tf.nn.dropout( x, keep_prob, noise_shape=None, seed=None, name=None )
See the guide: Neural Network > Activation Functions
keep_prob, outputs the input element scaled up by
1 / keep_prob, otherwise outputs
0. The scaling is so that the expected
sum is unchanged.
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.
keep_prob: A scalar
Tensorwith the same type as x. The probability that each element is kept.
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
keep_probis not in
(0, 1]or if
xis not a floating point tensor.