tf.keras.layers.Lambda( function, output_shape=None, mask=None, arguments=None, **kwargs )
Wraps arbitrary expressions as a
Lambda layer exists so that arbitrary TensorFlow functions
can be used when constructing
Sequential and Functional API
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, whereas subclassed
Layers can be saved via overriding their
get_config method. Overriding
get_config improves the portability of Models. 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))
Variables: 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:
```python 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.
output_shape = (input_shape, ) + output_shapeor, the input is
Noneand the sample dimension is also
output_shape = (None, ) + output_shapeIf a function, it specifies the entire shape as a function of the input shape:
output_shape = f(input_shape)
compute_masklayer method, or a tensor that will be returned as output mask regardless of what the input is.
Arbitrary. Use the keyword argument input_shape (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.