YOLOv5算法详解

2

5

=

32

2^{5} =32

25=32；最后对该数值除以2，即将填充的区域分散到两边。这样将416*416大小的图片缩小到416*320大小，因而极大的提升了算法的推理速度。**
  需要注意的是：（1）该操作仅在模型推理阶段执行，模型训练阶段仍然和传统的方法相同，将原始图片裁剪到416*416大小；(2)YOLOv3与YOLOv4中默认填充的数值是(0,0,0)，而YOLOv5中默认填充的数值是(114,114,114)；（3）该操作仅仅针对原始图片的短边而言，仍然将长边裁剪到416。

3.2.3 基准网络细节详解

• Focus结构-该结构的主要思想是通过slice操作来对输入图片进行裁剪。如下图所示，原始输入图片大小为608*608*3，经过Slice与Concat操作之后输出一个304*304*12的特征映射；接着经过一个通道个数为32的Conv层（该通道个数仅仅针对的是YOLOv5s结构，其它结构会有相应的变化），输出一个304*304*32大小的特征映射。
  
• CSP结构-YOLOv4网络结构中，借鉴了CSPNet的设计思路，仅仅在主干网络中设计了CSP结构。而YOLOv5中设计了两种CSP结构，以YOLOv5s网络为例，CSP1_X结构应用于Backbone主干网络中，另一种CSP2_X结构则应用于Neck网络中。CSP1_X与CSP2_X模块的实现细节如3.1所示。

3.2.4 Neck网络细节详解

• FPN+PAN-YOLOv5的Neck网络仍然使用了FPN+PAN结构，但是在它的基础上做了一些改进操作，YOLOv4的Neck结构中，采用的都是普通的卷积操作。而YOLOv5的Neck网络中，采用借鉴CSPnet设计的CSP2结构，从而加强网络特征融合能力。下图展示了YOLOv4与YOLOv5的Neck网络的具体细节，通过比较我们可以发现：（1）灰色区域表示第1个不同点，YOLOv5不仅利用CSP2_\1结构代替部分CBL模块，而且去掉了下方的CBL模块；（2）绿色区域表示第2个不同点，YOLOv5不仅将Concat操作之后的CBL模块更换为CSP2_1模块，而且更换了另外一个CBL模块的位置；（3）蓝色区域表示第3个不同点，YOLOv5中将原始的CBL模块更换为CSP2_1模块。
  

3.2.5 Head输出端细节详解

• GIoU_Loss-YOLOv5中采用GIoU_Loss做Bounding box的损失函数，更多的细节请参考这篇博客。

4、YOLOv5网络代码实现

# 检测类
class Detect(nn.Module):
    stride = None  # strides computed during build
    export = False  # onnx export

    def \_\_init\_\_(self, nc=80, anchors=(), ch=()):  # detection layer
        super(Detect, self).__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
        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
        self.register_buffer('anchors', a)  # shape(nl,na,2)
        self.register_buffer('anchor\_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no \* self.na, 1) for x in ch)  # output conv

    def forward(self, x):
        # x = x.copy() # for profiling
        z = []  # inference output
        self.training |= self.export
        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.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)

                y = x[i].sigmoid()
                y[..., 0:2] = (y[..., 0:2] \* 2. - 0.5 + self.grid[i].to(x[i].device)) \* self.stride[i]  # xy
                y[..., 2:4] = (y[..., 2:4] \* 2) \*\* 2 \* self.anchor_grid[i]  # wh
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1), x)

    @staticmethod
    def \_make\_grid(nx=20, ny=20):
        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()

# 根据配置的.yaml文件搭建模型
class Model(nn.Module):
    def \_\_init\_\_(self, cfg='yolov5s.yaml', ch=3, nc=None):  # model, input channels, number of classes
        super(Model, self).__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) as f:
                self.yaml = yaml.load(f, Loader=yaml.SafeLoader)  # model dict

        # Define model
        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
        if nc and nc != self.yaml['nc']:
            logger.info('Overriding model.yaml nc=%g with nc=%g' % (self.yaml['nc'], nc))
            self.yaml['nc'] = nc  # 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
        # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])

        # Build strides, anchors
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):
            s = 256  # 2x min stride
            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
            # print('Strides: %s' % m.stride.tolist())

        # Init weights, biases
        initialize_weights(self)
        self.info()
        logger.info('')

    def forward(self, x, augment=False, profile=False):
        if augment:
            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[..., :4] /= si  # de-scale
                if fi == 2:
                    yi[..., 1] = img_size[0] - yi[..., 1]  # de-flip ud
                elif fi == 3:
                    yi[..., 0] = img_size[1] - yi[..., 0]  # de-flip lr
                y.append(yi)
            return torch.cat(y, 1), None  # augmented inference, train
        else:
            return self.forward_once(x, profile)  # single-scale inference, train

    def forward\_once(self, x, profile=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:
                o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 \* 2 if thop else 0  # FLOPS
                t = time_synchronized()
                for _ in range(10):
                    _ = m(x)
                dt.append((time_synchronized() - t) \* 100)
                print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))

            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output

        if profile:
            print('%.1fms total' % sum(dt))
        return x

    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 - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)

    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)
            print(('%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:
    # print('%10.3g' % (m.w.detach().sigmoid() \* 2)) # shortcut weights

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        print('Fusing layers... ')
        for m in self.model.modules():
            if type(m) is Conv and hasattr(m, 'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.fuseforward  # update forward
        self.info()
        return self

    def nms(self, mode=True):  # add or remove NMS module
        present = type(self.model[-1]) is NMS  # last layer is NMS
        if mode and not present:
            print('Adding NMS... ')
            m = NMS()  # module
            m.f = -1  # from
            m.i = self.model[-1].i + 1  # index
            self.model.add_module(name='%s' % m.i, module=m)  # add
            self.eval()
        elif not mode and present:
            print('Removing NMS... ')
            self.model = self.model[:-1]  # remove
        return self

    def autoshape(self):  # add autoShape module
        print('Adding autoShape... ')
        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)

# 解析模型
def parse\_model(d, ch):  # model\_dict, input\_
**作者徽是vip1024c**
channels(3)
    logger.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
    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:
                pass

        n = max(round(n \* gd), 1) if n > 1 else n  # depth gain
        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
                 C3]:
            c1, c2 = ch[f], args[0]

            # Normal
            # if i > 0 and args[0] != no: # channel expansion factor
            # ex = 1.75 # exponential (default 2.0)
            # e = math.log(c2 / ch[1]) / math.log(2)
            # c2 = int(ch[1] \* ex \*\* e)
            # if m != Focus:

            c2 = make_divisible(c2 \* gw, 8) if c2 != no else c2

            # Experimental
            # if i > 0 and args[0] != no: # channel expansion factor
            # ex = 1 + gw # exponential (default 2.0)
            # ch1 = 32 # ch[1]
            # e = math.log(c2 / ch1) / math.log(2) # level 1-n
            # c2 = int(ch1 \* ex \*\* e)
            # if m != Focus:
            # c2 = make\_divisible(c2, 8) if c2 != no else c2

            args = [c1, c2, \*args[1:]]
            if m in [BottleneckCSP, C3]:
                args.insert(2, n)
                n = 1
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum([ch[x if x < 0 else x + 1] for x in f])
        elif m is Detect:


## 写在最后

**在结束之际，我想重申的是，学习并非如攀登险峻高峰，而是如滴水穿石般的持久累积。尤其当我们步入工作岗位之后，持之以恒的学习变得愈发不易，如同在茫茫大海中独自划舟，稍有松懈便可能被巨浪吞噬。然而，对于我们程序员而言，学习是生存之本，是我们在激烈市场竞争中立于不败之地的关键。一旦停止学习，我们便如同逆水行舟，不进则退，终将被时代的洪流所淘汰。因此，不断汲取新知识，不仅是对自己的提升，更是对自己的一份珍贵投资。让我们不断磨砺自己，与时代共同进步，书写属于我们的辉煌篇章。**


需要完整版PDF学习资源私我