View source on GitHub
|
Tensor statistics and normalization.
Classes
class EMATensorNormalizer: TensorNormalizer with exponential moving avg. mean and var estimates.
class StreamingTensorNormalizer: Normalizes mean & variance based on full history of tensor values.
class TensorNormalizer: Encapsulates tensor normalization and owns normalization variables.
Functions
kahan_summation(...): Calculate stable acculated sum using compensation for low-bits.
parallel_variance_calculation(...): Calculate the sufficient statistics (average & second moment) of two sets.
Other Members | |
|---|---|
| absolute_import |
Instance of __future__._Feature
|
| division |
Instance of __future__._Feature
|
| print_function |
Instance of __future__._Feature
|