' Concatenate '层要求输入具有匹配的形状，除了concat轴

Question

from keras.layers import Input, Conv3D, MaxPooling3D, concatenate, Conv3DTranspose, BatchNormalization, Dropout,  Lambda
from keras.optimizers import Adam

我的图像的形状是(36,128,128,1)。如何改变u7的形状，以便我可以执行连接?如何修改?

def simple_unet_model(IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS, num_classes):
#Build the model
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS))
#s = Lambda(lambda x: x / 255)(inputs)   #No need for this if we normalize our inputs beforehand
s = inputs
inputs = Input(shape=(36,128,128),name='input')
#Contraction path
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(s)
c1 = Dropout(0.1)(c1)
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c1)
p1 = MaxPooling3D((2, 2, 2))(c1)

c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p1)
c2 = Dropout(0.1)(c2)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c2)
p2 = MaxPooling3D((2, 2, 2))(c2)

c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p2)
c3 = Dropout(0.2)(c3)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c3)
p3 = MaxPooling3D((2, 2, 2))(c3)

c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p3)
c4 = Dropout(0.2)(c4)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c4)
p4 = MaxPooling3D(pool_size=(2, 2, 2))(c4)

c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p4)
c5 = Dropout(0.3)(c5)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c5)

#Expansive path 
u6 = Conv3DTranspose(128, (2, 2, 2), strides=(2, 2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u6)
c6 = Dropout(0.2)(c6)
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c6)

u7 = Conv3DTranspose(64, (2, 2, 2), strides=(2, 2, 2), padding='same')(c6)
u7 = concatenate([u7, c3])
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u7)
c7 = Dropout(0.2)(c7)
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c7)

u8 = Conv3DTranspose(32, (2, 2, 2), strides=(2, 2, 2), padding='same')(c7)
u8 = concatenate([u8, c2])
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u8)
c8 = Dropout(0.1)(c8)
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c8)

u9 = Conv3DTranspose(16, (2, 2, 2), strides=(2, 2, 2), padding='same')(c8)
u9 = concatenate([u9, c1])
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u9)
c9 = Dropout(0.1)(c9)
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c9)

outputs = Conv3D(num_classes, (1, 1, 1), activation='softmax')(c9)

model = Model(inputs=[inputs], outputs=[outputs])
#compile model outside of this function to make it flexible. 
model.summary()

return model

u7 = concatate ([u7, c3])

一个Concatenate层要求输入具有匹配的形状，除了concat轴。得到输入形状:[(None, 32, 32, 8, 64)， (None, 32, 32, 9, 64)]但是如果我的图像的形状是(64,128,128,1)。它工作正常。但是如果我将深度从36增加到64，图像就会改变

建立模型

epochs = 10
model.fit(
X_train,y_train,
validation_data=(X_test,y_test),
epochs=epochs,
shuffle=True,
verbose=2,
callbacks = callbacks_list)

我得到错误ValueError:输入0与层模型不兼容:期望形状=(None, 36, 128, 128, 1)，发现形状=(None, 64, 128, 128, 1)

Answer 1

您可以尝试在axis=1上连接并删除两个Input层中的一个。你只需要一个。下面是一个工作示例(尽管我不确定您的目标是什么):

from keras.layers import Input, Conv3D, MaxPooling3D, concatenate, Conv3DTranspose, BatchNormalization, Dropout,  Lambda
import tensorflow as tf
def simple_unet_model(IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS, num_classes):
#Build the model
kernel_initializer = tf.keras.initializers.GlorotNormal()
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS), name='input')
#s = Lambda(lambda x: x / 255)(inputs)   #No need for this if we normalize our inputs beforehand
s = inputs
#Contraction path
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(s)
c1 = Dropout(0.1)(c1)
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c1)
p1 = MaxPooling3D((2, 2, 2))(c1)

c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p1)
c2 = Dropout(0.1)(c2)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c2)
p2 = MaxPooling3D((2, 2, 2))(c2)

c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p2)
c3 = Dropout(0.2)(c3)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c3)
p3 = MaxPooling3D((2, 2, 2))(c3)

c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p3)
c4 = Dropout(0.2)(c4)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c4)
p4 = MaxPooling3D(pool_size=(2, 2, 2))(c4)

c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p4)
c5 = Dropout(0.3)(c5)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c5)

#Expansive path 
u6 = Conv3DTranspose(128, (2, 2, 2), strides=(2, 2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u6)
c6 = Dropout(0.2)(c6)
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c6)

u7 = Conv3DTranspose(64, (2, 2, 2), strides=(2, 2, 2), padding='same')(c6)
u7 = concatenate([u7, c3], axis=1)
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u7)
c7 = Dropout(0.2)(c7)
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c7)

u8 = Conv3DTranspose(32, (2, 2, 2), strides=(2, 2, 2), padding='same')(c7)
u8 = concatenate([u8, c2], axis=1)
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u8)
c8 = Dropout(0.1)(c8)
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c8)

u9 = Conv3DTranspose(16, (2, 2, 2), strides=(2, 2, 2), padding='same')(c8)
u9 = concatenate([u9, c1], axis=1)
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u9)
c9 = Dropout(0.1)(c9)
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c9)

outputs = Conv3D(num_classes, (1, 1, 1), activation='softmax')(c9)

model = tf.keras.Model(inputs=[inputs], outputs=[outputs])
#compile model outside of this function to make it flexible. 
model.summary()

return model

simple_unet_model(36,128,128, 1, 5)