飞桨-零基础实践深度学习-目标检测心得

飞桨-零基础实践深度学习-目标检测心得

我有幸参加百度的AI课程《零基础实践深度学习》，现在记录 一下第三周课程之目标检测的实践与感悟。

首先，我先用我自己的话来描述一下目标检测。目标检测看作一个任务，我们对任务拆分，可以大致分为图像划分、对众多划分出图像的特征提取、众多特征与标签对比建立损失函数并进行学习。
然后我们来看一下目标检测的官方介绍图。

以上，读者可以对目标检测的工作流建立起大致的概念。

下面我们通过YOLO V3来分别看一下图像特征提取和损失函数的建立。
图像特征提取的网络是Darknet53，也就是说，YOLO-V3算法使用的骨干网络是Darknet53。Darknet53网络的具体结构如图所示，在ImageNet图像分类任务上取得了很好的成绩。在检测任务中，将图中C0后面的平均池化、全连接层和Softmax去掉，保留从输入到C0部分的网络结构，作为检测模型的基础网络结构，也称为骨干网络。YOLO-V3模型会在骨干网络的基础上，再添加检测相关的网络模块。

损失函数的建立是通过特征图与标签建立连接来实现。如下图。建立连接的意思是，对特征图进行卷积，最终输出的通道数与图像的划分方格的大小对应起来，不同的通道一一对应标签上的数据。按图中例子来说，标签的数据在这里是（5+7）*3 = 36.其中5是是否包含目标和坐标，7是类别数，3是图片的通道数。

以上，读者便对目标检测的原理有了一定的概念。下面我们进入代码实践。

Darknet53网络

import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
from paddle.fluid.regularizer import L2Decay

from paddle.fluid.dygraph.nn import Conv2D, BatchNorm
from paddle.fluid.dygraph.base import to_variable

# YOLO-V3骨干网络结构Darknet53的实现代码

class ConvBNLayer(fluid.dygraph.Layer):
    """
    卷积 + 批归一化，BN层之后激活函数默认用leaky_relu
    """
    def __init__(self,
                 ch_in,
                 ch_out,
                 filter_size=3,
                 stride=1,
                 groups=1,
                 padding=0,
                 act="leaky",
                 is_test=True):
        super(ConvBNLayer, self).__init__()

        self.conv = Conv2D(
            num_channels=ch_in,
            num_filters=ch_out,
            filter_size=filter_size,
            stride=stride,
            padding=padding,
            groups=groups,
            param_attr=ParamAttr(
                initializer=fluid.initializer.Normal(0., 0.02)),
            bias_attr=False,
            act=None)

        self.batch_norm = BatchNorm(
            num_channels=ch_out,
            is_test=is_test,
            param_attr=ParamAttr(
                initializer=fluid.initializer.Normal(0., 0.02),
                regularizer=L2Decay(0.)),
            bias_attr=ParamAttr(
                initializer=fluid.initializer.Constant(0.0),
                regularizer=L2Decay(0.)))
        self.act = act

    def forward(self, inputs):
        out = self.conv(inputs)
        out = self.batch_norm(out)
        if self.act == 'leaky':
            out = fluid.layers.leaky_relu(x=out, alpha=0.1)
        return out

class DownSample(fluid.dygraph.Layer):
    """
    下采样，图片尺寸减半，具体实现方式是使用stirde=2的卷积
    """
    def __init__(self,
                 ch_in,
                 ch_out,
                 filter_size=3,
                 stride=2,
                 padding=1,
                 is_test=True):

        super(DownSample, self).__init__()

        self.conv_bn_layer = ConvBNLayer(
            ch_in=ch_in,
            ch_out=ch_out,
            filter_size=filter_size,
            stride=stride,
            padding=padding,
            is_test=is_test)
        self.ch_out = ch_out
    def forward(self, inputs):
        out = self.conv_bn_layer(inputs)
        return out

class BasicBlock(fluid.dygraph.Layer):
    """
    基本残差块的定义，输入x经过两层卷积，然后接第二层卷积的输出和输入x相加
    """
    def __init__(self, ch_in, ch_out, is_test=True):
        super(BasicBlock, self).__init__()

        self.conv1 = ConvBNLayer(
            ch_in=ch_in,
            ch_out=ch_out,
            filter_size=1,
            stride=1,
            padding=0,
            is_test=is_test
            )
        self.conv2 = ConvBNLayer(
            ch_in=ch_out,
            ch_out=ch_out*2,
            filter_size=3,
            stride=1,
            padding=1,
            is_test=is_test
            )
    def forward(self, inputs):
        conv1 = self.conv1(inputs)
        conv2 = self.conv2(conv1)
        out = fluid.layers.elementwise_add(x=inputs, y=conv2, act=None)
        return out

class LayerWarp(fluid.dygraph.Layer):
    """
    添加多层残差块，组成Darknet53网络的一个层级
    """
    def __init__(self, ch_in, ch_out, count, is_test=True):
        super(LayerWarp,self).__init__()

        self.basicblock0 = BasicBlock(ch_in,
            ch_out,
            is_test=is_test)
        self.res_out_list = []
        for i in range(1, count):
            res_out = self.add_sublayer("basic_block_%d" % (i), #使用add_sublayer添加子层
                BasicBlock(ch_out*2,
                    ch_out,
                    is_test=is_test))
            self.res_out_list.append(res_out)

    def forward(self,inputs):
        y = self.basicblock0(inputs)
        for basic_block_i in self.res_out_list:
            y = basic_block_i(y)
        return y

DarkNet_cfg = {53: ([1, 2, 8, 8, 4])}

class DarkNet53_conv_body(fluid.dygraph.Layer):
    def __init__(self,
                 
                 is_test=True):
        super(DarkNet53_conv_body, self).__init__()
        self.stages = DarkNet_cfg[53]
        self.stages = self.stages[0:5]

        # 第一层卷积
        self.conv0 = ConvBNLayer(
            ch_in=3,
            ch_out=32,
            filter_size=3,
            stride=1,
            padding=1,
            is_test=is_test)

        # 下采样，使用stride=2的卷积来实现
        self.downsample0 = DownSample(
            ch_in=32,
            ch_out=32 * 2,
            is_test=is_test)

        # 添加各个层级的实现
        self.darknet53_conv_block_list = []
        self.downsample_list = []
        for i, stage in enumerate(self.stages):
            conv_block = self.add_sublayer(
                "stage_%d" % (i),
                LayerWarp(32*(2**(i+1)),
                32*(2**i),
                stage,
                is_test=is_test))
            self.darknet53_conv_block_list.append(conv_block)
        # 两个层级之间使用DownSample将尺寸减半
        for i in range(len(self.stages) - 1):
            downsample = self.add_sublayer(
                "stage_%d_downsample" % i,
                DownSample(ch_in=32*(2**(i+1)),
                    ch_out=32*(2**(i+2)),
                    is_test=is_test))
            self.downsample_list.append(downsample)

    def forward(self,inputs):
        out = self.conv0(inputs)
        #print("conv1:",out.numpy())
        out = self.downsample0(out)
        #print("dy:",out.numpy())
        blocks = []
        for i, conv_block_i in enumerate(self.darknet53_conv_block_list): #依次将各个层级作用在输入上面
            out = conv_block_i(out)
            blocks.append(out)
            if i < len(self.stages) - 1:
                out = self.downsample_list[i](out)
        return blocks[-1:-4:-1] # 将C0, C1, C2作为返回值

损失函数的建立

# 定义上采样模块
class Upsample(fluid.dygraph.Layer):
    def __init__(self, scale=2):
        super(Upsample,self).__init__()
        self.scale = scale

    def forward(self, inputs):
        # get dynamic upsample output shape
        shape_nchw = fluid.layers.shape(inputs)
        shape_hw = fluid.layers.slice(shape_nchw, axes=[0], starts=[2], ends=[4])
        shape_hw.stop_gradient = True
        in_shape = fluid.layers.cast(shape_hw, dtype='int32')
        out_shape = in_shape * self.scale
        out_shape.stop_gradient = True

        # reisze by actual_shape
        out = fluid.layers.resize_nearest(
            input=inputs, scale=self.scale, actual_shape=out_shape)
        return out

# 定义YOLO-V3模型
class YOLOv3(fluid.dygraph.Layer):
    def __init__(self, num_classes=7, is_train=True):
        super(YOLOv3,self).__init__()

        self.is_train = is_train
        self.num_classes = num_classes
        # 提取图像特征的骨干代码
        self.block = DarkNet53_conv_body(
                                         is_test = not self.is_train)
        self.block_outputs = []
        self.yolo_blocks = []
        self.route_blocks_2 = []
        # 生成3个层级的特征图P0, P1, P2
        for i in range(3):
            # 添加从ci生成ri和ti的模块
            yolo_block = self.add_sublayer(
                "yolo_detecton_block_%d" % (i),
                YoloDetectionBlock(
                                   ch_in=512//(2**i)*2 if i==0 else 512//(2**i)*2 + 512//(2**i),
                                   ch_out = 512//(2**i),
                                   is_test = not self.is_train))
            self.yolo_blocks.append(yolo_block)

            num_filters = 3 * (self.num_classes + 5)

            # 添加从ti生成pi的模块，这是一个Conv2D操作，输出通道数为3 * (num_classes + 5)
            block_out = self.add_sublayer(
                "block_out_%d" % (i),
                Conv2D(num_channels=512//(2**i)*2,
                       num_filters=num_filters,
                       filter_size=1,
                       stride=1,
                       padding=0,
                       act=None,
                       param_attr=ParamAttr(
                           initializer=fluid.initializer.Normal(0., 0.02)),
                       bias_attr=ParamAttr(
                           initializer=fluid.initializer.Constant(0.0),
                           regularizer=L2Decay(0.))))
            self.block_outputs.append(block_out)
            if i < 2:
                # 对ri进行卷积
                route = self.add_sublayer("route2_%d"%i,
                                          ConvBNLayer(ch_in=512//(2**i),
                                                      ch_out=256//(2**i),
                                                      filter_size=1,
                                                      stride=1,
                                                      padding=0,
                                                      is_test=(not self.is_train)))
                self.route_blocks_2.append(route)
            # 将ri放大以便跟c_{i+1}保持同样的尺寸
            self.upsample = Upsample()

    def forward(self, inputs):
        outputs = []
        blocks = self.block(inputs)
        for i, block in enumerate(blocks):
            if i > 0:
                # 将r_{i-1}经过卷积和上采样之后得到特征图，与这一级的ci进行拼接
                block = fluid.layers.concat(input=[route, block], axis=1)
            # 从ci生成ti和ri
            route, tip = self.yolo_blocks[i](block)
            # 从ti生成pi
            block_out = self.block_outputs[i](tip)
            # 将pi放入列表
            outputs.append(block_out)

            if i < 2:
                # 对ri进行卷积调整通道数
                route = self.route_blocks_2[i](route)
                # 对ri进行放大，使其尺寸和c_{i+1}保持一致
                route = self.upsample(route)

        return outputs

    def get_loss(self, outputs, gtbox, gtlabel, gtscore=None,
                 anchors = [10, 13, 16, 30, 33, 23, 30, 61, 62, 45, 59, 119, 116, 90, 156, 198, 373, 326],
                 anchor_masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]],
                 ignore_thresh=0.7,
                 use_label_smooth=False):
        """
        使用fluid.layers.yolov3_loss，直接计算损失函数，过程更简洁，速度也更快
        """
        self.losses = []
        downsample = 32
        for i, out in enumerate(outputs): # 对三个层级分别求损失函数
            anchor_mask_i = anchor_masks[i]
            loss = fluid.layers.yolov3_loss(
                    x=out,  # out是P0, P1, P2中的一个
                    gt_box=gtbox,  # 真实框坐标
                    gt_label=gtlabel,  # 真实框类别
                    gt_score=gtscore,  # 真实框得分，使用mixup训练技巧时需要，不使用该技巧时直接设置为1，形状与gtlabel相同
                    anchors=anchors,   # 锚框尺寸，包含[w0, h0, w1, h1, ..., w8, h8]共9个锚框的尺寸
                    anchor_mask=anchor_mask_i, # 筛选锚框的mask，例如anchor_mask_i=[3, 4, 5]，将anchors中第3、4、5个锚框挑选出来给该层级使用
                    class_num=self.num_classes, # 分类类别数
                    ignore_thresh=ignore_thresh, # 当预测框与真实框IoU > ignore_thresh，标注objectness = -1
                    downsample_ratio=downsample, # 特征图相对于原图缩小的倍数，例如P0是32， P1是16，P2是8
                    use_label_smooth=False)      # 使用label_smooth训练技巧时会用到，这里没用此技巧，直接设置为False
            self.losses.append(fluid.layers.reduce_mean(loss))  #reduce_mean对每张图片求和
            downsample = downsample // 2 # 下一级特征图的缩放倍数会减半
        return sum(self.losses) # 对每个层级求和

以上。

参考：https://aistudio.baidu.com/aistudio/projectdetail/766570