Module: tfc  |  TensorFlow v2.16.1 (original) (raw)

Data compression in TensorFlow.

Modules

distributions module: Distributions, based on tfp.distributions.Distribution.

entropy_models module: Entropy models.

layers module: Layers, based on tf.keras.layers.Layer.

ops module: TensorFlow operations and functions.

Classes

class ContinuousBatchedEntropyModel: Batched entropy model for continuous random variables.

class ContinuousIndexedEntropyModel: Indexed entropy model for continuous random variables.

class DeepFactorized: Fully factorized distribution based on neural network cumulative.

class GDN: Generalized divisive normalization layer.

class GDNParameter: Nonnegative parameterization as needed for GDN parameters.

class IdentityInitializer: Initialize to the identity kernel with the given shape.

class LocationScaleIndexedEntropyModel: Indexed entropy model for location-scale family of random variables.

class MonotonicAdapter: Adapt a continuous distribution via an ascending monotonic function.

class NoisyDeepFactorized: DeepFactorized that is convolved with uniform noise.

class NoisyLaplace: Laplacian distribution with additive i.i.d. uniform noise.

class NoisyLogistic: Logistic distribution with additive i.i.d. uniform noise.

class NoisyLogisticMixture: Mixture of logistic distributions with additive i.i.d. uniform noise.

class NoisyMixtureSameFamily: Mixture of distributions with additive i.i.d. uniform noise.

class NoisyNormal: Gaussian distribution with additive i.i.d. uniform noise.

class NoisyNormalMixture: Mixture of normal distributions with additive i.i.d. uniform noise.

class NoisyRoundedDeepFactorized: Rounded DeepFactorized + uniform noise.

class NoisyRoundedNormal: Rounded normal distribution + uniform noise.

class NoisySoftRoundedDeepFactorized: Soft rounded DeepFactorized + uniform noise.

class NoisySoftRoundedNormal: Soft rounded normal distribution + uniform noise.

class PackedTensors: Packed representation of compressed tensors.

class Parameter: Reparameterized Layer variable.

class PowerLawEntropyModel: Entropy model for power-law distributed random variables.

class RDFTParameter: RDFT reparameterization of a convolution kernel.

class RoundAdapter: Continuous density function + round.

class SignalConv1D: 1D convolution layer.

class SignalConv2D: 2D convolution layer.

class SignalConv3D: 3D convolution layer.

class SoftRound: Applies a differentiable approximation of rounding.

class SoftRoundAdapter: Differentiable approximation to round.

class SoftRoundConditionalMean: Conditional mean of inputs given noisy soft rounded values.

class UniformNoiseAdapter: Additive i.i.d. uniform noise adapter distribution.

class UniversalBatchedEntropyModel: Batched entropy model model which implements Universal Quantization.

class UniversalIndexedEntropyModel: Indexed entropy model model which implements Universal Quantization.

class Y4MDataset: A tf.Dataset of Y'CbCr video frames from '.y4m' files.

Functions

create_range_decoder(...): Creates range decoder objects to be used by EntropyDecode* ops.

create_range_encoder(...): Creates range encoder objects to be used by EntropyEncode* ops.

entropy_decode_channel(...): Decodes the encoded stream inside handle.

entropy_decode_finalize(...): Finalizes the decoding process.

entropy_decode_index(...): Decodes the encoded stream inside handle.

entropy_encode_channel(...): Encodes each input in value.

entropy_encode_finalize(...): Finalizes the encoding process and extracts byte stream from the encoder.

entropy_encode_index(...): Encodes each input in value according to a distribution selected by index.

estimate_tails(...): Estimates approximate tail quantiles.

lower_bound(...): Same as tf.maximum, but with helpful gradient for inputs < bound.

lower_tail(...): Approximates lower tail quantile for range coding.

perturb_and_apply(...): Perturbs the inputs of a pointwise function.

pmf_to_quantized_cdf(...): Converts a PMF into a quantized CDF for range coding.

quantization_offset(...): Computes distribution-dependent quantization offset.

round_st(...): Straight-through round with optional quantization offset.

run_length_decode(...): Decodes data using run-length coding.

run_length_encode(...): Encodes data using run-length coding.

run_length_gamma_decode(...): Decodes data using run-length and Elias gamma coding.

run_length_gamma_encode(...): Encodes data using run-length and Elias gamma coding.

same_padding_for_kernel(...): Determine correct amount of padding for same convolution.

soft_round(...): Differentiable approximation to round.

soft_round_conditional_mean(...): Conditional mean of inputs given noisy soft rounded values.

soft_round_inverse(...): Inverse of soft_round.

stochastic_round(...): Rounds inputs / step_size stochastically.

upper_bound(...): Same as tf.minimum, but with helpful gradient for inputs > bound.

upper_tail(...): Approximates upper tail quantile for range coding.