【极市任务——安全帽检测|yolov5】一文带你快速通过任务|使用yolov5[6.0]|和极市说明文档不一样的yolov5内容|python

目录

 

时间：2022.6.23

极市的新人任务——安全帽识别通过简单的赛题带我们更好的熟悉了极市比赛、项目的打榜流程。

如果你也是深度学习爱好者，也不妨短暂停留看看！！！

1.开发环境选择

2.配置yolov5环境

3.编写代码

4.模型训练

5.模型测试

6.领取奖励

没有谁的成功是一步而就的，你需要花费比别人更多的时间，更多的精力，更多的热爱。

---

时间：2022.6.23

极市的新人任务——安全帽识别通过简单的赛题带我们更好的熟悉了极市比赛、项目的打榜流程。

极市开发者平台-计算机视觉算法开发落地平台 (cvmart.net)https://www.cvmart.net/

如果你也是深度学习爱好者，也不妨短暂停留看看！！！

此次的安全帽识别是典型的目标检测问题，为了方便有基础的选手们可以快速收悉流程，极市发布了yolov5打榜安全帽检测的一个说明文档，写的我认为是十分详细了，作为一个合格的小编，就不在博客里面复现了，给大家呈现一下我自己打榜的方法。

说明文档：（里面有一个yolov5教程）

极市开发者平台-计算机视觉算法开发落地平台 (cvmart.net)https://www.cvmart.net/document

---

 好了，废话不多，正片开始！

 1.开发环境选择

 我选择的是pytorch1.10.0，实例是一个乌班图系统，CUDA、OPENCV均自带好了，显卡是一张Tesla的显卡，显存大概15G。

Linux基础命令：（大神这里直接跳过吧~）//可能会用到

回到根目录：cd /
回到父级目录：cd ..
进入目录：cd XXX
列出当前目录下面的所有文件：ls
编辑文件：vim XXX
    --保存并退出：:wq
    --进入编译模式：i
    --退出编译模式：【esc】
清屏：clear
软连接：ln -s 目标文件或文件夹 软连接名字

创建实例之后可以进行代码编写（限时7个小时）- > 模型训练（单次训练文件不能超过1G，一共不能超过10G）->模型测试（编写并自动调用yi.py）->领取奖励。 

 编码注意事项：

 这里我选择的是VSCode编译器，他类似于咱的PyCharm，左边那个就是咱的老朋友Jupyter。

 点击左边的画红圈的那个，那个是文件树列表，蓝色的是测试的时候要建立一个ji.py文件，右边红色划线的时数据集存放的地方（我们只能看到样例数据集，看不到全部数据集）。

2.配置yolov5环境

在编写代码之前，我先给大家看一下咱的数据集长啥样~~~

 （指标都是0是因为数据集太少+学习率太高~~~~）

注：通过前面写的linux指令就能把他弄出来啦~~~

 

 可以看到极市的数据集都是标注好的VOC格式。

下一步，我们转移咱的yolov5代码，目前有两种方法（可能还有更多，我还没发现！！！）

1.把自己写好的代码复制上去——CV呗~（这种方法虽然笨，但是可以把自己改完的模型、代码上传上去）

2.打开终端：（Ctrl  + J）

cd /project/train/src_repo
git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

3.编写代码

这一步就和咱平时写代码一样。

附上一个我使用yolov5做项目的文章吧，这里就不再细细展开啦！！抱歉！抱歉！具体使用方法详见：

(132条消息) 【python 目标检测】基于深度学习的道路破损检测|yolov5|VOC_活成自己的样子啊的博客-CSDN博客_路面破损数据集https://blog.csdn.net/m0_61139217/article/details/124182727?spm=1001.2014.3001.5501

调试：F5       【不论是训练还是测试，都要先在本地调试，本地也有一张15G的显卡的，可以用于调试】

 这里我是点击的第一个。

 配置、转换数据集，为了放入咱的模型训练，我们需要把VOC转成YOLO格式的数据集，如图所示是我的数据集存放路径树：（和我做yolov5的时候基本一样）

这里给出变化后的2个制作数据集的代码：(注意位置！！！)（这里的相对路径写法一定要注意！！！）

/project/train/src_repo/makeTXT.py

"""生成Main里面的4个txt文件，对应每一个图片名称"""
import os
import random
 
def makeTXT():
    traintest_percent = 0.9  # 测试集的比例（1-traintest_percent）
    train_percent = 0.8  # 训练集和测试集的比例（训练集的占比）
    
    base_path = '/home/data'  # xml
    base_path = os.path.join(base_path, os.listdir(base_path)[0])
    txtsavepath = 'train/src_repo/datasets/VOC/ImageSets/Main'   # 训练集、验证集、测试集的路径
    total_xml = []

    for each_path in os.listdir(base_path):
        xmlfilepath = each_path.endswith('.xml')
        if xmlfilepath:
            total_xml.append(each_path)
    
    num = len(total_xml)
    list = range(num)  # 【0， num - 1】
    tv = int(num * traintest_percent)  # 验证集和训练集的数量
    tr = int(tv * train_percent)  # 训练集数量
    # sample(list, k)返回一个长度为k新列表，新列表存放list所产生k个随机唯一的元素
    trainval = random.sample(list, tv)
    train = random.sample(trainval, tr)
    
    ftrainval = open(txtsavepath + '/trainval.txt', 'w')
    ftest = open(txtsavepath + '/test.txt', 'w')
    ftrain = open(txtsavepath + '/train.txt', 'w')
    fval = open(txtsavepath + '/val.txt', 'w')
    
    for i in list:
        # [:-4]切掉后4位（.xml）
        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()

/project/train/src_repo/xml2txt.py

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
# sets设置的就是
sets = ['train', 'val', 'test']
 
# 类别
classes = ['hat', 'person', 'head']  # 寻找类别（这里写自己标注的类别就行）
 
# 转换成yolo格式的标注【类别， x代表标注中心横坐标在图像中的比例，y代表标注中心纵坐标在图像中的比例，w表示标注框宽占比，h表示标注框高占比】
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)
 
 
def convert_annotation(image_id):
    in_file = open('/home/data/831/%s.xml' % image_id, encoding='utf8')
    out_file = open('train/src_repo/datasets/VOC/labels/%s.txt' % image_id, 'w')
 
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
 
    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
 
        # b是2个坐标的4个值
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
 
        bb = convert((w, h), b)
 
        # 【类别， x代表标注中心横坐标在图像中的比例，y代表标注中心纵坐标在图像中的比例，w表示标注框宽占比，h表示标注框高占比】
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 

def runs():
    wd = r'train/src_repo/datasets/VOC'

    # sets：train、val、test
    for image_set in sets:
        #  创建labels
        if not os.path.exists(wd + '/labels/'):
            os.makedirs(wd + '/labels/')
    
        image_ids = open('train/src_repo/datasets/VOC/ImageSets/Main/%s.txt' % image_set).read().strip().split()
        list_file = open('train/src_repo/datasets/VOC/%s.txt' % image_set, 'w')
    
        # 对每一张进行操作
        for image_id in image_ids:
            list_file.write('/home/data/831/%s.jpg\n' % image_id)  # 写入每一个图片的路径
            convert_annotation(image_id)
        list_file.close()

 /project/train/src_repo/train.py  (这个是在原有train.py基础上改变过来的！！！直接CV即可)

修改：

---1---命令行参数默认值直接设置好了（所设置的文件路径也是需要放置的路径，比如hyp、data、model的yaml文件）

---2---其次是把上面的两个数据集制作函数一起加入到train.py里面了，这样就不用写.sh文件来启动命令了，对linux新手甚是友好！

---3---project保存路径改为：/project/train/tensorboard  （为了方便极市打开tensorboard）

---4---模型保存改为：torch.save(ckpt, r'/project/train/models/' + f'epoch{epoch}.pt')

import argparse
import math
import os
import random
import sys
import time
from copy import deepcopy
from datetime import datetime
from pathlib import Path

import numpy as np
import torch
import torch.distributed as dist
import torch.nn as nn
import yaml
from torch.nn.parallel import DistributedDataParallel as DDP
from torch.optim import SGD, Adam, AdamW, lr_scheduler
from tqdm import tqdm

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

import val  # for end-of-epoch mAP
from models.experimental import attempt_load
from models.yolo import Model
from utils.autoanchor import check_anchors
from utils.autobatch import check_train_batch_size
from utils.callbacks import Callbacks
from utils.dataloaders import create_dataloader
from utils.downloads import attempt_download
from utils.general import (LOGGER, check_amp, check_dataset, check_file, check_git_status, check_img_size,
                           check_requirements, check_suffix, check_version, check_yaml, colorstr, get_latest_run,
                           increment_path, init_seeds, intersect_dicts, labels_to_class_weights,
                           labels_to_image_weights, methods, one_cycle, print_args, print_mutation, strip_optimizer)
from utils.loggers import Loggers
from utils.loggers.wandb.wandb_utils import check_wandb_resume
from utils.loss import ComputeLoss
from utils.metrics import fitness
from utils.plots import plot_evolve, plot_labels
from utils.torch_utils import EarlyStopping, ModelEMA, de_parallel, select_device, torch_distributed_zero_first

LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
RANK = int(os.getenv('RANK', -1))
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))


def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictionary
    save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze = \
        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
        opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze
    callbacks.run('on_pretrain_routine_start')

    # Directories
    w = save_dir / 'weights'  # weights dir
    (w.parent if evolve else w).mkdir(parents=True, exist_ok=True)  # make dir
    last, best = w / 'last.pt', w / 'best.pt'

    # Hyperparameters
    if isinstance(hyp, str):
        with open(hyp, errors='ignore') as f:
            hyp = yaml.safe_load(f)  # load hyps dict
    LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))

    # Save run settings
    if not evolve:
        with open(save_dir / 'hyp.yaml', 'w') as f:
            yaml.safe_dump(hyp, f, sort_keys=False)
        with open(save_dir / 'opt.yaml', 'w') as f:
            yaml.safe_dump(vars(opt), f, sort_keys=False)

    # Loggers
    data_dict = None
    if RANK in {-1, 0}:
        loggers = Loggers(save_dir, weights, opt, hyp, LOGGER)  # loggers instance
        if loggers.wandb:
            data_dict = loggers.wandb.data_dict
            if resume:
                weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size

        # Register actions
        for k in methods(loggers):
            callbacks.register_action(k, callback=getattr(loggers, k))

    # Config
    plots = not evolve and not opt.noplots  # create plots
    cuda = device.type != 'cpu'
    init_seeds(1 + RANK)
    with torch_distributed_zero_first(LOCAL_RANK):
        data_dict = data_dict or check_dataset(data)  # check if None
    train_path, val_path = data_dict['train'], data_dict['val']
    nc = 1 if single_cls else int(data_dict['nc'])  # number of classes
    names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
    assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}'  # check
    is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt')  # COCO dataset

    # Model
    check_suffix(weights, '.pt')  # check weights
    pretrained = weights.endswith('.pt')
    if pretrained:
        with torch_distributed_zero_first(LOCAL_RANK):
            weights = attempt_download(weights)  # download if not found locally
        ckpt = torch.load(weights, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
        model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
        exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else []  # exclude keys
        csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
        csd = intersect_dicts(csd, model.state_dict(), exclude=exclude)  # intersect
        model.load_state_dict(csd, strict=False)  # load
        LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}')  # report
    else:
        model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
    amp = check_amp(model)  # check AMP

    # Freeze
    freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))]  # layers to freeze
    for k, v in model.named_parameters():
        v.requires_grad = True  # train all layers
        if any(x in k for x in freeze):
            LOGGER.info(f'freezing {k}')
            v.requires_grad = False

    # Image size
    gs = max(int(model.stride.max()), 32)  # grid size (max stride)
    imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple

    # Batch size
    if RANK == -1 and batch_size == -1:  # single-GPU only, estimate best batch size
        batch_size = check_train_batch_size(model, imgsz, amp)
        loggers.on_params_update({"batch_size": batch_size})

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

    g = [], [], []  # optimizer parameter groups
    bn = tuple(v for k, v in nn.__dict__.items() if 'Norm' in k)  # normalization layers, i.e. BatchNorm2d()
    for v in model.modules():
        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):  # bias
            g[2].append(v.bias)
        if isinstance(v, bn):  # weight (no decay)
            g[1].append(v.weight)
        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):  # weight (with decay)
            g[0].append(v.weight)

    if opt.optimizer == 'Adam':
        optimizer = Adam(g[2], lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
    elif opt.optimizer == 'AdamW':
        optimizer = AdamW(g[2], lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
    else:
        optimizer = SGD(g[2], lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

    optimizer.add_param_group({'params': g[0], 'weight_decay': hyp['weight_decay']})  # add g0 with weight_decay
    optimizer.add_param_group({'params': g[1]})  # add g1 (BatchNorm2d weights)
    LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
                f"{len(g[1])} weight (no decay), {len(g[0])} weight, {len(g[2])} bias")
    del g

    # Scheduler
    if opt.cos_lr:
        lf = one_cycle(1, hyp['lrf'], epochs)  # cosine 1->hyp['lrf']
    else:
        lf = lambda x: (1 - x / epochs) * (1.0 - hyp['lrf']) + hyp['lrf']  # linear
    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)  # plot_lr_scheduler(optimizer, scheduler, epochs)

    # EMA
    ema = ModelEMA(model) if RANK in {-1, 0} else None

    # 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']

        # EMA
        if ema and ckpt.get('ema'):
            ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
            ema.updates = ckpt['updates']

        # Epochs
        start_epoch = ckpt['epoch'] + 1
        if resume:
            assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.'
        if epochs < start_epoch:
            LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.")
            epochs += ckpt['epoch']  # finetune additional epochs

        del ckpt, csd

    # DP mode
    if cuda and RANK == -1 and torch.cuda.device_count() > 1:
        LOGGER.warning('WARNING: DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n'
                       'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.')
        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()')

    # Trainloader
    train_loader, dataset = create_dataloader(train_path,
                                              imgsz,
                                              batch_size // WORLD_SIZE,
                                              gs,
                                              single_cls,
                                              hyp=hyp,
                                              augment=True,
                                              cache=None if opt.cache == 'val' else opt.cache,
                                              rect=opt.rect,
                                              rank=LOCAL_RANK,
                                              workers=workers,
                                              image_weights=opt.image_weights,
                                              quad=opt.quad,
                                              prefix=colorstr('train: '),
                                              shuffle=True)
    mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max())  # max label class
    nb = len(train_loader)  # number of batches
    assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'

    # Process 0
    if RANK in {-1, 0}:
        val_loader = create_dataloader(val_path,
                                       imgsz,
                                       batch_size // WORLD_SIZE * 2,
                                       gs,
                                       single_cls,
                                       hyp=hyp,
                                       cache=None if noval else opt.cache,
                                       rect=True,
                                       rank=-1,
                                       workers=workers * 2,
                                       pad=0.5,
                                       prefix=colorstr('val: '))[0]

        if not 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, names, save_dir)

            # Anchors
            if not opt.noautoanchor:
                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
            model.half().float()  # pre-reduce anchor precision

        callbacks.run('on_pretrain_routine_end')

    # DDP mode
    if cuda and RANK != -1:
        if check_version(torch.__version__, '1.11.0'):
            model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK, static_graph=True)
        else:
            model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK)

    # Model attributes
    nl = de_parallel(model).model[-1].nl  # number of detection layers (to scale hyps)
    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
    hyp['label_smoothing'] = opt.label_smoothing
    model.nc = nc  # attach number of classes to model
    model.hyp = hyp  # attach hyperparameters to model
    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), 100)  # number of warmup iterations, max(3 epochs, 100 iterations)
    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
    last_opt_step = -1
    maps = np.zeros(nc)  # mAP per class
    results = (0, 0, 0, 0, 0, 0, 0)  # P, R, [email protected], [email protected], val_loss(box, obj, cls)
    scheduler.last_epoch = start_epoch - 1  # do not move
    scaler = torch.cuda.amp.GradScaler(enabled=amp)
    stopper = EarlyStopping(patience=opt.patience)
    compute_loss = ComputeLoss(model)  # init loss class
    callbacks.run('on_train_start')
    LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
                f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
                f"Logging results to {colorstr('bold', save_dir)}\n"
                f'Starting training for {epochs} epochs...')
    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
        callbacks.run('on_train_epoch_start')
        model.train()

        # Update image weights (optional, single-GPU only)
        if opt.image_weights:
            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

        # Update mosaic border (optional)
        # 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(3, device=device)  # mean losses
        if RANK != -1:
            train_loader.sampler.set_epoch(epoch)
        pbar = enumerate(train_loader)
        LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
        if RANK in {-1, 0}:
            pbar = tqdm(pbar, total=nb, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
        optimizer.zero_grad()
        for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
            callbacks.run('on_train_batch_start')
            ni = i + nb * epoch  # number integrated batches (since train start)
            imgs = imgs.to(device, non_blocking=True).float() / 255  # uint8 to float32, 0-255 to 0.0-1.0

            # Warmup
            if ni <= nw:
                xi = [0, nw]  # x interp
                # compute_loss.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 / 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 = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)

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

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

            # Optimize
            if ni - last_opt_step >= accumulate:
                scaler.step(optimizer)  # optimizer.step
                scaler.update()
                optimizer.zero_grad()
                if ema:
                    ema.update(model)
                last_opt_step = ni

            # Log
            if RANK in {-1, 0}:
                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
                mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G'  # (GB)
                pbar.set_description(('%10s' * 2 + '%10.4g' * 5) %
                                     (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
                callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots)
                if callbacks.stop_training:
                    return
            # end batch ------------------------------------------------------------------------------------------------

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

        if RANK in {-1, 0}:
            # mAP
            callbacks.run('on_train_epoch_end', epoch=epoch)
            ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
            final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
            if not noval or final_epoch:  # Calculate mAP
                results, maps, _ = val.run(data_dict,
                                           batch_size=batch_size // WORLD_SIZE * 2,
                                           imgsz=imgsz,
                                           model=ema.ema,
                                           single_cls=single_cls,
                                           dataloader=val_loader,
                                           save_dir=save_dir,
                                           plots=False,
                                           callbacks=callbacks,
                                           compute_loss=compute_loss)

            # Update best mAP
            fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, [email protected], [email protected]]
            if fi > best_fitness:
                best_fitness = fi
            log_vals = list(mloss) + list(results) + lr
            callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi)

            # Save model
            if (not nosave) or (final_epoch and not evolve):  # if save
                ckpt = {
                    'epoch': epoch,
                    'best_fitness': best_fitness,
                    'model': deepcopy(de_parallel(model)).half(),
                    'ema': deepcopy(ema.ema).half(),
                    'updates': ema.updates,
                    'optimizer': optimizer.state_dict(),
                    'wandb_id': loggers.wandb.wandb_run.id if loggers.wandb else None,
                    'date': datetime.now().isoformat()}

                # Save last, best and delete
                torch.save(ckpt, last)
                if best_fitness == fi:
                    torch.save(ckpt, best)
                if (epoch > 0) and (opt.save_period > 0) and (epoch % opt.save_period == 0):
                    # torch.save(ckpt, w / f'epoch{epoch}.pt')
                    torch.save(ckpt, r'/project/train/models/' + f'epoch{epoch}.pt')
                del ckpt
                callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)

            # Stop Single-GPU
            if RANK == -1 and stopper(epoch=epoch, fitness=fi):
                break

            # Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576
            # stop = stopper(epoch=epoch, fitness=fi)
            # if RANK == 0:
            #    dist.broadcast_object_list([stop], 0)  # broadcast 'stop' to all ranks

        # Stop DPP
        # with torch_distributed_zero_first(RANK):
        # if stop:
        #    break  # must break all DDP ranks

        # end epoch ----------------------------------------------------------------------------------------------------
    # end training -----------------------------------------------------------------------------------------------------
    if RANK in {-1, 0}:
        LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
        for f in last, best:
            if f.exists():
                strip_optimizer(f)  # strip optimizers
                if f is best:
                    LOGGER.info(f'\nValidating {f}...')
                    results, _, _ = val.run(
                        data_dict,
                        batch_size=batch_size // WORLD_SIZE * 2,
                        imgsz=imgsz,
                        model=attempt_load(f, device).half(),
                        iou_thres=0.65 if is_coco else 0.60,  # best pycocotools results at 0.65
                        single_cls=single_cls,
                        dataloader=val_loader,
                        save_dir=save_dir,
                        save_json=is_coco,
                        verbose=True,
                        plots=plots,
                        callbacks=callbacks,
                        compute_loss=compute_loss)  # val best model with plots
                    if is_coco:
                        callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)

        callbacks.run('on_train_end', last, best, plots, epoch, results)

    torch.cuda.empty_cache()
    return results


def parse_opt(known=False):
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', type=str, default='', help='initial weights path')
    parser.add_argument('--cfg', type=str, default='train/src_repo/yolov5s.yaml', help='model.yaml path')
    parser.add_argument('--data', type=str, default='train/src_repo/voc-myself.yaml', help='dataset.yaml path')
    parser.add_argument('--hyp', type=str, default='train/src_repo/hyp.myself.yaml', help='hyperparameters path')
    parser.add_argument('--epochs', type=int, default=100)
    parser.add_argument('--batch-size', type=int, default=32, help='total batch size for all GPUs, -1 for autobatch')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
    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('--noval', action='store_true', help='only validate final epoch')
    parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
    parser.add_argument('--noplots', action='store_true', help='save no plot files')
    parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
    parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
    parser.add_argument('--device', default='0', 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('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
    parser.add_argument('--workers', type=int, default=4, help='max dataloader workers (per RANK in DDP mode)')
    parser.add_argument('--project', default='/project/train/tensorboard', 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')
    parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
    parser.add_argument('--patience', type=int, default=30, help='EarlyStopping patience (epochs without improvement)')
    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
    parser.add_argument('--save-period', type=int, default=3, help='Save checkpoint every x epochs (disabled if < 1)')
    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')

    # Weights & Biases arguments
    parser.add_argument('--entity', default=None, help='W&B: Entity')
    parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option')
    parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
    parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')

    opt = parser.parse_known_args()[0] if known else parser.parse_args()
    return opt


def main(opt, callbacks=Callbacks()):
    # Checks
    if RANK in {-1, 0}:
        print_args(vars(opt))
        check_git_status()
        check_requirements(exclude=['thop'])

    # Resume
    if opt.resume and not check_wandb_resume(opt) and not opt.evolve:  # 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'
        with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
            opt = argparse.Namespace(**yaml.safe_load(f))  # replace
        opt.cfg, opt.weights, opt.resume = '', ckpt, True  # reinstate
        LOGGER.info(f'Resuming training from {ckpt}')
    else:
        opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
            check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project)  # checks
        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
        if opt.evolve:
            if opt.project == str(ROOT / 'runs/train'):  # if default project name, rename to runs/evolve
                opt.project = str(ROOT / 'runs/evolve')
            opt.exist_ok, opt.resume = opt.resume, False  # pass resume to exist_ok and disable resume
        if opt.name == 'cfg':
            opt.name = Path(opt.cfg).stem  # use model.yaml as name
        opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))

    # DDP mode
    device = select_device(opt.device, batch_size=opt.batch_size)
    if LOCAL_RANK != -1:
        msg = 'is not compatible with YOLOv5 Multi-GPU DDP training'
        assert not opt.image_weights, f'--image-weights {msg}'
        assert not opt.evolve, f'--evolve {msg}'
        assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size'
        assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE'
        assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
        torch.cuda.set_device(LOCAL_RANK)
        device = torch.device('cuda', LOCAL_RANK)
        dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")

    # Train
    if not opt.evolve:
        train(opt.hyp, opt, device, callbacks)
        if WORLD_SIZE > 1 and RANK == 0:
            LOGGER.info('Destroying process group... ')
            dist.destroy_process_group()

    # 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)
            'copy_paste': (1, 0.0, 1.0)}  # segment copy-paste (probability)

        with open(opt.hyp, errors='ignore') as f:
            hyp = yaml.safe_load(f)  # load hyps dict
            if 'anchors' not in hyp:  # anchors commented in hyp.yaml
                hyp['anchors'] = 3
        opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir)  # only val/save final epoch
        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
        evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
        if opt.bucket:
            os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {evolve_csv}')  # download evolve.csv if exists

        for _ in range(opt.evolve):  # generations to evolve
            if evolve_csv.exists():  # if evolve.csv exists: select best hyps and mutate
                # Select parent(s)
                parent = 'single'  # parent selection method: 'single' or 'weighted'
                x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
                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() + 1E-6  # weights (sum > 0)
                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([meta[k][0] for k in hyp.keys()])  # 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, callbacks)
            callbacks = Callbacks()
            # Write mutation results
            print_mutation(results, hyp.copy(), save_dir, opt.bucket)

        # Plot results
        plot_evolve(evolve_csv)
        LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n'
                    f"Results saved to {colorstr('bold', save_dir)}\n"
                    f'Usage example: $ python train.py --hyp {evolve_yaml}')


def run(**kwargs):
    # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
    opt = parse_opt(True)
    for k, v in kwargs.items():
        setattr(opt, k, v)
    main(opt)
    return opt



if __name__ == "__main__":
    import makeTXT
    import xml2txt
    makeTXT.makeTXT()
    xml2txt.runs()
    opt = parse_opt()
    main(opt)

其他文件速览：

train/src_repo/hyp.myself.yaml  :(可以参数跑的时候可能会出现p、r、map归零的情况，合理改变学习率或者batchsize即可，也可以换成自己的参数)

# YOLOv5  by Ultralytics, GPL-3.0 license
# Hyperparameters for low-augmentation COCO training from scratch
# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials

lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.937  # SGD momentum/Adam beta1
weight_decay: 0.0005  # optimizer weight decay 5e-4
warmup_epochs: 3.0  # warmup epochs (fractions ok)
warmup_momentum: 0.8  # warmup initial momentum
warmup_bias_lr: 0.1  # warmup initial bias lr
box: 0.05  # box loss gain
cls: 0.5  # cls loss gain
cls_pw: 1.0  # cls BCELoss positive_weight
obj: 1.0  # obj loss gain (scale with pixels)
obj_pw: 1.0  # obj BCELoss positive_weight
iou_t: 0.20  # IoU training threshold
anchor_t: 4.0  # anchor-multiple threshold
# anchors: 3  # anchors per output layer (0 to ignore)
fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4  # image HSV-Value augmentation (fraction)
degrees: 0.0  # image rotation (+/- deg)
translate: 0.1  # image translation (+/- fraction)
scale: 0.5  # image scale (+/- gain)
shear: 0.0  # image shear (+/- deg)
perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
flipud: 0.0  # image flip up-down (probability)
fliplr: 0.5  # image flip left-right (probability)
mosaic: 1.0  # image mosaic (probability)
mixup: 0.0  # image mixup (probability)
copy_paste: 0.0  # segment copy-paste (probability)

train/src_repo/voc-myself.yaml  :

train: datasets/VOC/train.txt #此处是/而不是\
val: datasets/VOC/val.txt #此处是/而不是\
test: datasets/VOC/test.txt #此处是/而不是\
 
# Classes
nc: 3  # number of classes 数据集类别数量
names: ['hat', 'person', 'head']  # class names 数据集类别名称，注意和标签的顺序对应`

train/src_repo/yolov5s.yaml  :

# YOLOv5  by Ultralytics, GPL-3.0 license

# Parameters
nc: 3  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [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 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-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)
  ]

注：安全帽检测一共有3个类别，分别是：'hat', 'person', 'head'

4.模型训练

训练模型，极市推荐使用 .sh 命令行，但是好多小伙伴不知道咋写，索性我们直接用命令就行（如果你用的是上面我改的代码的话！）

 没错！！！以上命令和我们平时右键运行【pycharm】是一样的效果哒~

一开始的训练日志：

 过了40轮之后的训练日志：

 可以看到指标发生了明显的提升！

当然，因为我修改了yolov5 project的保存路径，所以你也可以看到tensorboard效果图！

 

 注：这里可以看见我只训练了50轮。但是模型还没有收敛。

5.模型测试

这一步是最后一步，也是最关键的一步，不是最难的，但是最费事的。。。

可以看到：（我经过了无数次的失败测试，才成功提交上了！唔）

 极市测试是直接调用 /project/ev_sdk/src 下的 ji.py 文件（名字别弄错了），所以我们需要自己写一个接口在该路径下面！！！

我直接给出代码：

/project/ev_sdk/src/ji.py  ：（注意这里的导包！！用的是相对路径导包，没办法，极市非得用这个位置测试，我又懒得移动文件）

注：那个model_path变量赋值成自己的权重保存路径。。。别直接抄上了。。。

import json
import torch
import sys
import numpy as np
import cv2
from pathlib import Path

#from ensemble_boxes import weighted_boxes_fusion

# from train.src_repo.models.experimental import attempt_load
# from train.src_repo.utils.torch_utils import select_device
# from train.src_repo.utils.general import check_img_size, non_max_suppression, scale_coords
from train.src_repo.utils.augmentations import letterbox
from train.src_repo.models.common import DetectMultiBackend
from train.src_repo.utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from train.src_repo.utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from train.src_repo.utils.plots import Annotator, colors, save_one_box
from train.src_repo.utils.torch_utils import select_device, time_sync

device = torch.device("cuda:0")
model_path = r'/project/train/models/epoch48.pt'   # 模型地址一定要和测试阶段选择的模型地址一致！！！
@torch.no_grad()
def init():
    weights = model_path
    device = 'cuda:0'  # cuda device, i.e. 0 or 0,1,2,3 or

    half = True  # use FP16 half-precision inference
    device = select_device(device)
    w = str(weights[0] if isinstance(weights, list) else weights)
    # model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
    model = DetectMultiBackend(w, device=device, dnn=False, data=r'/project/train/src_repo/voc-myself.yaml', fp16=True)
    if half:
        model.half()  # to FP16
    model.eval()
    return model

def process_image(handle=None, input_image=None, args=None, **kwargs):
    half = True  # use FP16 half-precision inference
    conf_thres = 0.3  # confidence threshold
    iou_thres = 0.05  # NMS IOU threshold

    max_det = 1000  # maximum detections per image
    imgsz = [640, 640]
    names = {
        0: 'person',
        1: 'hat',
        2: 'head'
    }

    stride = 32
    fake_result = {}
    fake_result["model_data"] = {"objects": []}

    img = letterbox(input_image, imgsz, stride, True)[0]
    img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
    img  = img/255  # 0 - 255 to 0.0 - 1.0
    img = torch.from_numpy(img)
    img = torch.unsqueeze(img, dim=0).to(device)
    img = img.type(torch.cuda.HalfTensor)
    pred = handle(img, augment=False, visualize=False)
    pred = non_max_suppression(pred, conf_thres, iou_thres, None, False, max_det=max_det)

    for i, det in enumerate(pred):  # per image
        det[:, :4] = scale_coords(img.shape[2:], det[:, :4], input_image.shape).round()

        for *xyxy, conf, cls in reversed(det):
            xyxy_list = torch.tensor(xyxy).view(1, 4).view(-1).tolist()
            conf_list = conf.tolist()
            label = names[int(cls)]
            fake_result['model_data']['objects'].append({
                "xmin": int(xyxy_list[0]),
                "ymin": int(xyxy_list[1]),
                "xmax": int(xyxy_list[2]),
                "ymax": int(xyxy_list[3]),
                "confidence": conf_list,
                "name": label
                })

    return json.dumps(fake_result, indent=4)

你以为这样就完了吗？no way！

因为相对位置的原因，你需要把yolov5代码里面所有的导包给改掉，改成相对路径导包！！！

例如：加上  train.src_repo.

 左边画红圈的文件都需要改！！！

提示：

直接debug（F5）ji.py 文件，看他报错就行，知道不报导包的错误了，就说明全部改完了。

【这里如果有大神有好的办法也可以拿出来分享哦！！！】

6.领取奖励

emmm，最后别忘了领取奖励哦！

---

没有谁的成功是一步而就的，你需要花费比别人更多的时间，更多的精力，更多的热爱。