|TensorFlow 1 version||View source on GitHub|
Wraps arbitrary expressions as a
Compat aliases for migration
See Migration guide for more details.
tf.keras.layers.Lambda( function, output_shape=None, mask=None, arguments=None, **kwargs )
Used in the notebooks
|Used in the tutorials|
Lambda layer exists so that arbitrary expressions can be used
Layer when constructing
and Functional API models.
Lambda layers are best suited for simple
operations or quick experimentation. For more advanced use cases, follow
The main reason to subclass
tf.keras.layers.Layer instead of using a
Lambda layer is saving and inspecting a Model.
are saved by serializing the Python bytecode, which is fundamentally
non-portable. They should only be loaded in the same environment where
they were saved. Subclassed layers can be saved in a more portable way
by overriding their
get_config method. Models that rely on
subclassed Layers are also often easier to visualize and reason about.
# add a x -> x^2 layer model.add(Lambda(lambda x: x ** 2))
# add a layer that returns the concatenation # of the positive part of the input and # the opposite of the negative part def antirectifier(x): x -= K.mean(x, axis=1, keepdims=True) x = K.l2_normalize(x, axis=1) pos = K.relu(x) neg = K.relu(-x) return K.concatenate([pos, neg], axis=1) model.add(Lambda(antirectifier))
While it is possible to use Variables with Lambda layers, this practice is discouraged as it can easily lead to bugs. For instance, consider the following layer:
scale = tf.Variable(1.) scale_layer = tf.keras.layers.Lambda(lambda x: x * scale)
Because scale_layer does not directly track the
scale variable, it will
not appear in
scale_layer.trainable_weights and will therefore not be
scale_layer is used in a Model.
A better pattern is to write a subclassed Layer:
class ScaleLayer(tf.keras.layers.Layer): def __init__(self): super(ScaleLayer, self).__init__() self.scale = tf.Variable(1.) def call(self, inputs): return inputs * self.scale
In general, Lambda layers can be convenient for simple stateless computation, but anything more complex should use a subclass Layer instead.
||The function to be evaluated. Takes input tensor as first argument.|
Expected output shape from function. This argument can be
inferred if not explicitly provided. Can be a tuple or function. If a
tuple, it only specifies the first dimension onward;
sample dimension is assumed either the same as the input:
Either None (indicating no masking) or a callable with the same
signature as the