### 文章目录

 Hi，大家好，这里是丹成学长的毕设系列文章！

 对毕设有任何疑问都可以问学长哦!

 **基于YOLO实现的口罩佩戴检测 **

磊学长这里给一个题目综合评分(每项满分5分)

#### 刺 选题指导, 项目分享：

https://blog.csdn.net/Mr_DC_IT/article/details/126460477

## 2.1 算法简介

YOLOv5是一种单阶段目标检测算法，该算法在YOLOv4的基础上添加了一些新的改进思路，使其速度与精度都得到了极大的性能提升。主要的改进思路如下所示：

## 2.2 网络架构

Neck网络-Neck网络通常位于基准网络和头网络的中间位置，利用它可以进一步提升特征的多样性及鲁棒性。虽然YOLOv5同样用到了SPP模块、FPN+PAN模块，但是实现的细节有些不同。

## 3 关键代码

```class Detect(nn.Module):
stride = None  # strides computed during build
onnx_dynamic = False  # ONNX export parameter
def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
super().__init__()
self.nc = nc  # number of classes
self.no = nc + 5  # number of outputs per anchor
self.nl = len(anchors)  # number of detection layers
self.na = len(anchors[0]) // 2  # number of anchors
self.grid = [torch.zeros(1)] * self.nl  # init grid
self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
self.inplace = inplace  # use in-place ops (e.g. slice assignment)
def forward(self, x):
z = []  # inference output
for i in range(self.nl):
x[i] = self.m[i](x[i])  # conv
bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
if not self.training:  # inference
if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
y = x[i].sigmoid()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
y = torch.cat((xy, wh, y[..., 4:]), -1)
z.append(y.view(bs, -1, self.no))
return x if self.training else (torch.cat(z, 1), x)
def _make_grid(self, nx=20, ny=20, i=0):
d = self.anchors[i].device
if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
else:
yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
return grid, anchor_grid
class Model(nn.Module):
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg  # model dict
else:  # is *.yaml
import yaml  # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg, encoding='ascii', errors='ignore') as f:
self.yaml = yaml.safe_load(f)  # model dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding model.yaml nc={
self.yaml['nc']} with nc={
nc}")
self.yaml['nc'] = nc  # override yaml value
if anchors:
LOGGER.info(f'Overriding model.yaml anchors with anchors={
anchors}')
self.yaml['anchors'] = round(anchors)  # override yaml value
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
self.inplace = self.yaml.get('inplace', True)
# Build strides, anchors
m = self.model[-1]  # Detect()
if isinstance(m, Detect):
s = 256  # 2x min stride
m.inplace = self.inplace
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
m.anchors /= m.stride.view(-1, 1, 1)
check_anchor_order(m)
self.stride = m.stride
self._initialize_biases()  # only run once
# Init weights, biases
initialize_weights(self)
self.info()
LOGGER.info('')
def forward(self, x, augment=False, profile=False, visualize=False):
if augment:
return self._forward_augment(x)  # augmented inference, None
return self._forward_once(x, profile, visualize)  # single-scale inference, train
def _forward_augment(self, x):
img_size = x.shape[-2:]  # height, width
s = [1, 0.83, 0.67]  # scales
f = [None, 3, None]  # flips (2-ud, 3-lr)
y = []  # outputs
for si, fi in zip(s, f):
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
yi = self._forward_once(xi)[0]  # forward
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
yi = self._descale_pred(yi, fi, si, img_size)
y.append(yi)
y = self._clip_augmented(y)  # clip augmented tails
def _forward_once(self, x, profile=False, visualize=False):
y, dt = [], []  # outputs
for m in self.model:
if m.f != -1:  # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
if profile:
self._profile_one_layer(m, x, dt)
x = m(x)  # run
y.append(x if m.i in self.save else None)  # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
return x
def _descale_pred(self, p, flips, scale, img_size):
# de-scale predictions following augmented inference (inverse operation)
if self.inplace:
p[..., :4] /= scale  # de-scale
if flips == 2:
p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
elif flips == 3:
p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
else:
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
if flips == 2:
y = img_size[0] - y  # de-flip ud
elif flips == 3:
x = img_size[1] - x  # de-flip lr
p = torch.cat((x, y, wh, p[..., 4:]), -1)
return p
def _clip_augmented(self, y):
# Clip YOLOv5 augmented inference tails
nl = self.model[-1].nl  # number of detection layers (P3-P5)
g = sum(4 ** x for x in range(nl))  # grid points
e = 1  # exclude layer count
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
y[0] = y[0][:, :-i]  # large
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
y[-1] = y[-1][:, i:]  # small
return y
def _profile_one_layer(self, m, x, dt):
c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
t = time_sync()
for _ in range(10):
m(x.copy() if c else x)
dt.append((time_sync() - t) * 100)
if m == self.model[0]:
LOGGER.info(f"{
'time (ms)':>10s} {
'GFLOPs':>10s} {
'params':>10s}  {
'module'}")
LOGGER.info(f'{
dt[-1]:10.2f} {
o:10.2f} {
m.np:10.0f}  {
m.type}')
if c:
LOGGER.info(f"{
sum(dt):10.2f} {
'-':>10s} {
'-':>10s}  Total")
def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
# https://arxiv.org/abs/1708.02002 section 3.3
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
m = self.model[-1]  # Detect() module
for mi, s in zip(m.m, m.stride):  # from
b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # cls
def _print_biases(self):
m = self.model[-1]  # Detect() module
for mi in m.m:  # from
b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
LOGGER.info(
('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
# def _print_weights(self):
#     for m in self.model.modules():
#         if type(m) is Bottleneck:
#             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
LOGGER.info('Fusing layers... ')
for m in self.model.modules():
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
delattr(m, 'bn')  # remove batchnorm
m.forward = m.forward_fuse  # update forward
self.info()
return self
def autoshape(self):  # add AutoShape module
m = AutoShape(self)  # wrap model
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributes
return m
def info(self, verbose=False, img_size=640):  # print model information
model_info(self, verbose, img_size)
def _apply(self, fn):
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
self = super()._apply(fn)
m = self.model[-1]  # Detect()
if isinstance(m, Detect):
m.stride = fn(m.stride)
m.grid = list(map(fn, m.grid))
if isinstance(m.anchor_grid, list):
m.anchor_grid = list(map(fn, m.anchor_grid))
return self
def parse_model(d, ch):  # model_dict, input_channels(3)
LOGGER.info(f"
{
'':>3}{
'from':>18}{
'n':>3}{
'params':>10}  {
'module':<40}{
'arguments':<30}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
m = eval(m) if isinstance(m, str) else m  # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a  # eval strings
except NameError:
pass
n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
c1, c2 = ch[f], args[0]
if c2 != no:  # if not output
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
args.insert(2, n)  # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int):  # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
t = str(m)[8:-2].replace('__main__.', '')  # module type
np = sum(x.numel() for x in m_.parameters())  # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
LOGGER.info(f'{
i:>3}{
str(f):>18}{
n_:>3}{
np:10.0f}  {
t:<40}{
str(args):<30}')  # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
layers.append(m_)
if i == 0:
ch = []
ch.append(c2)
return nn.Sequential(*layers), sorted(save)```

## 4.1 安装

`pip install labelimg`

## 6.1 pyqt实现简单GUI

```from PyQt5 import QtCore, QtGui, QtWidgets
Win_mask.setStyleSheet("QString qstrStylesheet = \"background-color:rgb(43, 43, 255)\";
"
"ui.pushButton->setStyleSheet(qstrStylesheet);")
self.frame.setGeometry(QtCore.QRect(10, 140, 201, 701))
self.frame.setFrameShape(QtWidgets.QFrame.StyledPanel)
self.frame.setObjectName("frame")
self.pushButton = QtWidgets.QPushButton(self.frame)
self.pushButton.setGeometry(QtCore.QRect(10, 40, 161, 51))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.pushButton.setFont(font)
self.pushButton.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
self.pushButton.setObjectName("pushButton")
self.pushButton_2 = QtWidgets.QPushButton(self.frame)
self.pushButton_2.setGeometry(QtCore.QRect(10, 280, 161, 51))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.pushButton_2.setFont(font)
self.pushButton_2.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
self.pushButton_2.setObjectName("pushButton_2")
self.pushButton_3 = QtWidgets.QPushButton(self.frame)
self.pushButton_3.setGeometry(QtCore.QRect(10, 500, 161, 51))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
font.setStrikeOut(False)
self.pushButton_3.setFont(font)
self.pushButton_3.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
self.pushButton_3.setObjectName("pushButton_3")
self.frame_2.setGeometry(QtCore.QRect(230, 110, 1031, 861))
self.frame_2.setStyleSheet("")
self.frame_2.setFrameShape(QtWidgets.QFrame.StyledPanel)
self.frame_2.setObjectName("frame_2")
self.show_picture_page = QtWidgets.QStackedWidget(self.frame_2)
self.show_picture_page.setGeometry(QtCore.QRect(-10, 0, 871, 731))
font = QtGui.QFont()
font.setBold(True)
font.setWeight(75)
self.show_picture_page.setFont(font)
self.show_picture_page.setObjectName("show_picture_page")
self.photo = QtWidgets.QWidget()
self.photo.setObjectName("photo")
self.label = QtWidgets.QLabel(self.photo)
self.label.setGeometry(QtCore.QRect(10, 30, 641, 641))
font = QtGui.QFont()
font.setFamily("Arial")
font.setPointSize(36)
self.label.setFont(font)
self.label.setText("")
self.label.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
self.label.setObjectName("label")
self.pushButton_4 = QtWidgets.QPushButton(self.photo)
self.pushButton_4.setGeometry(QtCore.QRect(680, 220, 171, 61))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.pushButton_4.setFont(font)
self.pushButton_4.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.pushButton_4.setObjectName("pushButton_4")
self.pushButton_5 = QtWidgets.QPushButton(self.photo)
self.pushButton_5.setGeometry(QtCore.QRect(680, 400, 171, 61))
font = QtGui.QFont()
font.setUnderline(True)
self.pushButton_5.setFont(font)
self.pushButton_5.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.pushButton_5.setObjectName("pushButton_5")
self.videos = QtWidgets.QWidget()
self.videos.setObjectName("videos")
self.vid_img = QtWidgets.QLabel(self.videos)
self.vid_img.setGeometry(QtCore.QRect(10, 30, 640, 640))
font = QtGui.QFont()
font.setFamily("Arial")
font.setPointSize(36)
self.vid_img.setFont(font)
self.vid_img.setText("")
self.vid_img.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
self.vid_img.setObjectName("vid_img")
self.mp4_detection_btn = QtWidgets.QPushButton(self.videos)
self.mp4_detection_btn.setGeometry(QtCore.QRect(680, 220, 171, 61))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.mp4_detection_btn.setFont(font)
self.mp4_detection_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.mp4_detection_btn.setObjectName("mp4_detection_btn")
self.vid_stop_btn = QtWidgets.QPushButton(self.videos)
self.vid_stop_btn.setGeometry(QtCore.QRect(680, 400, 171, 61))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.vid_stop_btn.setFont(font)
self.vid_stop_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.vid_stop_btn.setObjectName("vid_stop_btn")
self.camera = QtWidgets.QWidget()
self.camera.setObjectName("camera")
self.webcam_detection_btn = QtWidgets.QPushButton(self.camera)
self.webcam_detection_btn.setGeometry(QtCore.QRect(680, 220, 171, 61))
self.webcam_detection_btn.setBaseSize(QtCore.QSize(2, 2))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.webcam_detection_btn.setFont(font)
self.webcam_detection_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.webcam_detection_btn.setObjectName("webcam_detection_btn")
self.cam_img = QtWidgets.QLabel(self.camera)
self.cam_img.setGeometry(QtCore.QRect(10, 30, 640, 640))
font = QtGui.QFont()
font.setFamily("Arial")
font.setPointSize(36)
self.cam_img.setFont(font)
self.cam_img.setText("")
self.cam_img.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
self.cam_img.setObjectName("cam_img")
self.vid_stop_btn_cma = QtWidgets.QPushButton(self.camera)
self.vid_stop_btn_cma.setGeometry(QtCore.QRect(680, 400, 171, 61))
font = QtGui.QFont()
font.setBold(True)
font.setUnderline(True)
font.setWeight(75)
self.vid_stop_btn_cma.setFont(font)
self.vid_stop_btn_cma.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
self.vid_stop_btn_cma.setObjectName("vid_stop_btn_cma")
self.label_2.setGeometry(QtCore.QRect(430, 40, 251, 71))
font = QtGui.QFont()
font.setPointSize(24)
font.setBold(True)
font.setItalic(False)
font.setUnderline(True)
font.setWeight(75)
self.label_2.setFont(font)
self.label_2.setStyleSheet("Font{background-color:rgb(85, 170, 255);}")
self.label_2.setObjectName("label_2")
self.listView.setGeometry(QtCore.QRect(-5, 1, 1121, 871))
self.listView.setStyleSheet("
"
"background-image: url(:/bg.png);")
self.listView.setObjectName("listView")
self.listView.raise_()
self.frame.raise_()
self.frame_2.raise_()
self.label_2.raise_()
self.show_picture_page.setCurrentIndex(0)

## 6.4 摄像头实时识别

#### 刺 选题指导, 项目分享：

https://blog.csdn.net/Mr_DC_IT/article/details/126460477