|TensorFlow 1 version||View source on GitHub|
tf.nn.dropout( x, rate, noise_shape=None, seed=None, name=None )
Used in the guide:
Used in the tutorials:
rate, drops elements of
x. Input that are kept are
scaled up by
1 / (1 - rate), otherwise outputs
0. The scaling is so that
the expected sum is unchanged.
Note: The behavior of dropout has changed between TensorFlow 1.x and 2.x. When converting 1.x code, please use named arguments to ensure behavior stays consistent.
By default, each element is kept or dropped independently. If
is specified, it must be
to the shape of
x, and only dimensions with
noise_shape[i] == shape(x)[i]
will make independent decisions. For example, if
shape(x) = [k, l, m, n]
noise_shape = [k, 1, 1, n], each batch and channel component will be
kept independently and each row and column will be kept or not kept together.
x: A floating point tensor.
rate: A scalar
Tensorwith the same type as x. The probability that each element is dropped. For example, setting rate=0.1 would drop 10% of input elements.
noise_shape: A 1-D
int32, representing the shape for randomly generated keep/drop flags.
seed: A Python integer. Used to create random seeds. See
name: A name for this operation (optional).
A Tensor of the same shape of
rateis not in
(0, 1]or if
xis not a floating point tensor.