tensorflow keras 使用卷积conv2d 池化pooling之后输出的shape

keras和TensorFlow设置卷积层的过程中可以设置padding参数，vaild和same。“valid”代表只进行有效的卷积，对边界数据不处理。“same”代表保留边界处的卷积结果，通常会导致输出shape与输入shape相同.

下面 W为输入大小，S为步长，F为核大小

一、tensorflow 中

1.卷积

在tensorflow中，conv后的shape可按照下边的公式计算

padding VALID

n = (W-F+1)/S 向上取整

padding SAME

n = W/S 向上取整

在valid方式中，dilation_rate为膨胀系数，默认为1，并且一般不设置。网上好多博主找到的官方说明（我没找到在哪）

 If padding == "SAME":
      output_spatial_shape[i] = ceil(input_spatial_shape[i] / strides[i])

    If padding == "VALID":
      output_spatial_shape[i] =
        ceil((input_spatial_shape[i] -
              (spatial_filter_shape[i]-1) * dilation_rate[i])
             / strides[i]).

  Raises:
    ValueError: If input/output depth does not match filter shape, if padding
      is other than "VALID" or "SAME", or if data_format is invalid.

2.池化

padding VALID

n = (W-F+1)/S 向上取整

padding SAME

n = W/S 向上取整
自己可使用一下代码测试

import tensorflow as tf

#自己修改input的维度,和conv2d的padding方式测试
input = tf.Variable(tf.random_normal([1, 5, 5, 3]))
filter = tf.Variable(tf.random_normal([3, 3, 3, 7]))

result = tf.nn.conv2d(input, filter, strides=[1, 2, 2, 1], padding='SAME')
pool_result = tf.nn.max_pool(input, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
with tf.Session() as sess:
    tf.global_variables_initializer().run()
    s = sess.run(result)
    p = sess.run(pool_result)
    print(s.shape)
    print(p.shape)

二、keras中

1.卷积

默认为 valid，默认strides=1，计算同tensorflow
如果设置了相关项，计算同tensorflow

2.池化

默认为 valid，默认strides None
如果只设置一个pool_size，那么N=W/F，same向上取整，valid向下取整

如果设置strides那么按照下边计算
同tensorflow

from keras.models import *
from keras.layers import *
from keras.optimizers import *

input = tf.Variable(tf.random_normal([1,572,572,1]))

conv1 = Conv2D(64,3,activation='relu',padding='same',kernel_initializer='he_normal')(input)
print(conv1.shape)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'glorot_normal')(conv1)
print(conv1.shape)
pool1 = MaxPooling2D(pool_size=(3, 3))(conv1)
print(pool1.shape)

前两次卷积
理论上和自己测试的一样，但要具体情况具体分析吧
比如u-net网络，就没搞懂padding=same，步长为1情况下，conv一次，尺寸减小2是怎么回事。因此怀疑应该是padding=valid，这样572-3+1=570,570-3+1=568才符合图示，但是很多博文以及github上很多代码也是使用same。

def unet(pretrained_weights = None,input_size = (256,256,1)):
    inputs = Input(input_size)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
    merge6 = concatenate([drop4,up6], axis = 3)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    merge7 = concatenate([conv3,up7], axis = 3)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    merge8 = concatenate([conv2,up8], axis = 3)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    merge9 = concatenate([conv1,up9], axis = 3)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)

    model = Model(input = inputs, output = conv10)

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])
    
    #model.summary()

    if(pretrained_weights):
    	model.load_weights(pretrained_weights)

    return model