如何通过keras获得每个图层的输出值？

Question

我想使用keras Lstm获取时间序列功能，然后使用Kmeans的功能。但现在我无法获得图层输出值。如何获取图层输出值？

这是我的网络

图层（类型）输出形状参数＃

lstm_66（LSTM）（无，无，50）10400

lstm_67（LSTM）（无，100）60400

dense_19（密集）（无，1）101

activation_19（激活）（无，1）0

我想获取lstm_67输出值，我的代码是：

import keras.backend as K
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' 
import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
import numpy as np
statesAll=[]
layers = model.layers
print layers[1].output,type(layers[1].output[1]),sess.run(layers[1].output)

结果是：

  

Tensor（＆＃34; lstm_61 / TensorArrayReadV3：0＆＃34;，shape =（？，100），dtype = float32）

那么，我怎样才能获得图层输出值？

谢谢！

但它不起作用，我的代码是：

def load_data(file_name, sequence_length=10, split=0.8):
    df = pd.read_csv(file_name, sep=',', usecols=[1])
    data_all = np.array(df).astype(float)
    scaler = MinMaxScaler()
    data_all = scaler.fit_transform(data_all)
    data = []
    print len(data_all)
    for i in range(len(data_all) - sequence_length - 1):
        data.append(data_all[i: i + sequence_length + 1])

    reshaped_data = np.array(data).astype('float64')
    np.random.shuffle(reshaped_data)
    x = reshaped_data[:, :-1]
    y = reshaped_data[:, -1]
    split_boundary = int(reshaped_data.shape[0] * split)
    train_x = x[: split_boundary]
    test_x = x[split_boundary:]

    train_y = y[: split_boundary]
    test_y = y[split_boundary:]

    return train_x, train_y, test_x, test_y, scaler

def build_model(n_samples, time_steps, input_dim):
    model = Sequential()
    model.add(LSTM(input_dim=1, output_dim=50,return_sequences=True))
    model.add(LSTM(100, return_sequences=False))
    model.add(Dense(output_dim=1))
    model.add(Activation('linear'))
    model.compile(loss='mse', optimizer='rmsprop')
    print(model.layers)
    return model

def train_model(train_x, train_y, test_x, test_y):
    model = build_model()
    model.fit(train_x, train_y, batch_size=128, nb_epoch=30,validation_split=0.1)
    return model


train_x, train_y, test_x, test_y, scaler = load_data(file path)
train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
test_x = np.reshape(test_x, (test_x.shape[0], test_x.shape[1], 1))

model = train_model(train_x, train_y, test_x, test_y)

from keras import backend as K
layers = model.layers
K.eval(layers[1].output)

Answer 1

keras.backend.eval()应该这样做。

查看文档here和here

Answer 2

首先，这是张量，您需要使用tf. Print ()方法来查看特定值。如果您使用Spyder，则不会在控制台中看到此信息。您需要在命令行中执行此程序。

Answer 3

在TensorFlow 2.x中，您可以这样做：

from tensorflow.python.keras import backend as K

model = build_model() 
# lstm_67 is the second layer.
lstm = K.function([model.layers[0].input], [model.layers[1].output])
lstm_output = lstm([test_x])[0]