获取在softmax层之前的CNN的最后一层中获得的向量 [英] Getting vector obtained in the last layer of CNN before softmax layer

问题描述

我正在尝试通过使用CNN编码输入来实现系统.在CNN之后，我需要获取一个向量并将其用于另一种深度学习方法中.

I am trying to implement a system by encoding inputs using CNN. After CNN, I need to get a vector and use it in another deep learning method.

  def get_input_representation(self):
    # get word vectors from embedding
    inputs = tf.nn.embedding_lookup(self.embeddings, self.input_placeholder)


    sequence_length = inputs.shape[1] # 56
    vocabulary_size = 160 # 18765
    embedding_dim = 256
    filter_sizes = [3,4,5]
    num_filters = 3
    drop = 0.5

    epochs = 10
    batch_size = 30

    # this returns a tensor
    print("Creating Model...")
    inputs = Input(shape=(sequence_length,), dtype='int32')
    embedding = Embedding(input_dim=vocabulary_size, output_dim=embedding_dim, input_length=sequence_length)(inputs)
    reshape = Reshape((sequence_length,embedding_dim,1))(embedding)

    conv_0 = Conv2D(num_filters, kernel_size=(filter_sizes[0], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
    conv_1 = Conv2D(num_filters, kernel_size=(filter_sizes[1], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
    conv_2 = Conv2D(num_filters, kernel_size=(filter_sizes[2], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)

    maxpool_0 = MaxPool2D(pool_size=(sequence_length - filter_sizes[0] + 1, 1), strides=(1,1), padding='valid')(conv_0)
    maxpool_1 = MaxPool2D(pool_size=(sequence_length - filter_sizes[1] + 1, 1), strides=(1,1), padding='valid')(conv_1)
    maxpool_2 = MaxPool2D(pool_size=(sequence_length - filter_sizes[2] + 1, 1), strides=(1,1), padding='valid')(conv_2)

    concatenated_tensor = Concatenate(axis=1)([maxpool_0, maxpool_1, maxpool_2])
    flatten = Flatten()(concatenated_tensor)
    dropout = Dropout(drop)(flatten)
    output = Dense(units=2, activation='softmax')(dropout)
    model = Model(inputs=inputs, outputs=output)
    adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)

    model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
    adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)

    model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
    print("Traning Model...")
    model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, callbacks=[checkpoint], validation_data=(X_test, y_test))  # starts training


    return ??

上面的代码使用X_train和Y_train训练模型，然后对其进行测试.但是在我的系统中，我没有Y_train或Y_test，我只需要softmax层之前的最后一个隐藏层中的向量.我如何获得它?

The above code, trains the model using X_train and Y_train and then tests it. However in my system I do not have Y_train or Y_test, I only need the vector in the last hidden layer before softmax layer. How can I obtain it?

推荐答案

为此，您可以定义一个后端函数来获取任意层的输出:

For that you can define a backend function to get the output of arbitrary layer(s):

from keras import backend as K

func = K.function([model.input], [model.layers[index_of_layer].output])

您可以使用model.summary()找到所需图层的索引，其中列出的图层从索引零开始.如果您需要在最后一层之前的层，则可以使用-2作为索引(即.layers属性实际上是一个列表，因此您可以像在python中的列表一样对其进行索引).然后，您可以通过传递输入数组的列表来使用已定义的功能:

You can find the index of your desired layer using model.summary() where the layers are listed starting from index zero. If you need the layer before the last layer you can use -2 as the index (i.e. .layers attribute is actually a list so you can index it like a list in python). Then you can use the function you have defined by passing a list of input array(s):

outputs = func(inputs)

或者，您也可以为此目的定义模型.此内容已在

Alternatively, you can also define a model for this purpose. This has been covered in Keras documentation more thoroughly so I advise you to read that.

这篇关于获取在softmax层之前的CNN的最后一层中获得的向量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！