symjax.nn.layers.BatchNormalization¶
-
class
symjax.nn.layers.
BatchNormalization
(input, axis, deterministic, const=0.001, beta_1=0.99, beta_2=0.99, W=<function ones>, b=<function zeros>, trainable_W=True, trainable_b=True)[source]¶ batch-normalization layer
- input_or_shape: shape or Tensor
- the layer input tensor or shape
- axis: list or tuple of ints
- the axis to normalize on. If using BN on a dense layer then axis should be [0] to normalize over the samples. If the layer if a convolutional layer with data format NCHW then axis should be [0, 2, 3] to normalize over the samples and spatial dimensions (commonly done)
- deterministic: bool or Tensor
- controlling the state of the layer
- const: float32 (optional)
- the constant used in the standard deviation renormalization
- beta1: flaot32 (optional)
- the parameter for the exponential moving average of the mean
- beta2: float32 (optional)
- the parameters for the exponential moving average of the std
Returns: output Return type: the layer output with attributes given by the layer options -
__init__
(input, axis, deterministic, const=0.001, beta_1=0.99, beta_2=0.99, W=<function ones>, b=<function zeros>, trainable_W=True, trainable_b=True)[source]¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__
(input, axis, deterministic[, …])Initialize self. BatchNormalization.add_update
BatchNormalization.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. BatchNormalization.create_tensor
BatchNormalization.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. BatchNormalization.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
BatchNormalization.fn_name
name
ndim
scope
shape
BatchNormalization.updates