Python 当LSTM与CNN组合时，Keras图断开连接
其想法是在两个BILSTM隐藏状态的余弦相似矩阵上训练CNN。 我试图使以下代码正常工作，但未能给出错误消息：Python 当LSTM与CNN组合时，Keras图断开连接,python,tensorflow,keras,lstm,Python,Tensorflow,Keras,Lstm,其想法是在两个BILSTM隐藏状态的余弦相似矩阵上训练CNN。 我试图使以下代码正常工作，但未能给出错误消息： Graph disconnected: cannot obtain value for tensor Tensor("bidirectional_4/concat:0", shape=(?, ?, 100), dtype=float32) at layer "input_11". The following previous layers were accessed without i
Graph disconnected: cannot obtain value for tensor
Tensor("bidirectional_4/concat:0", shape=(?, ?, 100), dtype=float32)
at layer "input_11". The following previous layers were accessed without issue: []
def train_model(self, sentences_pair, is_similar,
embedding_meta_data_skt, embedding_meta_data_tib ,
model_save_directory='./'):
tokenizer_skt = embedding_meta_data_skt['tokenizer']
tokenizer_tib = embedding_meta_data_tib['tokenizer']
embedding_matrix_skt = embedding_meta_data_skt['embedding_matrix']
embedding_matrix_tib = embedding_meta_data_tib['embedding_matrix']
train_data_x1, train_data_x2, train_labels, leaks_train, \
val_data_x1, val_data_x2, val_labels, leaks_val = create_train_dev_set(tokenizer_skt, sentences_pair,
is_similar, self.max_sequence_length,
self.validation_split_ratio)
nb_words_skt = len(tokenizer_skt.word_index) + 1
nb_words_tib = len(tokenizer_tib.word_index) + 1
# Creating word embedding layer
embedding_layer_skt = Embedding(nb_words_skt, self.embedding_dim, weights=[embedding_matrix_skt],
input_length=self.max_sequence_length, trainable=False)
embedding_layer_tib = Embedding(nb_words_tib, self.embedding_dim, weights=[embedding_matrix_tib],
input_length=self.max_sequence_length, trainable=False)
# Creating LSTM Encoder
lstm_layer = Bidirectional(LSTM(self.number_lstm_units, dropout=self.rate_drop_lstm, recurrent_dropout=self.rate_drop_lstm,return_sequences=True))
# Creating LSTM Encoder layer for First Sentence
sequence_1_input = Input(shape=(self.max_sequence_length,), dtype='int32')
embedded_sequences_1 = embedding_layer_skt(sequence_1_input)
skt_lstm = lstm_layer(embedded_sequences_1)
# Creating LSTM Encoder layer for Second Sentence
sequence_2_input = Input(shape=(self.max_sequence_length,), dtype='int32')
embedded_sequences_2 = embedding_layer_tib(sequence_2_input)
tib_lstm = lstm_layer(embedded_sequences_2)
A_input = keras.Input(tensor=skt_lstm)
B_input = keras.Input(tensor=tib_lstm)
dist_output = keras.layers.Lambda(pairwise_cosine_sim)([skt_lstm,tib_lstm,A_input,B_input])
dist_output = Reshape((40,40,1))(dist_output)
input_shape = (40,40,1)
cnn_model = Conv2D(128, (2, 2), input_shape=input_shape)(dist_output)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(164, (2, 2))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(192,(3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(192, (3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(128, (3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = MaxPooling2D(pool_size=(2,2))(cnn_model)
cnn_model = Dropout(0.40)(cnn_model)
cnn_model = Flatten()(cnn_model)
# Fully connected layer
cnn_model = Dense(256)(cnn_model)
cnn_model = BatchNormalization()(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Dropout(0.5)(cnn_model)
cnn_model = Dense(num_classes)(cnn_model)
preds = Dense(1, activation='sigmoid')(cnn_model)
model = Model(inputs=[sequence_1_input, sequence_2_input], outputs=preds)
model.compile(loss=keras.losses.binary_crossentropy,
optimizer=keras.optimizers.Adam(lr=learning_rate),
metrics=['accuracy'])
#model.compile(loss='binary_crossentropy', optimizer='nadam', metrics=['acc'])
filepath="skt-tib-bs" + str(batch_size) + "-" + "{epoch:02d}-{val_acc:.2f}.hdf5"
checkpoint = ModelCheckpoint('skt-tib.h5', monitor='val_acc')
callbacks_list = [checkpoint]
model.fit([train_data_x1, train_data_x2, leaks_train], train_labels,validation_data=([val_data_x1, val_data_x2, leaks_val], val_labels),
batch_size=batch_size,
epochs=epochs,
verbose=1,
class_weight = class_weight,
callbacks = callbacks_list)
score = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model.save(file_name)
def l2_norm(x, axis=None):
square_sum = K.sum(K.square(x), axis=axis, keepdims=True)
norm = K.sqrt(K.maximum(square_sum, K.epsilon()))
return norm
def pairwise_cosine_sim(A_B):
A,B,A_tensor,B_tensor = A_B
A_mag = l2_norm(A, axis=2)
B_mag = l2_norm(B, axis=2)
num = K.batch_dot(A_tensor, K.permute_dimensions(B_tensor, (0,2,1)))
den = (A_mag * K.permute_dimensions(B_mag, (0,2,1)))
dist_mat = num / den
return dist_mat
def train_model(self, sentences_pair, is_similar,
embedding_meta_data_skt, embedding_meta_data_tib ,
model_save_directory='./'):
tokenizer_skt = embedding_meta_data_skt['tokenizer']
tokenizer_tib = embedding_meta_data_tib['tokenizer']
embedding_matrix_skt = embedding_meta_data_skt['embedding_matrix']
embedding_matrix_tib = embedding_meta_data_tib['embedding_matrix']
train_data_x1, train_data_x2, train_labels, leaks_train, \
val_data_x1, val_data_x2, val_labels, leaks_val = create_train_dev_set(tokenizer_skt, sentences_pair,
is_similar, self.max_sequence_length,
self.validation_split_ratio)
nb_words_skt = len(tokenizer_skt.word_index) + 1
nb_words_tib = len(tokenizer_tib.word_index) + 1
# Creating word embedding layer
embedding_layer_skt = Embedding(nb_words_skt, self.embedding_dim, weights=[embedding_matrix_skt],
input_length=self.max_sequence_length, trainable=False)
embedding_layer_tib = Embedding(nb_words_tib, self.embedding_dim, weights=[embedding_matrix_tib],
input_length=self.max_sequence_length, trainable=False)
# Creating LSTM Encoder
lstm_layer = Bidirectional(LSTM(self.number_lstm_units, dropout=self.rate_drop_lstm, recurrent_dropout=self.rate_drop_lstm,return_sequences=True))
# Creating LSTM Encoder layer for First Sentence
sequence_1_input = Input(shape=(self.max_sequence_length,), dtype='int32')
embedded_sequences_1 = embedding_layer_skt(sequence_1_input)
skt_lstm = lstm_layer(embedded_sequences_1)
# Creating LSTM Encoder layer for Second Sentence
sequence_2_input = Input(shape=(self.max_sequence_length,), dtype='int32')
embedded_sequences_2 = embedding_layer_tib(sequence_2_input)
tib_lstm = lstm_layer(embedded_sequences_2)
A_input = keras.Input(tensor=skt_lstm)
B_input = keras.Input(tensor=tib_lstm)
dist_output = keras.layers.Lambda(pairwise_cosine_sim)([skt_lstm,tib_lstm,A_input,B_input])
dist_output = Reshape((40,40,1))(dist_output)
input_shape = (40,40,1)
cnn_model = Conv2D(128, (2, 2), input_shape=input_shape)(dist_output)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(164, (2, 2))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(192,(3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(192, (3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Conv2D(128, (3, 3))(cnn_model)
cnn_model = BatchNormalization(axis=-1)(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = MaxPooling2D(pool_size=(2,2))(cnn_model)
cnn_model = Dropout(0.40)(cnn_model)
cnn_model = Flatten()(cnn_model)
# Fully connected layer
cnn_model = Dense(256)(cnn_model)
cnn_model = BatchNormalization()(cnn_model)
cnn_model = Activation('relu')(cnn_model)
cnn_model = Dropout(0.5)(cnn_model)
cnn_model = Dense(num_classes)(cnn_model)
preds = Dense(1, activation='sigmoid')(cnn_model)
model = Model(inputs=[sequence_1_input, sequence_2_input], outputs=preds)
model.compile(loss=keras.losses.binary_crossentropy,
optimizer=keras.optimizers.Adam(lr=learning_rate),
metrics=['accuracy'])
#model.compile(loss='binary_crossentropy', optimizer='nadam', metrics=['acc'])
filepath="skt-tib-bs" + str(batch_size) + "-" + "{epoch:02d}-{val_acc:.2f}.hdf5"
checkpoint = ModelCheckpoint('skt-tib.h5', monitor='val_acc')
callbacks_list = [checkpoint]
model.fit([train_data_x1, train_data_x2, leaks_train], train_labels,validation_data=([val_data_x1, val_data_x2, leaks_val], val_labels),
batch_size=batch_size,
epochs=epochs,
verbose=1,
class_weight = class_weight,
callbacks = callbacks_list)
score = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model.save(file_name)
def l2_norm(x, axis=None):
square_sum = K.sum(K.square(x), axis=axis, keepdims=True)
norm = K.sqrt(K.maximum(square_sum, K.epsilon()))
return norm
def pairwise_cosine_sim(A_B):
A,B,A_tensor,B_tensor = A_B
A_mag = l2_norm(A, axis=2)
B_mag = l2_norm(B, axis=2)
num = K.batch_dot(A_tensor, K.permute_dimensions(B_tensor, (0,2,1)))
den = (A_mag * K.permute_dimensions(B_mag, (0,2,1)))
dist_mat = num / den
return dist_mat
我已经试了几个小时来修理它，但似乎没有用。有些地方输入和输出没有连接，但我就是不知道问题出在哪里。对此有何建议？要么完全删除
A_输入B_输入skt_lstmtib_lstm模型时将它们作为模型的输入传递，因为它们实际上是输入层：
model = Model(inputs=[sequence_1_input, sequence_2_input, A_input, B_input], outputs=preds)
但是，在调用fit
方法时，不需要为它们传递任何相应的数组，因为它们将使用相应的张量skt_lstm
和tib_lstm
（即，它们将充当这些张量的包装器）。模型有两个输入层，即输入=[sequence_1_input，sequence_2_input]
但您给它三个输入数组，即[train_data_x1，train_data_x2，leaks_train]
。为什么会这样？感谢您的提示，这是早期实验的遗留问题，删除此参数不会改变错误。请同时包含成对余弦sim
函数的定义。它现在已包含在内！我不明白您为什么将a\u input
和B\u input
定义为输入层如果它们不是最初的输入层？只需直接使用skt_lstm
和tib_lstm
。这就成功了，非常感谢！我接受了你的第一个建议。