Edit on GitHub

Normalizations

FluxExtra.Normalizations.norm_01! — Function
norm_01!(data::T,min_vals::T, max_vals::T) where {F<:AbstractFloat,N,T<:Array{F,N}}

Rescales each feature (last dimension) to be in the range [0,1].

source
norm_01!(data::Vector{T}) where {F<:AbstractFloat,N,T<:Array{F,N}}

Rescales each feature (last dimension) to be in the range [0,1]. Returns min and max values for each feature.

source
FluxExtra.Normalizations.norm_negpos1! — Function
norm_negpos1(data::T,min_vals::T,max_vals::T) where {F<:AbstractFloat,N,T<:Array{F,N}}

Rescales each feature (last dimension) to be in the range [-1,1].

source
norm_negpos1(data::Vector{T}) where {F<:AbstractFloat,N,T<:Array{F,N}}

Rescales each feature (last dimension) to be in the range [-1,1]. Returns min and max values for each feature.

source
FluxExtra.Normalizations.norm_zerocenter! — Function
norm_zerocenter!(data::T,mean_vals::T) where {F<:AbstractFloat,N,T<:Array{F,N}}

Subtracts the mean of each feature (last dimension).

source
norm_zerocenter!(data::Vector{T}) where {F<:AbstractFloat,N,T<:Array{F,N}}

Subtracts the mean of each feature (last dimension). Returns a mean value for each feature.

source
FluxExtra.Normalizations.norm_zscore! — Function
norm_zscore!(data::T,mean_vals::T,std_vals::T) where {F<:AbstractFloat,N,T<:Array{F,N}}

Subtracts the mean and divides by the standard deviation of each feature (last dimension).

source
norm_zscore!(data::Vector{T}) where {F<:AbstractFloat,N,T<:Array{F,N}}

Subtracts the mean and divides by the standard deviation of each feature (last dimension). Returns mean and standard deviation values for each feature.

source

Other

Makes Flux.Parallel layer type stable when used with tuples.