问题描述

在大数据建模过程中，希望融合多种特征，因此需要将模型中间的是特征保存下来，以便后面使用。

解决办法

1.定义模型

def arch(data):
    Random(0)
    model = keras.Sequential(
        [
            layers.Input(shape=(data.shape[1], data.shape[2])),
            layers.Conv1D(
                filters=32, kernel_size=7, padding="same", strides=2, activation="relu"
            ),
            layers.Dropout(rate=0.2),
            layers.Conv1D(
                filters=16, kernel_size=7, padding="same", strides=2, activation="relu"
            ),
            layers.Conv1DTranspose(
                filters=16, kernel_size=7, padding="same", strides=2, activation="relu"
            ),
            layers.Dropout(rate=0.2),
            layers.Conv1DTranspose(
                filters=32, kernel_size=7, padding="same", strides=2, activation="relu"
            ),
            layers.Conv1DTranspose(filters=1, kernel_size=7, padding="same"),
        ]
    )
    model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.001), loss="mse")
    model.summary()

    history = model.fit(
        data,
        data,
        epochs=100,
        batch_size=32,
        validation_split=0.1,
        verbose=0,
        callbacks=[
            keras.callbacks.EarlyStopping(monitor="val_loss", patience=5, mode="min", verbose=0)
        ],
    )
    return history, model

查看模型架构

model.summary()

2.获取conv1d_transpose_4层的输出结果。代码如下：

from keras import backend as K
representation_layer = K.function(inputs=[model.layers[0].input], outputs=[model.get_layer('conv1d_transpose_4').output])

representation = representation_layer([X])
representation = np.array(representation)[0]
print(representation.shape)
print(type(representation))
print(representation)

结果如图，保存即可。

参考链接：https://blog.csdn.net/selectopti/article/details/115933551