PyTorch-YOLOV3源码解读（网络结构）

系列文章目录

1. 数据集加载和预处理
2. 网络结构
3. loss计算

---

---

前言

源代码连接https://github.com/eriklindernoren/PyTorch-YOLOv3
当前代码用到的数据集为coco2014，这里提供官网地址https://cocodataset.org/

---

构建网络模型models.py

代码中构建模型的方法是通过读取config/yolov3.cfg的配置文件，进行搭建的
这里可以通过Netron查看网络结构，由于网络很长，这里只截取了部分结构。

yolov3.cfg中每个层次结构开头对会有[…]来进行说明，当前属于什么网络层次，和一些必要的参数。

[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=16
subdivisions=1
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

# Downsample

[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky.......

这里我们先看utils/parse_config.py中的parse_model_config函数, 内容很简单就是通过读取yolov3.cfg中的每一行网络结构，来判断参数属于哪一层，以字典的形式保存在module_defs数组中

def parse_model_config(path):
    """Parses the yolo-v3 layer configuration file and returns module definitions"""
    file = open(path, 'r')		# 读取文件
    lines = file.read().split('\n')	# 读取每一行
    lines = [x for x in lines if x and not x.startswith('#')]	 # 去除文件中的注释内容
    lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
    module_defs = []
    for line in lines:
        if line.startswith('['): # This marks the start of a new block  代表一个新的网络块
            module_defs.append({})
            module_defs[-1]['type'] = line[1:-1].rstrip()   # '[]'中的内容
            if module_defs[-1]['type'] == 'convolutional':
                module_defs[-1]['batch_normalize'] = 0
        else:
            key, value = line.split("=")
            value = value.strip()
            module_defs[-1][key.rstrip()] = value.strip()

    return module_defs

上面的module_defs在传入下面的函数，用来真正的创建网络模型

def create_modules(module_defs):
    """
    Constructs module list of layer blocks from module configuration in module_defs
    """
    hyperparams = module_defs.pop(0)
    output_filters = [int(hyperparams["channels"])] # 图像的输出通道数 3
    module_list = nn.ModuleList()
    for module_i, module_def in enumerate(module_defs):
        modules = nn.Sequential()

        if module_def["type"] == "convolutional":
            bn = int(module_def["batch_normalize"])
            filters = int(module_def["filters"])
            kernel_size = int(module_def["size"])
            pad = (kernel_size - 1) // 2
            modules.add_module(
                f"conv_{module_i}",
                nn.Conv2d(
                    in_channels=output_filters[-1],
                    out_channels=filters,
                    kernel_size=kernel_size,
                    stride=int(module_def["stride"]),
                    padding=pad,
                    bias=not bn,
                ),
            )
            if bn:
                modules.add_module(f"batch_norm_{module_i}", nn.BatchNorm2d(filters, momentum=0.9, eps=1e-5))
            if module_def["activation"] == "leaky":
                modules.add_module(f"leaky_{module_i}", nn.LeakyReLU(0.1))

        elif module_def["type"] == "maxpool":
            kernel_size = int(module_def["size"])
            stride = int(module_def["stride"])
            if kernel_size == 2 and stride == 1:
                modules.add_module(f"_debug_padding_{module_i}", nn.ZeroPad2d((0, 1, 0, 1)))
            maxpool = nn.MaxPool2d(kernel_size=kernel_size, stride=stride, padding=int((kernel_size - 1) // 2))
            modules.add_module(f"maxpool_{module_i}", maxpool)

        elif module_def["type"] == "upsample":
            upsample = Upsample(scale_factor=int(module_def["stride"]), mode="nearest")
            modules.add_module(f"upsample_{module_i}", upsample)

        elif module_def["type"] == "route":
            layers = [int(x) for x in module_def["layers"].split(",")]
            filters = sum([output_filters[1:][i] for i in layers])  # 两个输出channels相加
            modules.add_module(f"route_{module_i}", EmptyLayer())

        elif module_def["type"] == "shortcut":
            filters = output_filters[1:][int(module_def["from"])]
            modules.add_module(f"shortcut_{module_i}", EmptyLayer())

        elif module_def["type"] == "yolo":
            anchor_idxs = [int(x) for x in module_def["mask"].split(",")]
            # Extract anchors
            anchors = [int(x) for x in module_def["anchors"].split(",")]
            anchors = [(anchors[i], anchors[i + 1]) for i in range(0, len(anchors), 2)]
            anchors = [anchors[i] for i in anchor_idxs]
            num_classes = int(module_def["classes"])
            img_size = int(hyperparams["height"])
            # Define detection layer
            yolo_layer = YOLOLayer(anchors, num_classes, img_size)
            modules.add_module(f"yolo_{module_i}", yolo_layer)
        # Register module list and number of output filters
        module_list.append(modules)
        output_filters.append(filters)

    return hyperparams, module_list

#上采样层
class Upsample(nn.Module):
    """ nn.Upsample is deprecated """

    def __init__(self, scale_factor, mode="nearest"):
        super(Upsample, self).__init__()
        self.scale_factor = scale_factor
        self.mode = mode

    def forward(self, x):
        x = F.interpolate(x, scale_factor=self.scale_factor, mode=self.mode)    # 线性插值进行上采样
        return x

# route和shortcut层，这里不做任何操作，因为rout和shortcut层实际并不存在
class EmptyLayer(nn.Module):
    """Placeholder for 'route' and 'shortcut' layers"""

    def __init__(self):
        super(EmptyLayer, self).__init__()

Darknet类用来读取数据，进行正向传播计算

class Darknet(nn.Module):
    """YOLOv3 object detection model"""

    def __init__(self, config_path, img_size=416):
        super(Darknet, self).__init__()
        self.module_defs = parse_model_config(config_path)  # 解析网络配置文件， 返回网络定义的结构
        self.hyperparams, self.module_list = create_modules(self.module_defs)
        self.yolo_layers = [layer[0] for layer in self.module_list if hasattr(layer[0], "metrics")]     # yolo 多尺度检测层
        self.img_size = img_size
        self.seen = 0
        self.header_info = np.array([0, 0, 0, self.seen, 0], dtype=np.int32)

    def forward(self, x, targets=None):
        img_dim = x.shape[2]
        loss = 0
        layer_outputs, yolo_outputs = [], []
        for i, (module_def, module) in enumerate(zip(self.module_defs, self.module_list)):
            if module_def["type"] in ["convolutional", "upsample", "maxpool"]:
                x = module(x)
            elif module_def["type"] == "route":
                x = torch.cat([layer_outputs[int(layer_i)] for layer_i in module_def["layers"].split(",")], 1)
            elif module_def["type"] == "shortcut":
                layer_i = int(module_def["from"])
                x = layer_outputs[-1] + layer_outputs[layer_i]  # 残差块输入加输出
            elif module_def["type"] == "yolo":
                x, layer_loss = module[0](x, targets, img_dim)
                loss += layer_loss
                yolo_outputs.append(x)
            layer_outputs.append(x)
        yolo_outputs = to_cpu(torch.cat(yolo_outputs, 1))
        return yolo_outputs if targets is None else (loss, yolo_outputs)