symjax.nn.layers.Dropout

class symjax.nn.layers.Dropout(input, p, deterministic, seed=None)[source]

binary mask onto the input

Parameters:
  • input_or_shape (shape or Tensor) – the layer input or shape
  • p (float (0<=p<=1)) – the probability to drop the value
  • deterministic (bool or Tensor) – the state of the layer
  • seed (seed) – the RNG seed
Returns:

output
Return type:

the layer output
__init__(input, p, deterministic, seed=None)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(input, p, deterministic[, seed]) Initialize self.
Dropout.add_update
Dropout.add_variable
argmax([axis, out]) Returns the indices of the maximum values along an axis.
argmin([axis, out]) Returns the indices of the minimum values along an axis.
astype(new_dtype) Elementwise cast.
cast(new_dtype) Elementwise cast.
clone(givens)
conj() Return the complex conjugate, element-wise.
conjugate() Return the complex conjugate, element-wise.
Dropout.create_tensor
Dropout.create_variable
dot(b, *[, precision]) Dot product of two arrays.
expand_dims(axis, Tuple[int, …]]) Expand the shape of an array.
flatten() reshape the input into a vector
forward()
imag() Return the imaginary part of the complex argument.
Dropout.init_input
matmul(b, *[, precision]) Matrix product of two arrays.
max([axis, out, keepdims, initial, where]) Return the maximum of an array or maximum along an axis.
mean([axis, dtype, out, keepdims]) Compute the arithmetic mean along the specified axis.
min([axis, out, keepdims, initial, where]) Return the minimum of an array or minimum along an axis.
prod([axis, dtype, out, keepdims, initial, …]) Return the product of array elements over a given axis.
real() Return the real part of the complex argument.
repeat(repeats[, axis, total_repeat_length]) Repeat elements of an array.
reshape(newshape[, order]) Gives a new shape to an array without changing its data.
round([decimals, out]) Round an array to the given number of decimals.
squeeze(axis, Tuple[int, …]] = None) Remove single-dimensional entries from the shape of an array.
std([axis, dtype, out, ddof, keepdims]) Compute the standard deviation along the specified axis.
sum([axis, dtype, out, keepdims, initial, where]) Sum of array elements over a given axis.
transpose([axes]) Reverse or permute the axes of an array; returns the modified array.
var([axis, dtype, out, ddof, keepdims]) Compute the variance along the specified axis.
variables([trainable])

Attributes

dtype
Dropout.fn_name
name
ndim
scope
shape
Dropout.updates