从顺序Keras模型中保存特定层 [英] Saving the specific layer from within a sequential Keras model

问题描述

我正在构建自动编码器并训练模型，以使目标输出与输入相同.

I am building an auto-encoder and training the model so the targeted output is the same as the input.

我正在使用顺序Keras模型.当我使用model.predict时，我希望它从特定层(Dense256)而不是输出中导出数组.

I am using a sequential Keras model. When I use model.predict I would like it to export the array from a specific layer (Dense256) not the output.

这是我当前的模型:

model = Sequential()
model.add(Dense(4096, input_dim = x.shape[1], activation = 'relu'))
model.add(Dense(2048, activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(256, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(2048, activation='relu'))
model.add(Dense(4096, activation='relu'))
model.add(Dense(x.shape[1], activation ='sigmoid'))
model.compile(loss = 'mean_squared_error', optimizer = 'adam')
history = model.fit(data_train,data_train,
                    verbose=1,
                    epochs=10, 
                    batch_size=256,
                    shuffle=True,
                    validation_data=(data_test, data_test))

推荐答案

训练后，从训练有素的模型(模型)中创建一个新模型(model2)，该模型以所需的层结束.

After training, create a new model (model2) from your trained model (model) ending in your desired layer.

您可以使用图层名称进行操作:

You can do so either with layer name:

(在model.summary()中，具有256个神经元的密集层的名称"为density_5)

(In model.summary(), your dense's layer 'name' with 256 neurons is dense_5)

from keras.models import Model
model2= Model(model.input,model.get_layer('dense_5').output)

或具有图层顺序:

(您的具有256个神经元的致密层在model.summary()中排名第五)

(your dense layer with 256 neurons is fifth in model.summary())

from keras.models import Model
model2= Model(model.input,model.layers[4].output)

然后您可以使用预测

preds=model2.predict(x)

这篇关于从顺序Keras模型中保存特定层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！