Yolov5 网络构建代码(2)- Model

Yolov5 网络构建代码(2)- Model_第1张图片

在该目录下存放着yolo.py文件,里面的代码是关于网络构建相关的。

里面其实就写了两个class,一个是Detect,一个是Model

Model

首先我们看先看__init__初始化方法

 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, 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('')

一开始是接受的了4个数据  cfg='yolov5s.yaml', ch=3, nc=None, anchors=None

cfg:网络架构配置文件

ch:输入通道数,默认为3

nc:总类别数

anchors:先验框参数。

然后是判断输入的cfg(网络架构文件)是否为字典。一般都不是字典,直接进入else,打开yaml文件,转换成字典格式:

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, errors='ignore') as f:
        self.yaml = yaml.safe_load(f)  # model dict

 

转换为字典以后,就可以进行模型定义了:他这里是通过parse_model来进行解析和建立模型的。parse_model的类也是在yolo.py文件下的方法。到这一步为止,我们的yolo模型的网络架构就已经全部搭建完成了,可以在这个地方打个断电,去看self.model的值,就可以看到整体的网络架构了。

# 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)
Yolov5 网络构建代码(2)- Model_第2张图片 self.model断点检查的部分值

 

当建立完网络后,要确定每一个维度的步长(其实这个步长也可以理解为,下采样的倍率)和先验框的参数。先 m = self.model[-1] 将Detect模块的参数取出,判断是否为真,然后,计算步长和先验框的参数。这里要注意的是这里的先验框的大小是按照维度,等比例下采样的,你这里看到的m.anchors的值应该是1.xx的大小,是已经进过下采样的值了。

这里的 check_anchor_order(m)  是检查anchor的顺序和strides的顺序是否一致。

self._initialize_biases()  初始化偏置

initialize_weights(self)   初始化权重

# 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('')

 然后就是forward函数

fforward函数

 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

这边做了一个分支,是否为推理模式,如果是则进推理的forward(_forward_augment)。如果不是,则进训练的forward(_forward_once)

推理的forward(_forward_augment)

 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
        return torch.cat(y, 1), None  # augmented inference, train

这里的代码是在推理的时候做数据增强TTA,提升推理的效果。

训练的forward(_forward_once)

 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    把图像进过网络进行处理
            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

对模型每一层进行迭代。

这里中间有一个判断 

if profile:
                self._profile_one_layer(m, x, dt)

这个是调用了model里面的_profile_one_layer这个方法主要作用是使用thop.profile模块对模型进行评估。

 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")

之后就是一些功能函数

1. _initialize_biases  初始化偏置函数

    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)

用于初始化Detect的偏置。

2.fuse   将Conv2d + BN 进行融合。

    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

在融合的时候主要是调用了 fuse_conv_and_bn 这个函数

 parse_model   解析网络配置文件和构建模型

def parse_model(d, ch):  # model_dict, input_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 NameError:
                pass
        
        #  深度控制代码
        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('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n_, np, t, args))  # 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)

这个函数接受了两个文件,一个是d,一个是ch

d就是model文件解析的yaml字典,ch是输入的通道数。

他通过解析出来的字典文件,去构建模型。

 n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain    控制了模型的深度。

 if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)    控制了模型的宽度,也就是卷积核的个数。

到此为止,模型已经全部搭建完毕。接下来就是一些功能函数,比如在dataset文件下的letterbox矩形推理功能,数据集载入功能等。之后再继续看源码。

你可能感兴趣的:(YOLO,深度学习,人工智能)