基于深度学习YOLOv5目标检测的人脸表情识别系统

第一步：YOLOv5介绍

YOLOv5是一种目标检测算法，它是YOLO（You Only Look Once）系列的最新版本。YOLOv5在YOLOv4的基础上进行了改进和优化，以提高检测的准确性和速度。

YOLOv5采用了一些新的技术和方法来改进目标检测的性能。其中包括以下几个方面：

1. 损失函数：YOLOv5使用了CIOU_Loss作为bounding box的损失函数。CIOU_Loss是一种改进的IOU_Loss，可以更好地衡量目标框的位置和大小。

2. 非极大值抑制（NMS）：YOLOv5使用NMS来抑制重叠的边界框，以减少重复检测的问题。

3. 聚类anchors：YOLOv5使用k-means聚类算法来生成anchors，这些anchors用于检测不同尺度的目标。

总的来说，YOLOv5在YOLOv4的基础上进行了一些改进和优化，以提高目标检测的准确性和速度。

标注数据，YOLOv5的训练和测试步骤，各路大神都已经做了很多工作，我就不再写了。

这里的表情识别相当于是一步到位，检测到人脸的时候，也判断出此人脸属于什么表情，市面上大部分表情识别的做法是两步，第一步检测到人脸，第二步基于fer2013训练一个分类网络来判断检测到的人脸属于什么表情。

第二步：YOLOv5网络结构

第三步：代码展示

"""Train a YOLOv5 model on a custom dataset

Usage:
    $ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640
"""

import argparse
import logging
import os
import random
import sys
import time
import warnings
from copy import deepcopy
from pathlib import Path
from threading import Thread

import math
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

FILE = Path(__file__).absolute()
sys.path.append(FILE.parents[0].as_posix())  # add yolov5/ to path

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.datasets import create_dataloader
from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
    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, de_parallel
from utils.wandb_logging.wandb_utils import WandbLogger, check_wandb_resume
from utils.metrics import fitness

LOGGER = logging.getLogger(__name__)
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,  # path/to/hyp.yaml or hyp dictionary
          opt,
          device,
          ):
    save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, = \
        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

    # Directories
    save_dir = Path(save_dir)
    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'

    # Hyperparameters
    if isinstance(hyp, str):
        with open(hyp) 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
    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)

    # Configure
    plots = not evolve  # create plots
    cuda = device.type != 'cpu'
    init_seeds(1 + RANK)
    with open(data) as f:
        data_dict = yaml.safe_load(f)  # data dict

    # Loggers
    loggers = {'wandb': None, 'tb': None}  # loggers dict
    if RANK in [-1, 0]:
        # TensorBoard
        if not evolve:
            prefix = colorstr('tensorboard: ')
            LOGGER.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/")
            loggers['tb'] = SummaryWriter(str(save_dir))

        # W&B
        opt.hyp = hyp  # add hyperparameters
        run_id = torch.load(weights).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None
        run_id = run_id if opt.resume else None  # start fresh run if transfer learning
        wandb_logger = WandbLogger(opt, save_dir.stem, run_id, data_dict)
        loggers['wandb'] = wandb_logger.wandb
        if loggers['wandb']:
            data_dict = wandb_logger.data_dict
            weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp  # may update weights, epochs if resuming

    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, '%g names found for nc=%g dataset in %s' % (len(names), nc, data)  # check
    is_coco = data.endswith('coco.yaml') and nc == 80  # COCO dataset

    # Model
    pretrained = weights.endswith('.pt')
    if pretrained:
        with torch_distributed_zero_first(RANK):
            weights = attempt_download(weights)  # download if not found locally
        ckpt = torch.load(weights, map_location=device)  # load checkpoint
        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
        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(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
    with torch_distributed_zero_first(RANK):
        check_dataset(data_dict)  # check
    train_path = data_dict['train']
    val_path = data_dict['val']

    # 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 / 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']}")

    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(