Base class for applying common real-time data preprocessing.
This class is meant to be used as an argument of
input_data. When training
a model, the defined pre-processing methods will be applied at both
training and testing time. Note that DataAugmentation is similar to
DataPreprocessing, but only applies at training time.
Apply any custom pre-processing function to the .
- func: a
Functionthat take a numpy array as input and returns a numpy array.
Scale each sample by the specified standard deviation. If no std specified, std is evaluated over all samples data.
float(optional). Provides a custom standard derivation. If none provided, it will be automatically caluclated based on the training dataset. Default: None.
Zero center every sample with specified mean. If not specified, the mean is evaluated over all samples.
float(optional). Provides a custom mean. If none provided, it will be automatically caluclated based on the training dataset. Default: None.
Scale each sample with its standard deviation.
Zero center each sample by subtracting it by its mean.
Apply ZCA Whitening to data.
array(optional). Use the provided pre-computed principal component instead of computing it.