TFGENZOO.flows.unsafe package

Submodules

• TFGENZOO.flows.unsafe.actnorm module
• TFGENZOO.flows.unsafe.actnorm_test module

Module contents

class TFGENZOO.flows.unsafe.Actnorm(scale: float = 1.0, logscale_factor: float = 3.0, **kwargs)

Bases: TFGENZOO.flows.flowbase.FlowComponent

Actnorm Layer

This layer can SyncBatch Normalization, but may crash frequently.

Sources:

https://github.com/openai/glow/blob/master/tfops.py#L71-L163

Note

• initialize

  mean = mean(first_batch)

  var = variance(first_batch)

  logs = log(scale / sqrt(var)) / logscale_factor

  bias = - mean

• forward formula

  logs = logs * logscale_factor

  scale = exp(logs)

  z = (x + bias) * scale log_det_jacobain = sum(logs) * H * W

• inverse formula

  logs = logs * logsscale_factor

  inv_scale = exp(-logs)

  z = x * inv_scale - bias

  inverse_log_det_jacobian = sum(- logs) * H * W

calc_ldj

bool flag of calculate log det jacobian

scale

float initialize batch’s variance scaling

logscale_factor

float barrier log value to - Inf

property bias

build(input_shape: tensorflow.python.framework.tensor_shape.TensorShape)

Creates the variables of the layer (optional, for subclass implementers).

This is a method that implementers of subclasses of Layer or Model can override if they need a state-creation step in-between layer instantiation and layer call.

This is typically used to create the weights of Layer subclasses.

Parameters

input_shape – Instance of TensorShape, or list of instances of TensorShape if the layer expects a list of inputs (one instance per input).

data_dep_initialize(x: tensorflow.python.framework.ops.Tensor)

forward(x: tensorflow.python.framework.ops.Tensor, **kwargs)

get_config()

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns

Python dictionary.

inverse(z: tensorflow.python.framework.ops.Tensor, **kwargs)

property logs