Press "Enter" to skip to content

TensorFlow之keras.layers.Conv2D( )

keras.layers.Conv2D( ) 函数参数

 

    def __init__(self, filters,
                 kernel_size,
                 strides=(1, 1),
                 padding='valid',
                 data_format=None,
                 dilation_rate=(1, 1),
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):

 

参数:

 

filters卷积核个数的变化,filters 影响的是最后输入结果的的第三个维度的变化,例如,输入的维度是 (600, 600, 3 ), filters 的个数是 64,转变后的维度是 (600, 600, 64 )

 

>>> from keras.layers import (Input, Reshape)
>>> input = Input(shape=(600, 600, 3))
>>> x = Conv2D(64, (1, 1), strides=(1, 1), name='conv1')(input)
>>> x
<tf.Tensor 'conv1_1/BiasAdd:0' shape=(?, 600, 600, 64) dtype=float32>

 

kernel_size 参数 表示卷积核的大小,可以直接写一个数,影响的是输出结果前两个数据的维度,例如,(600, 600, 3)=> ( 599, 599 , 64)

 

>>> from keras.layers import (Input, Conv2D)
>>> input = Input(shape=(600, 600, 3))
>>> Conv2D(64, (2, 2), strides=(1, 1), name='conv1')(input)
<tf.Tensor 'conv1/BiasAdd:0' shape=(?, 599, 599, 64) dtype=float32>

 

直接写 2 也是可以的

 

>>> from keras.layers import (Input, Conv2D)
>>> input = Input(shape=(600, 600, 3))
>>> Conv2D(64, 2, strides=(1, 1), name='conv1')(input)
<tf.Tensor 'conv1_2/BiasAdd:0' shape=(?, 599, 599, 64) dtype=float32>

 

strides 步长 同样会影响输出的前两个维度,例如,(600, 600, 3)=> ( 300, 300 , 64),值得注意的是,括号里的数据可以不一致,分别控制横坐标和纵坐标,这里步长的计算公式为:

 

>>> from keras.layers import (Input, Conv2D)
>>> input = Input(shape=(600, 600, 3))
>>> Conv2D(64, 1, strides=(2, 2), name='conv1')(input)
<tf.Tensor 'conv1_4/BiasAdd:0' shape=(?, 300, 300, 64) dtype=float32>

 

padding 是否对周围进行填充,“same” 即使通过 kernel_size 缩小了维度 ,但是四周会填充 0,保持原先的维度;“valid”表示存储不为0的有效信息。多个对比效果如下:

 

>>> Conv2D(64, 1, strides=(2, 2), padding="same", name='conv1')(input)
<tf.Tensor 'conv1_6/BiasAdd:0' shape=(?, 300, 300, 64) dtype=float32>
>>> Conv2D(64, 3, strides=(2, 2), padding="same", name='conv1')(input)
<tf.Tensor 'conv1_7/BiasAdd:0' shape=(?, 300, 300, 64) dtype=float32>
>>> Conv2D(64, 3, strides=(1, 1), padding="same", name='conv1')(input)
<tf.Tensor 'conv1_8/BiasAdd:0' shape=(?, 600, 600, 64) dtype=float32>
>>> Conv2D(64, 3, strides=(1, 1), padding="valid", name='conv1')(input)
<tf.Tensor 'conv1_9/BiasAdd:0' shape=(?, 598, 598, 64) dtype=float32>

 

通过这种最简单的方式,可以观察 ResNet50 的组成结构

 

 

Conv Block 的架构:

 

def conv_block(input_tensor, kernel_size, filters, stage, block, strides):
    filters1, filters2, filters3 = filters  # filters1 64, filters3 256  将数值传入到filters。。。中
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    x = Conv2D(filters1, (1, 1), strides=strides, name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters2, kernel_size, padding='same', name=conv_name_base + '2b')(x)
    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(name=bn_name_base + '2c')(x)
    shortcut = Conv2D(filters3, (1, 1), strides=strides, name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(name=bn_name_base + '1')(shortcut)
    x = layers.add([x, shortcut])
    x = Activation("relu")(x)
    return x

 

Identity Block 的架构:

 

 

def identity_block(input_tensor, kernel_size, filters, stage, block):
    filters1, filters2, filters3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters2, kernel_size, padding='same', name=conv_name_base + '2b')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2c')(x)
    x = layers.add([x, input_tensor])
    x = Activation('relu')(x)
    return x

 

附上理论链接 Resnet-50网络结构详解  https://www.cnblogs.com/qianchaomoon/p/12315906.html

Be First to Comment

发表回复

您的电子邮箱地址不会被公开。 必填项已用*标注