#1 makeTxt.py（將訓(xùn)練數(shù)據(jù)自動劃分為訓(xùn)練集、驗證集和測試集）... 2

#2 voc_label.py（將VOC格式數(shù)據(jù)集轉(zhuǎn)換成yolo數(shù)據(jù)集）... 3

#3 tube.yaml 6

#4 yolov5s.yaml 7

#5 train.py. 9

#6 detect.py. 28

#7 Video.py(每間隔3秒對應(yīng)的幀數(shù)采集照片并yolov5檢測最后保存) 36

#1 makeTxt.py（將訓(xùn)練數(shù)據(jù)自動劃分為訓(xùn)練集、驗證集和測試集）

import os
import random


trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = 'data/Annotations'
txtsavepath = 'data/ImageSet'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('data/ImageSet/trainval.txt', 'w')
ftest = open('data/ImageSet/test.txt', 'w')
ftrain = open('data/ImageSet/train.txt', 'w')
fval = open('data/ImageSet/val.txt', 'w')

for i in list:
??? name = total_xml[i][:-4] + '\n'
??? if i in trainval:
??????? ftrainval.write(name)
??????? if i in train:
??????????? ftrain.write(name)
??????? else:
??????????? fval.write(name)
??? else:
??????? ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

#2 voc_label.py（將VOC格式數(shù)據(jù)集轉(zhuǎn)換成yolo數(shù)據(jù)集）

#xml解析包import xml.etree.ElementTree as ETimport pickleimport os# os.listdir() 方法用于返回指定的文件夾包含的文件或文件夾的名字的列表from os import listdir, getcwdfrom os.path import joinsets = ['train', 'test', 'val']classes = ['01', '02', '03', '04', '05', '06', '07', '08', '09']# 進(jìn)行歸一化操作def convert(size, box): # size:(原圖w,原圖h) , box:(xmin,xmax,ymin,ymax)dw = 1./size[0]???? # 1/wdh = 1./size[1]???? # 1/hx = (box[0] + box[1])/2.0?? # 物體在圖中的中心點x坐標(biāo)y = (box[2] + box[3])/2.0?? # 物體在圖中的中心點y坐標(biāo)w = box[1] - box[0]???????? # 物體實際像素寬度h = box[3] - box[2]???????? # 物體實際像素高度x = x*dw??? # 物體中心點x的坐標(biāo)比(相當(dāng)于 x/原圖w)w = w*dw??? # 物體寬度的寬度比(相當(dāng)于 w/原圖w)y = y*dh??? # 物體中心點y的坐標(biāo)比(相當(dāng)于 y/原圖h)h = h*dh??? # 物體寬度的寬度比(相當(dāng)于 h/原圖h)return (x, y, w, h)??? # 返回 相對于原圖的物體中心點的x坐標(biāo)比,y坐標(biāo)比,寬度比,高度比,取值范圍[0-1]# year ='2012', 對應(yīng)圖片的id（文件名）def convert_annotation(image_id):'''將對應(yīng)文件名的xml文件轉(zhuǎn)化為label文件，xml文件包含了對應(yīng)的bunding框以及圖片長款大小等信息，通過對其解析，然后進(jìn)行歸一化最終讀到label文件中去，也就是說一張圖片文件對應(yīng)一個xml文件，然后通過解析和歸一化，能夠?qū)?yīng)的信息保存到唯一一個label文件中去labal文件中的格式：calss x y w h　　同時，一張圖片對應(yīng)的類別有多個，所以對應(yīng)的ｂｕｎｄｉｎｇ的信息也有多個'''# 對應(yīng)的通過year 找到相應(yīng)的文件夾，并且打開相應(yīng)image_id的xml文件，其對應(yīng)bund文件in_file = open('data/Annotations/%s.xml' % (image_id), encoding='utf-8')# 準(zhǔn)備在對應(yīng)的image_id 中寫入對應(yīng)的label，分別為# <object-class> <x> <y> <width> <height>out_file = open('data/labels/%s.txt' % (image_id), 'w', encoding='utf-8')# 解析xml文件tree = ET.parse(in_file)# 獲得對應(yīng)的鍵值對root = tree.getroot()# 獲得圖片的尺寸大小size = root.find('size')# 如果xml內(nèi)的標(biāo)記為空，增加判斷條件if size != None:# 獲得寬w = int(size.find('width').text)# 獲得高h = int(size.find('height').text)# 遍歷目標(biāo)objfor obj in root.iter('object'):# 獲得difficult ？？difficult = obj.find('difficult').text# 獲得類別 =string 類型cls = obj.find('name').text# 如果類別不是對應(yīng)在我們預(yù)定好的class文件中，或difficult==1則跳過if cls not in classes or int(difficult) == 1:continue# 通過類別名稱找到idcls_id = classes.index(cls)# 找到bndbox 對象xmlbox = obj.find('bndbox')# 獲取對應(yīng)的bndbox的數(shù)組 = ['xmin','xmax','ymin','ymax']b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),float(xmlbox.find('ymax').text))print(image_id, cls, b)# 帶入進(jìn)行歸一化操作# w = 寬, h = 高， b= bndbox的數(shù)組 = ['xmin','xmax','ymin','ymax']bb = convert((w, h), b)# bb 對應(yīng)的是歸一化后的(x,y,w,h)# 生成 calss x y w h 在label文件中out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')# 返回當(dāng)前工作目錄wd = getcwd()print(wd)for image_set in sets:'''對所有的文件數(shù)據(jù)集進(jìn)行遍歷做了兩個工作：１．將所有圖片文件都遍歷一遍，并且將其所有的全路徑都寫在對應(yīng)的txt文件中去，方便定位２．同時對所有的圖片文件進(jìn)行解析和轉(zhuǎn)化，將其對應(yīng)的bundingbox 以及類別的信息全部解析寫到label 文件中去最后再通過直接讀取文件，就能找到對應(yīng)的label 信息'''# 先找labels文件夾如果不存在則創(chuàng)建if not os.path.exists('data/labels/'):os.makedirs('data/labels/')# 讀取在ImageSets/Main 中的train、test..等文件的內(nèi)容# 包含對應(yīng)的文件名稱image_ids = open('data/ImageSet/%s.txt' % (image_set)).read().strip().split()# 打開對應(yīng)的2012_train.txt 文件對其進(jìn)行寫入準(zhǔn)備list_file = open('data/%s.txt' % (image_set), 'w')# 將對應(yīng)的文件_id以及全路徑寫進(jìn)去并換行for image_id in image_ids:list_file.write('data/images/%s.jpg\n' % (image_id))# 調(diào)用? year = 年份? image_id = 對應(yīng)的文件名_idconvert_annotation(image_id)# 關(guān)閉文件list_file.close()# os.system(‘comand’) 會執(zhí)行括號中的命令，如果命令成功執(zhí)行，這條語句返回0，否則返回1# os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt")# os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")

#3 tube.yaml

train: ../mydata3/train/images # train images (relative to 'path') 118287 imagesval: ../mydata3/val/images # train images (relative to 'path') 5000 imagesnc: 19? # number of classesnames: ['module1', '0001', '0010', '0011', '0100', '0101', '0110', '0111', '1000', '1001', 'Open', 'Tube body', 'module2', 'Bar 1', 'Bar 2', 'Bar 3', 'module3', '1010', '1011']? # class names

#4 yolov5s.yaml

# parametersnc: 19? # number of classesdepth_multiple: 0.33? # model depth multiplewidth_multiple: 0.50? # layer channel multiple# anchorsanchors:- [10,13, 16,30, 33,23]? # P3/8- [30,61, 62,45, 59,119]? # P4/16- [116,90, 156,198, 373,326]? # P5/32# YOLOv5 backbonebackbone:# [from, number, module, args][[-1, 1, Focus, [64, 3]],? # 0-P1/2[-1, 1, Conv, [128, 3, 2]],? # 1-P2/4[-1, 3, C3, [128]],[-1, 1, Conv, [256, 3, 2]],? # 3-P3/8[-1, 9, C3, [256]],[-1, 1, Conv, [512, 3, 2]],? # 5-P4/16[-1, 9, C3, [512]],[-1, 1, Conv, [1024, 3, 2]],? # 7-P5/32[-1, 1, SPP, [1024, [5, 9, 13]]],[-1, 3, C3, [1024, False]],? # 9]# YOLOv5 headhead:[[-1, 1, Conv, [512, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest']],[[-1, 6], 1, Concat, [1]],? # cat backbone P4[-1, 3, C3, [512, False]],? # 13[-1, 1, Conv, [256, 1, 1]],[-1, 1, nn.Upsample, [None, 2, 'nearest']],[[-1, 4], 1, Concat, [1]],? # cat backbone P3[-1, 3, C3, [256, False]],? # 17 (P3/8-small)[-1, 1, Conv, [256, 3, 2]],[[-1, 14], 1, Concat, [1]],? # cat head P4[-1, 3, C3, [512, False]],? # 20 (P4/16-medium)[-1, 1, Conv, [512, 3, 2]],[[-1, 10], 1, Concat, [1]],? # cat head P5[-1, 3, C3, [1024, False]],? # 23 (P5/32-large)[[17, 20, 23], 1, Detect, [nc, anchors]],? # Detect(P3, P4, P5)]

#5 train.py

import argparse
import logging
import math
import os

os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
import random
import time
from pathlib import Path
from threading import Thread

import numpy as np
import torch.distributed as dist
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.optim.lr_scheduler as lr_scheduler
import torch.utils.data
import yaml
from torch.cuda import amp
from torch.nn.parallel import DistributedDataParallel as DDP
from torch.utils.tensorboard import SummaryWriter
from tqdm import tqdm

import test? # import test.py to get mAP after each epoch
from models.experimental import attempt_load
from models.yolo import Model
from utils.autoanchor import check_anchors
from utils.datasets import create_dataloader
from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
??? fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
??? check_requirements, print_mutation, set_logging, one_cycle, colorstr
from utils.google_utils import attempt_download
from utils.loss import ComputeLoss
from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first

logger = logging.getLogger(__name__)


def train(hyp, opt, device, tb_writer=None, wandb=None):
??? logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
??? save_dir, epochs, batch_size, total_batch_size, weights, rank = \
??????? Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank

??? # Directories
??? wdir = save_dir / 'weights'
??? wdir.mkdir(parents=True, exist_ok=True)? # make dir
??? last = wdir / 'last.pt'
??? best = wdir / 'best.pt'
??? results_file = save_dir / 'results.txt'

??? # Save run settings
??? with open(save_dir / 'hyp.yaml', 'w') as f:
??????? yaml.dump(hyp, f, sort_keys=False)
??? with open(save_dir / 'opt.yaml', 'w') as f:
??????? yaml.dump(vars(opt), f, sort_keys=False)

??? # Configure
??? plots = not opt.evolve? # create plots
??? cuda = device.type != 'cpu'
??? init_seeds(2 + rank)
??? with open(opt.data) as f:
??????? data_dict = yaml.load(f, Loader=yaml.SafeLoader)? # data dict
??? with torch_distributed_zero_first(rank):
??????? check_dataset(data_dict)? # check
??? train_path = data_dict['train']
??? test_path = data_dict['val']
??? nc = 1 if opt.single_cls else int(data_dict['nc'])? # number of classes
??? names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names']? # class names
??? assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data)? # check

??? # Model
??? pretrained = weights.endswith('.pt')
??? if pretrained:
??????? with torch_distributed_zero_first(rank):
??????????? attempt_download(weights)? # download if not found locally
??????? ckpt = torch.load(weights, map_location=device)? # load checkpoint
??????? if hyp.get('anchors'):
??????????? ckpt['model'].yaml['anchors'] = round(hyp['anchors'])? # force autoanchor
??????? model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc).to(device)? # create
??????? exclude = ['anchor'] if opt.cfg or hyp.get('anchors') else []? # exclude keys
??????? state_dict = ckpt['model'].float().state_dict()? # to FP32
??????? state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude)? # intersect
??????? model.load_state_dict(state_dict, strict=False)? # load
??????? logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights))? # report
??? else:
??????? model = Model(opt.cfg, ch=3, nc=nc).to(device)? # create

??? # Freeze
??? freeze = []? # parameter names to freeze (full or partial)
??? for k, v in model.named_parameters():
??????? v.requires_grad = True? # train all layers
??????? if any(x in k for x in freeze):
??????????? print('freezing %s' % k)
??????????? v.requires_grad = False

??? # Optimizer
??? nbs = 64? # nominal batch size
??? accumulate = max(round(nbs / total_batch_size), 1)? # accumulate loss before optimizing
??? hyp['weight_decay'] *= total_batch_size * accumulate / nbs? # scale weight_decay
??? logger.info(f"Scaled weight_decay = {hyp['weight_decay']}")

??? pg0, pg1, pg2 = [], [], []? # optimizer parameter groups
??? for k, v in model.named_modules():
??????? if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
??????????? pg2.append(v.bias)? # biases
??????? if isinstance(v, nn.BatchNorm2d):
??????????? pg0.append(v.weight)? # no decay
??????? elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
??????????? pg1.append(v.weight)? # apply decay

??? if opt.adam:
??????? optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))? # adjust beta1 to momentum
??? else:
??????? optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

??? optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})? # add pg1 with weight_decay
??? optimizer.add_param_group({'params': pg2})? # add pg2 (biases)
??? logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
??? del pg0, pg1, pg2

??? # Scheduler https://arxiv.org/pdf/1812.01187.pdf
??? # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
??? lf = one_cycle(1, hyp['lrf'], epochs)? # cosine 1->hyp['lrf']
??? scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
? ??# plot_lr_scheduler(optimizer, scheduler, epochs)

??? # Logging
??? if rank in [-1, 0] and wandb and wandb.run is None:
??????? opt.hyp = hyp? # add hyperparameters
??????? wandb_run = wandb.init(config=opt, resume="allow",
?????????????????????????????? project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
?????????????????????????????? name=save_dir.stem,
?????????????????????????????? id=ckpt.get('wandb_id') if 'ckpt' in locals() else None)
??? loggers = {'wandb': wandb}? # loggers dict

??? # Resume
??? start_epoch, best_fitness = 0, 0.0
??? if pretrained:
??????? # Optimizer
??????? if ckpt['optimizer'] is not None:
??????????? optimizer.load_state_dict(ckpt['optimizer'])
??????????? best_fitness = ckpt['best_fitness']

??????? # Results
??????? if ckpt.get('training_results') is not None:
??????????? with open(results_file, 'w') as file:
??????????????? file.write(ckpt['training_results'])? # write results.txt

??????? # Epochs
????? ??start_epoch = ckpt['epoch'] + 1
??????? if opt.resume:
??????????? assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
??????? if epochs < start_epoch:
??????????? logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
??????????????????????? (weights, ckpt['epoch'], epochs))
??????????? epochs += ckpt['epoch']? # finetune additional epochs

??????? del ckpt, state_dict

??? # Image sizes
??? gs = int(model.stride.max())? # grid size (max stride)
??? nl = model.model[-1].nl? # number of detection layers (used for scaling hyp['obj'])
??? imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]? # verify imgsz are gs-multiples

??? # DP mode
??? if cuda and rank == -1 and torch.cuda.device_count() > 1:
??????? model = torch.nn.DataParallel(model)

??? # SyncBatchNorm
??? if opt.sync_bn and cuda and rank != -1:
??????? model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
??????? logger.info('Using SyncBatchNorm()')

??? # EMA
??? ema = ModelEMA(model) if rank in [-1, 0] else None

??? # DDP mode
??? if cuda and rank != -1:
??????? model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank)

??? # Trainloader
??? dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
??????????????????????????????????????????? hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
??????????????????? ????????????????????????world_size=opt.world_size, workers=opt.workers,
??????????????????????????????????????????? image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
??? mlc = np.concatenate(dataset.labels, 0)[:, 0].max()? # max label class
??? nb = len(dataloader)? # number of batches
??? assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)

??? # Process 0
??? if rank in [-1, 0]:
??????? ema.updates = start_epoch * nb // accumulate? # set EMA updates
??????? testloader = create_dataloader(test_path, imgsz_test, total_batch_size, gs, opt,? # testloader
?????????????????????????????????????? hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True, rank=-1,
?????????????????????????????????????? world_size=opt.world_size, workers=opt.workers,
?????????????????????????????????????? pad=0.5, prefix=colorstr('val: '))[0]

??????? if not opt.resume:
??????????? labels = np.concatenate(dataset.labels, 0)
??????????? c = torch.tensor(labels[:, 0])? # classes
??????????? # cf = torch.bincount(c.long(), minlength=nc) + 1.? # frequency
??????????? # model._initialize_biases(cf.to(device))
??????????? if plots:
??????????????? plot_labels(labels, save_dir, loggers)
??????????????? if tb_writer:
??????????????????? tb_writer.add_histogram('classes', c, 0)

??????????? # Anchors
??????????? if not opt.noautoanchor:
??????????????? check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)

??? # Model parameters
??? hyp['box'] *= 3. / nl? # scale to layers
??? hyp['cls'] *= nc / 80. * 3. / nl? # scale to classes and layers
??? hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl? # scale to image size and layers
??? model.nc = nc? # attach number of classes to model
??? model.hyp = hyp? # attach hyperparameters to model
??? model.gr = 1.0? # iou loss ratio (obj_loss = 1.0 or iou)
??? model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc? # attach class weights
??? model.names = names

??? # Start training
??? t0 = time.time()
??? nw = max(round(hyp['warmup_epochs'] * nb), 1000)? # number of warmup iterations, max(3 epochs, 1k iterations)
??? # nw = min(nw, (epochs - start_epoch) / 2 * nb)? # limit warmup to < 1/2 of training
??? maps = np.zeros(nc)? # mAP per class
??? results = (0, 0, 0, 0, 0, 0, 0)? # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
??? scheduler.last_epoch = start_epoch - 1? # do not move
??? scaler = amp.GradScaler(enabled=cuda)
??? compute_loss = ComputeLoss(model)? # init loss class
??? logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n'
??????????????? f'Using {dataloader.num_workers} dataloader workers\n'
??????????????? f'Logging results to {save_dir}\n'
??????????????? f'Starting training for {epochs} epochs...')
??? for epoch in range(start_epoch, epochs):? # epoch ------------------------------------------------------------------
??????? model.train()

??????? # Update image weights (optional)
??????? if opt.image_weights:
??????????? # Generate indices
??????????? if rank in [-1, 0]:
??????????????? cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc? # class weights
??????????????? iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)? # image weights
??????????????? dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)? # rand weighted idx
??????????? # Broadcast if DDP
??????????? if rank != -1:
??????????????? indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
??????????????? dist.broadcast(indices, 0)
??????????????? if rank != 0:
??????????????????? dataset.indices = indices.cpu().numpy()

??????? # Update mosaic border
??????? # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
??????? # dataset.mosaic_border = [b - imgsz, -b]? # height, width borders

??????? mloss = torch.zeros(4, device=device)? # mean losses
??????? if rank != -1:
??????????? dataloader.sampler.set_epoch(epoch)
??????? pbar = enumerate(dataloader)
??????? logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'targets', 'img_size'))
??????? if rank in [-1, 0]:
??????????? pbar = tqdm(pbar, total=nb)? # progress bar
??????? optimizer.zero_grad()
??????? for i, (imgs, targets, paths, _) in pbar:? # batch -------------------------------------------------------------
??????????? ni = i + nb * epoch? # number integrated batches (since train start)
??????????? imgs = imgs.to(device, non_blocking=True).float() / 255.0? # uint8 to float32, 0-255 to 0.0-1.0

??????????? # Warmup
??????????? if ni <= nw:
??????????????? xi = [0, nw]? # x interp
??????????????? # model.gr = np.interp(ni, xi, [0.0, 1.0])? # iou loss ratio (obj_loss = 1.0 or iou)
??????????????? accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
??????????????? for j, x in enumerate(optimizer.param_groups):
??????????????????? # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
??????????????????? x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
??????????????????? if 'momentum' in x:
??????????????????????? x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])

??????????? # Multi-scale
??????????? if opt.multi_scale:
??????????????? sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs? # size
??????????????? sf = sz / max(imgs.shape[2:])? # scale factor
??????????????? if sf != 1:
??????????????????? ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]? # new shape (stretched to gs-multiple)
??????????????????? imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)

??????????? # Forward
??????????? with amp.autocast(enabled=cuda):
??????????????? pred = model(imgs)? # forward
??????????????? loss, loss_items = compute_loss(pred, targets.to(device))? # loss scaled by batch_size
??????????????? if rank != -1:
??????????????????? loss *= opt.world_size? # gradient averaged between devices in DDP mode
??????????????? if opt.quad:
??????????????????? loss *= 4.

??????????? # Backward
??????????? scaler.scale(loss).backward()

??????????? # Optimize
??????????? if ni % accumulate == 0:
??????????????? scaler.step(optimizer)? # optimizer.step
??????????????? scaler.update()
??????????????? optimizer.zero_grad()
??????????????? if ema:
??????????????????? ema.update(model)

??????????? # Print
??????????? if rank in [-1, 0]:
??????????????? mloss = (mloss * i + loss_items) / (i + 1)? # update mean losses
??????????????? mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0)? # (GB)
??????????????? s = ('%10s' * 2 + '%10.4g' * 6) % (
??????????????????? '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
??????????????? pbar.set_description(s)

??????????????? # Plot
??????????????? if plots and ni < 3:
??????????????????? f = save_dir / f'train_batch{ni}.jpg'? # filename
??????????????????? Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
??????????????????? # if tb_writer:
??????????????????? #???? tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
??????????????????? #???? tb_writer.add_graph(model, imgs)? # add model to tensorboard
??????????????? elif plots and ni == 10 and wandb:
??????????????????? wandb.log({"Mosaics": [wandb.Image(str(x), caption=x.name) for x in save_dir.glob('train*.jpg')
?????????????????????????????????????????? if x.exists()]}, commit=False)

??????????? # end batch ------------------------------------------------------------------------------------------------
??????? # end epoch ----------------------------------------------------------------------------------------------------

??????? # Scheduler
??????? lr = [x['lr'] for x in optimizer.param_groups]? # for tensorboard
??????? scheduler.step()

??????? # DDP process 0 or single-GPU
??????? if rank in [-1, 0]:
??????????? # mAP
??????????? if ema:
??????????????? ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
??????????? final_epoch = epoch + 1 == epochs
??????????? if not opt.notest or final_epoch:? # Calculate mAP
??????????????? results, maps, times = test.test(opt.data,
?????????????????????????????????????????? ??????batch_size=total_batch_size,
???????????????????????????????????????????????? imgsz=imgsz_test,
???????????????????????????????????????????????? model=ema.ema,
???????????????????????????????????????????????? single_cls=opt.single_cls,
???????????????????????????????????????????????? dataloader=testloader,
???????????????????????????????????????????????? save_dir=save_dir,
??????????????????????????????????????? ?????????verbose=nc < 50 and final_epoch,
???????????????????????????????????????????????? plots=plots and final_epoch,
???????????????????????????????????????????????? log_imgs=opt.log_imgs if wandb else 0,
??????????????????????????????????????????????? ?compute_loss=compute_loss)

??????????? # Write
??????????? with open(results_file, 'a') as f:
??????????????? f.write(s + '%10.4g' * 7 % results + '\n')? # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
??????????? if len(opt.name) and opt.bucket:
??????????????? os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))

??????????? # Log
??????????? tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss',? # train loss
??????????????????? 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
??????????????????? 'val/box_loss', 'val/obj_loss', 'val/cls_loss',? # val loss
??????????????????? 'x/lr0', 'x/lr1', 'x/lr2']? # params
??????????? for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
??????????????? if tb_writer:
??????????????????? tb_writer.add_scalar(tag, x, epoch)? # tensorboard
??????????????? if wandb:
??????????????????? wandb.log({tag: x}, step=epoch, commit=tag == tags[-1])? # W&B

??????????? # Update best mAP
??????????? fi = fitness(np.array(results).reshape(1, -1))? # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
??????????? if fi > best_fitness:
??????????????? best_fitness = fi

??????????? # Save model
??????????? save = (not opt.nosave) or (final_epoch and not opt.evolve)
??????????? if save:
??????????????? with open(results_file, 'r') as f:? # create checkpoint
??????????????????? ckpt = {'epoch': epoch,
??????????????????????????? 'best_fitness': best_fitness,
??????????????????????????? 'training_results': f.read(),
??????????????????????????? 'model': ema.ema,
??????????????????????????? 'optimizer': None if final_epoch else optimizer.state_dict(),
??????????????????????????? 'wandb_id': wandb_run.id if wandb else None}

??????????????? # Save last, best and delete
??????????????? torch.save(ckpt, last)
??????????????? if best_fitness == fi:
??????????????????? torch.save(ckpt, best)
??????????????? del ckpt
??????? # end epoch ----------------------------------------------------------------------------------------------------
??? # end training

??? if rank in [-1, 0]:
??????? # Strip optimizers
??????? final = best if best.exists() else last? # final model
??????? for f in [last, best]:
??????????? if f.exists():
??????????????? strip_optimizer(f)? # strip optimizers
??????? if opt.bucket:
??????????? os.system(f'gsutil cp {final} gs://{opt.bucket}/weights')? # upload

??????? # Plots
??????? if plots:
??????????? plot_results(save_dir=save_dir)? # save as results.png
??????????? if wandb:
??????????????? files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
??????????????? wandb.log({"Results": [wandb.Image(str(save_dir / f), caption=f) for f in files
?????????????????????????????????????? if (save_dir / f).exists()]})
??????????????? if opt.log_artifacts:
??????????????????? wandb.log_artifact(artifact_or_path=str(final), type='model', name=save_dir.stem)

??????? # Test best.pt
??????? logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
??????? if opt.data.endswith('coco.yaml') and nc == 80:? # if COCO
??????????? for conf, iou, save_json in ([0.25, 0.45, False], [0.001, 0.65, True]):? # speed, mAP tests
??????????????? results, _, _ = test.test(opt.data,
????????????????????????????????????????? batch_size=total_batch_size,
????????????????????????????????????????? imgsz=imgsz_test,
????????????????????????????????????????? conf_thres=conf,
????????????????????????????????????????? iou_thres=iou,
????????????????????????????????????????? model=attempt_load(final, device).half(),
????????????????????????????????????????? single_cls=opt.single_cls,
????????????????????????????????????????? dataloader=testloader,
????????????????????????????????????????? save_dir=save_dir,
????????????????????????????????????????? save_json=save_json,
????????????????????????????????????????? plots=False)

??? else:
??????? dist.destroy_process_group()

??? wandb.run.finish() if wandb and wandb.run else None
??? torch.cuda.empty_cache()
??? return results


if __name__ == '__main__':
??? parser = argparse.ArgumentParser()
??? parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
??? parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
??? parser.add_argument('--data', type=str, default='data/tube.yaml', help='data.yaml path')
??? parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')
??? parser.add_argument('--epochs', type=int, default=100)
??? parser.add_argument('--batch-size', type=int, default=8, help='total batch size for all GPUs')
??? parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
??? parser.add_argument('--rect', action='store_true', help='rectangular training')
??? parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
??? parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
??? parser.add_argument('--notest', action='store_true', help='only test final epoch')
??? parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
??? parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
??? parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
??? parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
??? parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
??? parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
??? parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
??? parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
??? parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
??? parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
??? parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
??? parser.add_argument('--log-imgs', type=int, default=16, help='number of images for W&B logging, max 100')
??? parser.add_argument('--log-artifacts', action='store_true', help='log artifacts, i.e. final trained model')
??? parser.add_argument('--workers', type=int, default=0, help='maximum number of dataloader workers')
??? parser.add_argument('--project', default='runs/train', help='save to project/name')
??? parser.add_argument('--name', default='exp', help='save to project/name')
??? parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
??? parser.add_argument('--quad', action='store_true', help='quad dataloader')
??? opt = parser.parse_args()

??? # Set DDP variables
??? opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
??? opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
??? set_logging(opt.global_rank)
??? if opt.global_rank in [-1, 0]:
??????? check_git_status()
??????? check_requirements()

??? # Resume
??? if opt.resume:? # resume an interrupted run
??????? ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run()? # specified or most recent path
??????? assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
??????? apriori = opt.global_rank, opt.local_rank
??????? with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
??????????? opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader))? # replace
??????? opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori? # reinstate
??????? logger.info('Resuming training from %s' % ckpt)
??? else:
??????? # opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
??????? opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp)? # check files
??????? assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
??????? opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))? # extend to 2 sizes (train, test)
??????? opt.name = 'evolve' if opt.evolve else opt.name
??????? opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve)? # increment run

??? # DDP mode
??? opt.total_batch_size = opt.batch_size
??? device = select_device(opt.device, batch_size=opt.batch_size)
??? if opt.local_rank != -1:
??????? assert torch.cuda.device_count() > opt.local_rank
??????? torch.cuda.set_device(opt.local_rank)
??????? device = torch.device('cuda', opt.local_rank)
??????? dist.init_process_group(backend='nccl', init_method='env://')? # distributed backend
??????? assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
??????? opt.batch_size = opt.total_batch_size // opt.world_size

??? # Hyperparameters
??? with open(opt.hyp) as f:
??????? hyp = yaml.load(f, Loader=yaml.SafeLoader)? # load hyps

??? # Train
??? logger.info(opt)
??? # try:
??? #???? #import wandb
??? # except ImportError:
??? wandb = None
??? prefix = colorstr('wandb: ')
??? logger.info(f"{prefix}Install Weights & Biases for YOLOv5 logging with 'pip install wandb' (recommended)")
??? if not opt.evolve:
??????? tb_writer = None? # init loggers
??????? if opt.global_rank in [-1, 0]:
??????????? logger.info(f'Start Tensorboard with "tensorboard --logdir {opt.project}", view at http://localhost:6006/')
??????????? tb_writer = SummaryWriter(opt.save_dir)? # Tensorboard
??????? train(hyp, opt, device, tb_writer, wandb)

??? # Evolve hyperparameters (optional)
??? else:
??????? # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
??????? meta = {'lr0': (1, 1e-5, 1e-1),? # initial learning rate (SGD=1E-2, Adam=1E-3)
??????????????? 'lrf': (1, 0.01, 1.0),? # final OneCycleLR learning rate (lr0 * lrf)
??????????????? 'momentum': (0.3, 0.6, 0.98),? # SGD momentum/Adam beta1
??????????????? 'weight_decay': (1, 0.0, 0.001),? # optimizer weight decay
??????????????? 'warmup_epochs': (1, 0.0, 5.0),? # warmup epochs (fractions ok)
??????????????? 'warmup_momentum': (1, 0.0, 0.95),? # warmup initial momentum
??????????????? 'warmup_bias_lr': (1, 0.0, 0.2),? # warmup initial bias lr
??????????????? 'box': (1, 0.02, 0.2),? # box loss gain
??????????????? 'cls': (1, 0.2, 4.0),? # cls loss gain
??????????????? 'cls_pw': (1, 0.5, 2.0),? # cls BCELoss positive_weight
??????????????? 'obj': (1, 0.2, 4.0),? # obj loss gain (scale with pixels)
??????????????? 'obj_pw': (1, 0.5, 2.0),? # obj BCELoss positive_weight
??????????????? 'iou_t': (0, 0.1, 0.7),? # IoU training threshold
??????????????? 'anchor_t': (1, 2.0, 8.0),? # anchor-multiple threshold
??????????????? 'anchors': (2, 2.0, 10.0),? # anchors per output grid (0 to ignore)
??????????????? 'fl_gamma': (0, 0.0, 2.0),? # focal loss gamma (efficientDet default gamma=1.5)
??????????????? 'hsv_h': (1, 0.0, 0.1),? # image HSV-Hue augmentation (fraction)
??????????????? 'hsv_s': (1, 0.0, 0.9),? # image HSV-Saturation augmentation (fraction)
??????????????? 'hsv_v': (1, 0.0, 0.9),? # image HSV-Value augmentation (fraction)
??????????????? 'degrees': (1, 0.0, 45.0),? # image rotation (+/- deg)
??????????????? 'translate': (1, 0.0, 0.9),? # image translation (+/- fraction)
??????????????? 'scale': (1, 0.0, 0.9),? # image scale (+/- gain)
??????????????? 'shear': (1, 0.0, 10.0),? # image shear (+/- deg)
??????????????? 'perspective': (0, 0.0, 0.001),? # image perspective (+/- fraction), range 0-0.001
??????????????? 'flipud': (1, 0.0, 1.0),? # image flip up-down (probability)
??????????????? 'fliplr': (0, 0.0, 1.0),? # image flip left-right (probability)
??????????????? 'mosaic': (1, 0.0, 1.0),? # image mixup (probability)
??????????????? 'mixup': (1, 0.0, 1.0)}? # image mixup (probability)

??????? assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
??????? opt.notest, opt.nosave = True, True? # only test/save final epoch
??????? # ei = [isinstance(x, (int, float)) for x in hyp.values()]? # evolvable indices
??????? yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml'? # save best result here
??????? if opt.bucket:
??????????? os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)? # download evolve.txt if exists

??????? for _ in range(300):? # generations to evolve
??????????? if Path('evolve.txt').exists():? # if evolve.txt exists: select best hyps and mutate
??????????????? # Select parent(s)
??????????????? parent = 'single'? # parent selection method: 'single' or 'weighted'
??????????????? x = np.loadtxt('evolve.txt', ndmin=2)
???? ???????????n = min(5, len(x))? # number of previous results to consider
??????????????? x = x[np.argsort(-fitness(x))][:n]? # top n mutations
??????????????? w = fitness(x) - fitness(x).min()? # weights
??????????????? if parent == 'single' or len(x) == 1:
??????????????????? # x = x[random.randint(0, n - 1)]? # random selection
??????????????????? x = x[random.choices(range(n), weights=w)[0]]? # weighted selection
??????????????? elif parent == 'weighted':
??????????????????? x = (x * w.reshape(n, 1)).sum(0) / w.sum()? # weighted combination

??????????????? # Mutate
??????????????? mp, s = 0.8, 0.2? # mutation probability, sigma
??????????????? npr = np.random
??????????????? npr.seed(int(time.time()))
??????????????? g = np.array([x[0] for x in meta.values()])? # gains 0-1
??????????????? ng = len(meta)
??????????????? v = np.ones(ng)
??????????????? while all(v == 1):? # mutate until a change occurs (prevent duplicates)
??????????????????? v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
??????????????? for i, k in enumerate(hyp.keys()):? # plt.hist(v.ravel(), 300)
??????????????????? hyp[k] = float(x[i + 7] * v[i])? # mutate

??????????? # Constrain to limits
??????????? for k, v in meta.items():
??????????????? hyp[k] = max(hyp[k], v[1])? # lower limit
??????????????? hyp[k] = min(hyp[k], v[2])? # upper limit
??????????????? hyp[k] = round(hyp[k], 5)? # significant digits

??????????? # Train mutation
??????????? results = train(hyp.copy(), opt, device, wandb=wandb)

??????????? # Write mutation results
??????????? print_mutation(hyp.copy(), results, yaml_file, opt.bucket)

??????? # Plot results
??????? plot_evolution(yaml_file)
??????? print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
????????????? f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')

#6 detect.py

"""Run inference with a YOLOv5 model on images, videos, directories, streamsUsage:$ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640"""import argparseimport sysimport timefrom pathlib import Pathimport cv2import torchimport torch.backends.cudnn as cudnnFILE = Path(__file__).absolute()sys.path.append(FILE.parents[0].as_posix())? # add yolov5/ to pathfrom models.experimental import attempt_loadfrom utils.datasets import LoadStreams, LoadImagesfrom utils.general import check_img_size, check_requirements, check_imshow, colorstr, non_max_suppression, \apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_boxfrom utils.plots import colors, plot_one_boxfrom utils.torch_utils import select_device, load_classifier, time_sync@torch.no_grad()def run(weights='E:/555/555/yolov5-master/runs/train/exp24/weights/best.pt',? # model.pt path(s),E:/555/555/yolov5-master/runs/train/exp24/weights/best.pt? 默認(rèn)： yolov5s.ptsource='data/images',? # file/dir/URL/glob, 0 for webcamimgsz=640,? # inference size (pixels)conf_thres=0.25,? # confidence thresholdiou_thres=0.45,? # NMS IOU thresholdmax_det=1000,? # maximum detections per imagedevice='',? # cuda device, i.e. 0 or 0,1,2,3 or cpu 默認(rèn)使用GPU，選擇CPU時那么會在CPU設(shè)備檢測view_img=True,? # show results 顯示檢測的結(jié)果save_txt=False,? # save results to *.txtsave_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='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 inference):"""opt參數(shù)詳解weights:測試的模型權(quán)重文件data:數(shù)據(jù)集配置文件，數(shù)據(jù)集路徑，類名等batch-size:前向傳播時的批次, 默認(rèn)32img-size:輸入圖片分辨率大小, 默認(rèn)640conf-thres:篩選框的時候的置信度閾值, 默認(rèn)0.001iou-thres:進(jìn)行NMS的時候的IOU閾值, 默認(rèn)0.65save-json:是否按照coco的json格式保存預(yù)測框，并且使用cocoapi做評估(需要同樣coco的json格式的標(biāo)簽), 默認(rèn)Falsetask:設(shè)置測試形式, 默認(rèn)val, 具體可看下面代碼解析注釋device:測試的設(shè)備，cpu；0(表示一個gpu設(shè)備cuda:0)；0,1,2,3(多個gpu設(shè)備)single-cls:數(shù)據(jù)集是否只有一個類別，默認(rèn)Falseaugment:測試時是否使用TTA(test time augmentation), 默認(rèn)Falsemerge:在進(jìn)行NMS時，是否通過合并方式獲得預(yù)測框, 默認(rèn)Falseverbose:是否打印出每個類別的mAP, 默認(rèn)Falsesave-txt:是否以txt文件的形式保存模型預(yù)測的框坐標(biāo), 默認(rèn)False"""save_img = not nosave and not source.endswith('.txt')? # save inference imageswebcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))# 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# Initializeset_logging()device = select_device(device)half &= device.type != 'cpu'? # half precision only supported on CUDA# Load modelw = weights[0] if isinstance(weights, list) else weightsclassify, pt, onnx = False, w.endswith('.pt'), w.endswith('.onnx')? # inference typestride, names = 64, [f'class{i}' for i in range(1000)]? # assign defaultsif pt:model = attempt_load(weights, map_location=device)? # load FP32 modelstride = int(model.stride.max())? # model stridenames = model.module.names if hasattr(model, 'module') else model.names? # get class namesif half:model.half()? # to FP16if classify:? # second-stage classifiermodelc = load_classifier(name='resnet50', n=2)? # initializemodelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()elif onnx:check_requirements(('onnx', 'onnxruntime'))import onnxruntimesession = onnxruntime.InferenceSession(w, None)imgsz = check_img_size(imgsz, s=stride)? # check image size# Dataloaderif webcam:view_img = check_imshow()cudnn.benchmark = True? # set True to speed up constant image size inferencedataset = LoadStreams(source, img_size=imgsz, stride=stride)bs = len(dataset)? # batch_sizeelse:dataset = LoadImages(source, img_size=imgsz, stride=stride)bs = 1? # batch_sizevid_path, vid_writer = [None] * bs, [None] * bs# Run inferenceif pt and device.type != 'cpu':model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))? # run oncet0 = time.time()for path, img, im0s, vid_cap in dataset:if pt:img = torch.from_numpy(img).to(device)img = img.half() if half else img.float()? # uint8 to fp16/32elif onnx:img = img.astype('float32')img /= 255.0? # 0 - 255 to 0.0 - 1.0if len(img.shape) == 3:img = img[None]? # expand for batch dim# Inferencet1 = time_sync()if pt:visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else Falsepred = model(img, augment=augment, visualize=visualize)[0]elif onnx:pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))# NMSpred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)t2 = time_sync()# Second-stage classifier (optional)if classify:pred = apply_classifier(pred, modelc, img, im0s)# Process predictionsfor i, det in enumerate(pred):? # detections per imageif webcam:? # batch_size >= 1p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.countelse:p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)p = Path(p)? # to Pathsave_path = str(save_dir / p.name)? # img.jpgtxt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')? # img.txts += '%gx%g ' % img.shape[2:]? # print stringgn = torch.tensor(im0.shape)[[1, 0, 1, 0]]? # normalization gain whwhimc = im0.copy() if save_crop else im0? # for save_cropif len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()# Print resultsfor c in det[:, -1].unique():n = (det[:, -1] == c).sum()? # detections per classs += f"{n} {names[int(c)]}{'s' * (n > 1)}, "? # add to string# Write resultsfor *xyxy, conf, cls in reversed(det):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(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}')plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=line_thickness)if save_crop:save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)# Print time (inference + NMS)print(f'{s}Done. ({t2 - t1:.3f}s)')# Stream resultsif view_img: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 += '.mp4'vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))vid_writer[i].write(im0)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 ''print(f"Results saved to {colorstr('bold', save_dir)}{s}")if update:strip_optimizer(weights)? # update model (to fix SourceChangeWarning)print(f'Done. ({time.time() - t0:.3f}s)')def parse_opt():#這里參數(shù)可以修改parser = argparse.ArgumentParser()parser.add_argument('--weights', nargs='+', type=str, default='E:/555/555/yolov5-master/runs/train/exp24/weights/best.pt', help='model.pt path(s)') #打開訓(xùn)練完的自己數(shù)據(jù)集（best.pt）路徑: E:/555/555/yolov5-master/runs/train/exp14/weights/best.ptparser.add_argument('--source', type=str, default='0', help='file/dir/URL/glob, 0 for webcam')#data/images，打開普通照片路徑：E:/555/555/mydata3/test，打開攝像頭：0parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')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='', 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-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: --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('--visualize', action='store_true', help='visualize features')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')parser.add_argument('--line-thickness', default=3, 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')opt = parser.parse_args()return optdef main(opt):print(colorstr('detect: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))check_requirements(exclude=('tensorboard', 'thop'))run(**vars(opt))if __name__ == "__main__":opt = parse_opt()main(opt)

#7 Video.py(每間隔3秒對應(yīng)的幀數(shù)采集照片并yolov5檢測最后保存)

import timeimport cv2import numpy as npfrom PIL import Imageimport detect# from detect import parse_opt #這里的detect是detect.py（yolov5的檢測）文件，parse_opt表示檢測參數(shù)的設(shè)置# detect = parse_optcapture = cv2.VideoCapture(0)# capture=cv2.VideoCapture("D:/1.mp4")if capture.isOpened():ref, frame = capture.read()else:ref = Falsefps = 0.0timeF = 420?? #yolov5每秒140幀（FPS）c = 1while ref:t1 = time.time()# 讀取某一幀ref, frame = capture.read()# 此處保存圖片無檢測結(jié)果，用于采集訓(xùn)練數(shù)據(jù)和測試攝像頭是否清晰穩(wěn)定if (c % timeF == 0):fps = (fps + (1. / (time.time() - t1))) / 2print("fps= %.2f" % (fps))frame = cv2.putText(frame, "fps= %.2f" % (fps), (0, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)# 采集到每隔420幀的圖像，保存到/runs/img./in/cv2.imwrite("./runs/img/in/" + str(c) + '.jpg', frame)# 將采集到的/runs/img./in/圖像輸入detect檢測，結(jié)果保存在/runs/img/outdetect.run(source="./runs/img/in/" + str(c) + '.jpg', name='../img/out/photo')c += 1# print(frame)## # 格式轉(zhuǎn)變，BGRtoRGB# frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)# # 轉(zhuǎn)變成Image# frame = Image.fromarray(np.uint8(frame))# # 進(jìn)行檢測# frame = np.array(detect.run(source=frame))# # RGBtoBGR滿足opencv顯示格式# frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)## # 此處保存的圖片有檢測結(jié)果，用于保留檢測結(jié)果# if (c % timeF == 0):#???? cv2.imwrite("./runs/" + str(c) + '.jpg', frame)# c += 1## fps = (fps + (1. / (time.time() - t1))) / 2# print("fps= %.2f" % (fps))# frame = cv2.putText(frame, "fps= %.2f" % (fps), (0, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)# 此處保存的圖片上既有檢測結(jié)果，也有fps值，用于監(jiān)測不同fps下的檢測結(jié)果# if (c % timeF == 0):#??? cv2.imwrite("D:/photo/" + str(c) + '.jpg', frame)# c += 1# 顯示攝像頭cv2.imshow("video", frame)k = cv2.waitKey(1)# 按q退出if k == ord('q'):capture.release()break# 按ESC退出k = cv2.waitKey(1)if k == 27:capture.release()break

總結(jié)

以上是生活随笔為你收集整理的基于YOLOV5动态检测19种类别的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。