2021-01-05

##本片文章只自己学习使用，文章大部分代码及文字来自于 [link]https://blog.csdn.net/weixin_44791964/article/details/103276106

yolo3的实现思路

1、主题网络Darknet-53的介绍

特点是使用了残差网络Residual，darknet53中的残差卷积就是进行一次3X3、步长为2的卷积，然后保存该卷积layer，再进行一次1X1的卷积和一次3X3的卷积，并把这个结果加上layer作为最后的结果。优点是容易优化，且可以通过一定的增加一定的深度来提高准确率  

另外darknet53的每一个卷积部分使用了特有的DarknetConv2D结构，每一次卷积的时候进行l2正则化，完成卷积后进行BatchNormalization标准化与LeakyReLU。普通的ReLU是将所有的负值都设为零，Leaky ReLU则是给所有负值赋予一个非零斜率。以数学的方式我们可以表示为：

这是一个13* 13的网格图


13，13是指图二中点的个数即图二中有13*13，共169个点
x_offset代表偏移量（y_offset同理），height和width代表偏移后的框架的长和宽，3代表每个点采用三个框来识别，置信度用来判断是否这个框是一个有物体的框。

其实yolo3的基本思路就是将一个图片分为若干个网格点，之后选择每个点用几个框去试探，如果试探到了某个框里有物体，那么就把这个物体给框出来然后说明这个物体是什么。

#附上两个部分的代码
1、 Darknet部分

from functools import wraps
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate, MaxPooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.regularizers import l2
from utils.utils import compose


#--------------------------------------------------#
#   单次卷积（可以用来提高效率）
#--------------------------------------------------#
@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
    darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
    darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
    darknet_conv_kwargs.update(kwargs)
    return Conv2D(*args, **darknet_conv_kwargs)

#---------------------------------------------------#
#   卷积块
#   DarknetConv2D + BatchNormalization + LeakyReLU
#---------------------------------------------------#
def DarknetConv2D_BN_Leaky(*args, **kwargs):
    no_bias_kwargs = {'use_bias': False}
    no_bias_kwargs.update(kwargs)
    return compose( 
        DarknetConv2D(*args, **no_bias_kwargs),
        BatchNormalization(),
        LeakyReLU(alpha=0.1))

#---------------------------------------------------#
#   卷积块
#   DarknetConv2D + BatchNormalization + LeakyReLU
#---------------------------------------------------#
def resblock_body(x, num_filters, num_blocks):
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = DarknetConv2D_BN_Leaky(num_filters//2, (1,1))(x)
        y = DarknetConv2D_BN_Leaky(num_filters, (3,3))(y)
        x = Add()([x,y])
    return x

#---------------------------------------------------#
#   darknet53 的主体部分
#---------------------------------------------------#
def darknet_body(x):
    x = DarknetConv2D_BN_Leaky(32, (3,3))(x)
    x = resblock_body(x, 64, 1)
    x = resblock_body(x, 128, 2)
    x = resblock_body(x, 256, 8)
    feat1 = x
    x = resblock_body(x, 512, 8)
    feat2 = x
    x = resblock_body(x, 1024, 4)
    feat3 = x
    return feat1,feat2,feat3

第二部分

from functools import wraps

import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate, MaxPooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2
from nets.darknet53 import darknet_body
from utils.utils import compose


#--------------------------------------------------#
#   单次卷积
#--------------------------------------------------#
@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
    darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
    darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
    darknet_conv_kwargs.update(kwargs)
    return Conv2D(*args, **darknet_conv_kwargs)

#---------------------------------------------------#
#   卷积块
#   DarknetConv2D + BatchNormalization + LeakyReLU
#---------------------------------------------------#
def DarknetConv2D_BN_Leaky(*args, **kwargs):
    no_bias_kwargs = {'use_bias': False}
    no_bias_kwargs.update(kwargs)
    return compose( 
        DarknetConv2D(*args, **no_bias_kwargs),
        BatchNormalization(),
        LeakyReLU(alpha=0.1))

#---------------------------------------------------#
#   特征层->最后的输出
#---------------------------------------------------#
def make_last_layers(x, num_filters, out_filters):
    # 五次卷积
    x = DarknetConv2D_BN_Leaky(num_filters, (1,1))(x)
    x = DarknetConv2D_BN_Leaky(num_filters*2, (3,3))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (1,1))(x)
    x = DarknetConv2D_BN_Leaky(num_filters*2, (3,3))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (1,1))(x)

    # 将最后的通道数调整为outfilter
    y = DarknetConv2D_BN_Leaky(num_filters*2, (3,3))(x)
    y = DarknetConv2D(out_filters, (1,1))(y)
            
    return x, y

#---------------------------------------------------#
#   特征层->最后的输出
#---------------------------------------------------#
def yolo_body(inputs, num_anchors, num_classes):
    # 生成darknet53的主干模型
    feat1,feat2,feat3 = darknet_body(inputs)
    darknet = Model(inputs, feat3)

    # 第一个特征层
    # y1=(batch_size,13,13,3,85)
    x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))

    x = compose(
            DarknetConv2D_BN_Leaky(256, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,feat2])
    # 第二个特征层
    # y2=(batch_size,26,26,3,85)
    x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))

    x = compose(
            DarknetConv2D_BN_Leaky(128, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,feat1])
    # 第三个特征层
    # y3=(batch_size,52,52,3,85)
    x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))

    return Model(inputs, [y1,y2,y3])

今天的学习就到这了哈哈