dirmodel[channel]['algip'] = info['deviceAlgorithmIp'] dataele = { "algorithmCode": self.dirmodel[channel]['classindex'], "algorithmIp":self.dirmodel[channel]['algip'], "channel":self.dirmodel[channel]['channel'] } resultele = requests.post(url=urlele,data=dataele).json()['data']['pointCollections'] resultele = resultele.split(',||') resultele = tuple(resultele) point = '%s:'*len(resultele) %resultele if Path(self.opt.weights).stem == 'personcount': resultper = requests.post(url=urlperson,data=dataele).json()['data'] personcountdir[channel] = int(resultper) if (Path(self.opt.weights).stem == "uniform" or Path(self.opt.weights).stem == "fall") and len(point[:-2])<=1: self.dirmodel[channel]['point'] = "150#144,1100#144,1100#550,150#550" else: self.dirmodel[channel]['point'] = point[:-2] self.dirmodel[channel]['preim'] = None self.dirmodel[channel]['oripreim'] = None self.dirmodel[channel]['detframe'] = [0 for _ in range(2)] self.dirmodel[channel]['postpretime'] = 0 self.dirmodel[channel]['detflag'] = False self.dirmodel[channel]['detpretime'] = float('inf') self.dirmodel[channel]['label'] = modellabeldir[data['algorithmCode']] if Path(self.opt.weights).stem == 'sleep' or Path(self.opt.weights).stem == 'duty' : datatime= { "algorithmCode": self.dirmodel[channel]['classindex'], "algorithmIp":self.dirmodel[channel]['algip'], "channel":self.dirmodel[channel]['channel'] } resulttime = requests.post(url=urltime,data=dataele).json()['data'] self.dirmodel[channel]['durtime'] = int(resulttime) else: self.dirmodel[channel]['durtime'] = 0 self.dirmodel[channel]['posttime'] = 0 print(self.dirmodel) return sorted(channell) # str = str.split(":") # lista = [] # for liststr in str: # if len(liststr) > 0: # li = liststr.split(',') # listpoint = [] # for i, j in zip(li[::2], li[1::2]): # listpoint.append((i, j)) # lista.append(listpoint) # return listpoint #def preprocess(): # print('preprocess-----------------------------------------------') def getframe(queuelist,channelsl,source,tt,numworks,lock,numworkv): while True: print("dataloader") imgsz = [768, 768] print(f'source = {source}') dataset = LoadStreamsSQLTN(channelsl,source, img_size=832, auto=True, vid_stride=20, tt=tt,numworks = numworks) bs = len(dataset) vid_path, vid_writer = [None] * bs, [None] * bs # self.detframe = [[0 for _ in range(8)] for i in range(bs)] # self.postpretime = [0]*bs # Run inference #imgsz = (1 , 3, *self.imgsz) print(imgsz) #self.model.warmup(imgsz=(1 , 3, *imgsz)) # warmup seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) # # print ("数据库打开成功") pretime = time.time() tag = 0 sourcebase = 'project0117.db' for path, im, im0s, vid_cap, s, videotime,channels in dataset: # print('*'*21) # global tag # print('datasetvideo') # if time.time()-pretime > 300: # pretime = time.time() # conn = sqlite3.connect(sourcebase) # c = conn.cursor() # cursor = c.execute("SELECT modelname, addstream,delstream,streaming from CHANGESTREAM WHERE modelname= 'helmet'") # contentid = cursor.fetchall() # tag = contentid[0][3] # if tag == 1: # lock.acquire() # numworkv.value += 1 # dataset.close() # if numworkv.value==3: # print('newstreaming=', tag) # conn = sqlite3.connect(source) # c = conn.cursor() # c.execute("UPDATE CHANGESTREAM set streaming = 0 , addstream=0,delstream=0 where modelname='helmet'") # print(123) # conn.commit() # c.close() # conn.close() # lock.release() # print('opencv1') # # cv2.destroyAllWindows() # print('opencv') # break # else: # print('nonewstreaming=', tag) if time.time()-pretime > 300: channellist = [] pretime = time.time() data = { "algorithmCode": None, "deviceIp":None, "fwqCode":None } try: result = requests.post(url=urlt,data=data).json()['data'] except Exception: result = [] for info in result: data = { "channel": info["deviceChannel"], "ip": info["deviceAlgorithmIp"] } chaflag = any(info["deviceChannel"] in t for t in channellist) #personcountdir[channel] = num if not chaflag: address = requests.post(url=urlrtsp,data=data).json()['msg'] channellist.append((info['deviceChannel'],address)) channelsa = [] sourcea = [] channellist = set(channellist) channellist = sorted(channellist,key=lambda x:x[0]) #channellist = set(channellist) for cha,add in channellist: channelsa.append(cha) sourcea.append(add) channelsl = sorted(channelsl) #channelsa = sorted(channelsa) if channelsa!=channelsl and len(channelsa)>0: print(f'channelsa = {channelsa}') print(f'channelsl = {channelsl}') dataset.close() channelsl = channelsa source = sourcea break; for key,value in queuelist.items(): hour = time.localtime(time.time()).tm_hour if hour in range(7,18): value[-1].put((path, im, im0s, vid_cap, s, videotime,channels)) value[-1].get() if value[-1].qsize() == 10 else time.sleep(0.001) def getmutpro(channels,source,streamlist,numworkv,lock,numworks=1,modellen=None): processlist = [] queuelist = {} for i in range(numworks): for model in modellen: queue = Queue(maxsize=10) queuelist.setdefault(model,[]) queuelist[model].append(queue) process = Process(target=getframe, args=(queuelist, channels,source, i,numworks,lock,numworkv)) processlist.append(process) process.start() #queuelist.append(queue) return queuelist # path = [] # im0s = [] # vid_cap = None # s = '' # videotime = [] # while True: # imlist = [] # pathlist = [] # im0slist = [] # channelslist = [] # vid_cap = None # s = '' # videotimelist = [] # for q in queuelist: # if q.qsize()>0: # setframe = q.get() # path, im, im0s, vid_cap, s, videotime ,channels = setframe # pathlist += path # channelslist +=channels # im0slist += im0s # videotimelist += videotime # imlist.append(im) # if len(imlist)>0: # im = np.concatenate(imlist) # if len(pathlist)>0: # print(len(path),im.shape,len(im0s)) # streamlist.append((pathlist, im, im0slist, vid_cap, s, videotimelist,channelslist)) #print(f'streamlist = {len(streamlist)}') # streamlist.pop(0) if len(streamlist) > 3 else time.sleep(0.001) def modelfun(queue,weights,sourcedb,classes,device,classify,conf_thres,runmodel,v8=False): print(weights) detectdemo=Detect(weights=weights,source=sourcedb,classes=classes,device=device,classify=classify,conf_thres=conf_thres,v8=v8) detectdemo.infer(queue,runmodel) def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL') opt = parser.parse_args() return opt def main(opt): check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) run(**vars(opt)) if __name__ == '__main__': #torch.multiprocessing.set_start_method('spawn') #set_start_method('spawn') opt = parse_opt() DEVICE = "cuda" if torch.cuda.is_available() else "cpu" processor = AutoProcessor.from_pretrained(r"/mnt/liq_weight/smolVLM") model = AutoModelForVision2Seq.from_pretrained( r"/mnt/liq_weight/smolVLM", torch_dtype=torch.bfloat16, # _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager", ).to(DEVICE) dbpath = 'projectnew.db' conn = sqlite3.connect(dbpath) # # print ("数据库打开成功") c = conn.cursor() task(c,conn,urlt,urla) cursor = c.execute('select channel,algip from stream ') result = cursor.fetchall() for channel ,algip in result: data = { "channel": channel, "ip":algip } #personcountdir[channel] = num address = requests.post(url=urlrtsp,data=data).json()['msg'] c.execute('UPDATE STREAM set address= (?) where channel =(?)',(address,channel)) conn.commit() cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet' or modelname = 'smoke' or modelname = 'uniform' or modelname = 'fire' or modelname ='duty' or modelname = 'sleep' or modelname='occupancy' or modelname = 'personcar' or modelname = 'phone' or modelname = 'reflective' or modelname = 'extinguisher' or modelname = 'danager' or modelname = 'inspection' or modelname = 'cross' or modelname = 'personcount' or modelname= 'arm' or modelname = 'persontre' or modelname = 'bag'") #cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet'") content = cursor.fetchall() cursor = c.execute("SELECT address,channel from STREAM ") #cursor = c.execute("SELECT address from STREAM where modelname = 'helmet'") contenta = cursor.fetchall() source = [] modellist = [] addcha = [] channellist = [] for i in contenta: addcha.append((i[0],i[1])) #modellist.append(i[1]) addcha = set(addcha) addcha = sorted(addcha,key=lambda x:x[1]) for add,cha in addcha: source.append(add) channellist.append(cha) #source = set(source) print(addcha) source = list(source) cursor = c.execute("SELECT modelname from STREAM where (modelname ='helmet' or modelname = 'smoke' or modelname = 'uniform' or modelname = 'fire' or modelname = 'duty' or modelname = 'sleep' or modelname='occupancy' or modelname = 'personcar' or modelname = 'phone' or modelname = 'reflective' or modelname = 'extinguisher' or modelname = 'danager' or modelname = 'inspection' or modelname = 'cross' or modelname = 'personcount' or modelname = 'arm' or modelname = 'persontre' or modelname = 'bag')") contentm = cursor.fetchall() for m in contentm: modellist.append(m[0]) modellist = set(modellist) modellist = list(modellist) contentlist = [] for i in content: contentlist.append(i[0]) #source.sort() n = len(content) print(f'modelname={n}') print(content) #content.reverse() print(content) print(source) # main(opt) #processes = [] streamqueue = Queue(maxsize=4) numworkv = Value('i', 0) manager = Manager() lock = multiprocessing.Lock() streamlist = manager.list() numworks = 7 modellen = [] for i in modellist: if i in contentlist: modellen.append(i) queuelist = getmutpro(channellist,source, streamlist, numworkv, lock, numworks,modellen) deid = 0 #pool = ThreadPoolExecutor(max_workers=n) runmodel = manager.dict() while True: for i in modellist: if i in contentlist: if i not in runmodel: #print(i) #detectdemo=Detect(weights=f'/mnt/project/yolodemo/yolov5-master/{i[0]}.pt') c.execute('select conf,cla from changestream where modelname = (?)',(i,)) rea = c.fetchall() print(f'weights ={i[0]}.pt') if i in ['duty','danager','inspection','cross','personcount']: process = Process(target=modelfun,args=(queuelist[i],f'{i}.pt',dbpath,[0],0,rea[0][1],rea[0][0],runmodel,True)) else: if i in ['fall','extinguisher']: process = Process(target=modelfun,args=(queuelist[i],f'{i}.pt',dbpath,None,0,rea[0][1],rea[0][0],runmodel)) else: process = Process(target=modelfun,args=(queuelist[i],f'{i}.pt',dbpath,None,0,rea[0][1],rea[0][0],runmodel,True)) #elif i in ['helmet','fire','smoke','fall']: #process = Process(target=modelfun,args=(queuelist,f'{i}.pt',dbpath,None,deid%2,True)) #else: #process = Process(target=modelfun,args=(queuelist,f'{i}.pt',dbpath,None,deid%2,False)) #processes.append(process) #process.start() #detectobj = Process(target=detectdemo.infer,args=(queue,)) # Detect(weights=f'{i[0]}.pt') time.sleep(3) process.start() deid = deid+1 runmodel[i] = 1 time.sleep(600) task(c,conn,urlt,urla) #cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet' or modelname = 'fall' or modelname = 'uniform' or modelname = 'personcount' or modelname = 'arm' or modelname = 'bag'") #cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet'") cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'helmet' or modelname = 'smoke' or modelname = 'uniform' or modelname = 'fire' or modelname ='duty' or modelname = 'sleep' or modelname='occupancy' or modelname = 'personcar' or modelname = 'phone' or modelname = 'reflective' or modelname = 'extinguisher' or modelname = 'danager' or modelname = 'inspection' or modelname = 'cross' or modelname = 'personcount' or modelname = 'arm' or modelname = 'persontre' or modelname = 'bag'") content = cursor.fetchall() contentlist = [] for con in content: contentlist.append(con[0]) #cursor = c.execute("SELECT address,modelname,channel from STREAM where modelname='helmet' or modelname = 'sleep' or modelname = 'smoke' or modelname = 'danager'or modelname = 'gloves' or modelname = 'other'") cursor = c.execute("SELECT address,channel from STREAM ") contenta = cursor.fetchall() source = [] modellist = [] addcha = [] channellist = [] for i in contenta: addcha.append((i[0],i[1])) #modellist.append(i[1]) addcha = set(addcha) addcha = sorted(addcha) for a,cha in addcha: source.append(a) channellist.append(cha) print(addcha) #source = set(source) source = list(source) #source.sort() cursor = c.execute("SELECT modelname from STREAM where (modelname = 'helmet' or modelname = 'smoke' or modelname = 'uniform' or modelname = 'fire' or modelname = 'duty' or modelname = 'sleep' or modelname='occupancy' or modelname = 'personcar' or modelname = 'phone' or modelname = 'reflective' or modelname = 'extinguisher' or modelname = 'danager' or modelname = 'inspection' or modelname = 'cross' or modelname = 'personcount' or modelname = 'arm' or modelname = 'persontre' or modelname = 'bag')") contentm = cursor.fetchall() for m in contentm: modellist.append(m[0]) modellist = set(modellist) n = len(content) print(f'modelname={n}') print(content) #content.reverse() print(content) #pool.submit(detectobj.infer) #cursor = c.execute("SELECT modelname from CHANGESTREAM where modelname = 'fall'") #content = cursor.fetchall() #n = len(content) #print(f'modelname={n}') #print(content) #content.reverse() #print(content) # main(opt) #processes = [] #pool = ProcessPoolExecutor(max_workers=n) #for i in content: #print(i) #detectdemo=Detect(weights=f'{i[0]}.pt') #process = Process(target=detectdemo.infer) #processes.append(process) #process.start() #detectobj = Detect(weights=f'{i[0]}.pt') # time.sleep(3) #pool.submit(detectobj.infer) # print('111111111111111111111111111111111111111111111111111111111') #pool.submit(TestA().func1, '张三', i) #print('----------------------------------------------------------------') #time.sleep(3000) # 等待所有进程执行完毕 #for process in processes: # process.join() #pool.submit(Detect(weights=f'{i[0]}.pt').infer) # if isinstance(opt.weights,list): # opt.weights = opt.weights[0] #signal.signal(signal.SIGINT, my_handler) #detectdemo1 = Detect(weights=f'{content[0][0]}.pt') #detectdemo1.infer() #a = Test #with ProcessPoolExecutor(3) as ppool: #for i in range(3): # print('hello') #ppool.submit(self.postprocess,pred[i::3],path[i::3],im0s[i::3],dataset,im[i::3],s) #ppool.submit(TestA().func1, '张三', i) #ta = TestA() #with ProcessPoolExecutor(5) as ppool: # 创建一个5个进程的进程池 # for i in range(1, 4): # ppool.submit(func1, '张三', i) #f1= pool.submit(detectdemo1.infer) # print("线程1-----------------------------------------------------------------------------------") #detectdemo2 = Detect(weights=r"helmet.pt") #f2=pool.submit(detectdemo2.infer) # print("线程2-------------------------------------------------------------------------------------") #detectdemo3 = threading.Thread(target=detectdemo3.infer) #detectdemo3 = Detect(weights=r"fall.pt") #f3=pool.submit(detectdemo3.infer)