Modeling-related questions

How can I obtain the output of an intermediate layer (feature extraction)?

In the Functional API and Sequential API, if a layer has been called exactly once, you can retrieve its output via layer.output and its input via layer.input. This enables you do quickly instantiate feature-extraction models, like this one:

import keras
from keras import layers

model = Sequential([
    layers.Conv2D(32, 3, activation='relu'),
    layers.Conv2D(32, 3, activation='relu'),
    layers.MaxPooling2D(2),
    layers.Conv2D(32, 3, activation='relu'),
    layers.Conv2D(32, 3, activation='relu'),
    layers.GlobalMaxPooling2D(),
    layers.Dense(10),
])
extractor = keras.Model(inputs=model.inputs,
                        outputs=[layer.output for layer in model.layers])
features = extractor(data)

Naturally, this is not possible with models that are subclasses of Model that override call.

Here’s another example: instantiating a Model that returns the output of a specific named layer:

model = ...  # create the original model

layer_name = 'my_layer'
intermediate_layer_model = keras.Model(inputs=model.input,
                                       outputs=model.get_layer(layer_name).output)
intermediate_output = intermediate_layer_model(data)