Python 属性错误：'；非类型'；对象没有属性'_入站节点'；尝试添加多个keras密集层时

输入为3个独立通道，共1000个功能。我试图让每个通道通过一个独立的NN路径，然后将它们连接到一个平面层中。然后在展平层上应用FCN进行二元分类。 我尝试将多个致密层添加到一起，如下所示：

def tst_1（）：

但我有一个错误：

/usr/local/lib/python2.7/dist-packages/keras/engine/network.pyc in build\u map（张量、完成的节点、进行中的节点、层、节点索引、张量索引） 1310值错误：如果检测到循环。 1311 """ ->1312节点=层。\入站\节点[节点\索引] 1313 1314#防止循环

AttributeError:“非类型”对象没有属性“\u入站节点”

---

问题在于，使用

输入[0，：，1]

拆分输入数据不是作为keras层完成的

您需要创建一个层才能完成此操作

以下代码：

from keras import layers
from keras.layers import Input, Add, Dense,Dropout, Lambda, Concatenate
from keras.layers import Flatten
from keras.optimizers import Adam
from keras.models import Model
import keras.backend as K


def tst_1(): 

    num_channels = 3
    inputs = Input(shape=(num_channels, 1000, 1))

    branch_outputs = []
    for i in range(num_channels):
        # Slicing the ith channel:
        out = Lambda(lambda x: x[:, i, :, :], name = "Lambda_" + str(i))(inputs)

        # Setting up your per-channel layers (replace with actual sub-models):
        out = Dense(224, activation='relu', name = "Dense_224_" + str(i))(out)
        out = Dense(112, activation='relu', name = "Dense_112_" + str(i))(out)
        out = Dense(56, activation='relu', name = "Dense_56_" + str(i))(out)
        branch_outputs.append(out)

    # Concatenating together the per-channel results:
    out = Concatenate()(branch_outputs)


    dense1 = Dense(224, activation='relu')(out)
    drop1 = Dropout(0.5)(dense1)
    dense2 = Dense(112, activation='relu')(drop1)
    drop2 = Dropout(0.5)(dense2)
    dense3 = Dense(32, activation='relu')(drop2)
    densef = Dense(1, activation='sigmoid')(dense3)

    model = Model(inputs = inputs, outputs = densef)

    return model

Net = tst_1()
Net.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])

Net.summary()

正确创建了所需的网络

---

问题在于，使用

输入[0，：，1]

拆分输入数据不是作为keras层来完成的

您需要创建一个层才能完成此操作

以下代码：

from keras import layers
from keras.layers import Input, Add, Dense,Dropout, Lambda, Concatenate
from keras.layers import Flatten
from keras.optimizers import Adam
from keras.models import Model
import keras.backend as K


def tst_1(): 

    num_channels = 3
    inputs = Input(shape=(num_channels, 1000, 1))

    branch_outputs = []
    for i in range(num_channels):
        # Slicing the ith channel:
        out = Lambda(lambda x: x[:, i, :, :], name = "Lambda_" + str(i))(inputs)

        # Setting up your per-channel layers (replace with actual sub-models):
        out = Dense(224, activation='relu', name = "Dense_224_" + str(i))(out)
        out = Dense(112, activation='relu', name = "Dense_112_" + str(i))(out)
        out = Dense(56, activation='relu', name = "Dense_56_" + str(i))(out)
        branch_outputs.append(out)

    # Concatenating together the per-channel results:
    out = Concatenate()(branch_outputs)


    dense1 = Dense(224, activation='relu')(out)
    drop1 = Dropout(0.5)(dense1)
    dense2 = Dense(112, activation='relu')(drop1)
    drop2 = Dropout(0.5)(dense2)
    dense3 = Dense(32, activation='relu')(drop2)
    densef = Dense(1, activation='sigmoid')(dense3)

    model = Model(inputs = inputs, outputs = densef)

    return model

Net = tst_1()
Net.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])

Net.summary()

正确创建了所需的网络

谢谢@CAta.RAy

我是这样解决的：

import numpy as np
from keras import layers
from keras.layers import Input, Add, Dense,Dropout, Lambda
from keras.layers import Flatten
from keras.optimizers import Adam
from keras.models import Model
import keras.backend as K




def tst_1(): 
    inputs = Input((3, 1000))

    x1 = Lambda(lambda x:x[:,0])(inputs)
    dense10 = Dense(224, activation='relu')(x1)
    dense11 = Dense(112, activation='relu')(dense10)
    dense12 = Dense(56, activation='relu')(dense11)

    x2 = Lambda(lambda x:x[:,1])(inputs)
    dense20 = Dense(224, activation='relu')(x2)
    dense21 = Dense(112, activation='relu')(dense20)
    dense22 = Dense(56, activation='relu')(dense21)

    x3 = Lambda(lambda x:x[:,2])(inputs)
    dense30 = Dense(224, activation='relu')(x3)
    dense31 = Dense(112, activation='relu')(dense30)
    dense32 = Dense(56, activation='relu')(dense31)

    flat = Add()([dense12, dense22, dense32])

    dense1 = Dense(224, activation='relu')(flat)
    drop1 = Dropout(0.5)(dense1)
    dense2 = Dense(112, activation='relu')(drop1)
    drop2 = Dropout(0.5)(dense2)
    dense3 = Dense(32, activation='relu')(drop2)
    densef = Dense(1, activation='sigmoid')(dense3)

    model = Model(inputs = inputs, outputs = densef)

    return model

Net = tst_1()
Net.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])

Net.summary()

感谢@CAta.RAy

我是这样解决的：

import numpy as np
from keras import layers
from keras.layers import Input, Add, Dense,Dropout, Lambda
from keras.layers import Flatten
from keras.optimizers import Adam
from keras.models import Model
import keras.backend as K




def tst_1(): 
    inputs = Input((3, 1000))

    x1 = Lambda(lambda x:x[:,0])(inputs)
    dense10 = Dense(224, activation='relu')(x1)
    dense11 = Dense(112, activation='relu')(dense10)
    dense12 = Dense(56, activation='relu')(dense11)

    x2 = Lambda(lambda x:x[:,1])(inputs)
    dense20 = Dense(224, activation='relu')(x2)
    dense21 = Dense(112, activation='relu')(dense20)
    dense22 = Dense(56, activation='relu')(dense21)

    x3 = Lambda(lambda x:x[:,2])(inputs)
    dense30 = Dense(224, activation='relu')(x3)
    dense31 = Dense(112, activation='relu')(dense30)
    dense32 = Dense(56, activation='relu')(dense31)

    flat = Add()([dense12, dense22, dense32])

    dense1 = Dense(224, activation='relu')(flat)
    drop1 = Dropout(0.5)(dense1)
    dense2 = Dense(112, activation='relu')(drop1)
    drop2 = Dropout(0.5)(dense2)
    dense3 = Dense(32, activation='relu')(drop2)
    densef = Dense(1, activation='sigmoid')(dense3)

    model = Model(inputs = inputs, outputs = densef)

    return model

Net = tst_1()
Net.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])

Net.summary()

---

您应该添加更多信息：例如，您试图完成什么，数据集的性质，预处理…model.summaty的输出也会有用。输入是3个独立的通道，共1000个观测值。我试图通过一个独立的NN路径传递每个通道，然后将它们连接到一个平面层中。然后应用FCN在二元分类的扁平化层上。那么…为什么要添加而不是连接？扁平化的大小将非常不同。我应用了连接，但我得到了相同的错误。我想添加（）这里做的事情与输入是1D张量相同。你应该添加更多信息：例如，你想完成什么，数据集的性质，预处理…model.summaty的输出也会有用。输入是3个独立的通道，共1000个观测值。我试图通过一个独立的NN路径传递每个通道，然后将它们连接到一个平面层。然后在平面层上应用FCN进行二进制分类。然后…为什么要添加而不是连接？平面的大小将非常不同。我应用了连接，但我得到了相同的错误。我猜Add（）在这里做同样的事情，因为输入是1D张量。谢谢你的回答。但是裁剪函数的输出是（3,1），而它应该是（1000,1）。我从你的回答中得到了想法，并用以下方式解决：@samuha修改了代码以允许你需要的功能。谢谢你的回答。但是裁剪函数的输出是（3,1），而它应该是（1000,1）。我从你的回答中得到了这个想法，并通过以下方式解决：@Sam_Ha修改了代码，以允许使用你需要的功能。