TFGENZOO.flows.cond_affine_coupling module

class TFGENZOO.flows.cond_affine_coupling.ConditionalAffineCoupling(mask_type: TFGENZOO.flows.affine_coupling.AffineCouplingMask = <AffineCouplingMask.ChannelWise: 1>, scale_shift_net: tensorflow.python.keras.engine.base_layer.Layer = None, scale_shift_net_template: Callable[[tensorflow.python.keras.engine.input_layer.Input], tensorflow.python.keras.engine.training.Model] = None, scale_type='safe_exp', **kwargs)

Bases: TFGENZOO.flows.flowbase.FlowComponent

Affine Coupling Layer

Sources:

https://github.com/masa-su/pixyz/blob/master/pixyz/flows/coupling.py

Note

• forward formula

  [x1, x2] = split(x)

  log_scale, shift = NN([x1, c])

  scale = sigmoid(log_scale + 2.0)

  z1 = x1

  z2 = (x2 + shift) * scale

  z = concat([z1, z2])

  LogDetJacobian = sum(log(scale))

• inverse formula

  [z1, z2] = split(x)

  log_scale, shift = NN([z1, c])

  scale = sigmoid(log_scale + 2.0)

  x1 = z1

  x2 = z2 / scale - shift

  z = concat([x1, x2])

  InverseLogDetJacobian = - sum(log(scale))

• implementation notes

  in Glow’s Paper, scale is calculated by exp(log_scale),

  but IN IMPLEMENTATION, scale is done by sigmoid(log_scale + 2.0)

  where c is the conditional input for WaveGlow or cINN

  https://arxiv.org/abs/1907.02392

• TODO notes

  cINN uses double coupling, but our coupling is single coupling

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).

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

class TFGENZOO.flows.cond_affine_coupling.ConditionalAffineCoupling2DWithMask(mask_type: TFGENZOO.flows.affine_coupling.AffineCouplingMask = <AffineCouplingMask.ChannelWise: 1>, scale_shift_net: tensorflow.python.keras.engine.base_layer.Layer = None, scale_shift_net_template: Callable[[tensorflow.python.keras.engine.input_layer.Input], tensorflow.python.keras.engine.training.Model] = None, scale_type='safe_exp', **kwargs)

Bases: TFGENZOO.flows.cond_affine_coupling.ConditionalAffineCouplingWithMask

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).

class TFGENZOO.flows.cond_affine_coupling.ConditionalAffineCouplingWithMask(mask_type: TFGENZOO.flows.affine_coupling.AffineCouplingMask = <AffineCouplingMask.ChannelWise: 1>, scale_shift_net: tensorflow.python.keras.engine.base_layer.Layer = None, scale_shift_net_template: Callable[[tensorflow.python.keras.engine.input_layer.Input], tensorflow.python.keras.engine.training.Model] = None, scale_type='safe_exp', **kwargs)

Bases: TFGENZOO.flows.cond_affine_coupling.ConditionalAffineCoupling

Conditional Affine Coupling Layer with mask

Sources:

https://github.com/masa-su/pixyz/blob/master/pixyz/flows/coupling.py

Note

• forward formula

  [x1, x2] = split(x)

  log_scale, shift = NN([x1, c])

  scale = exp(log_scale)

  z1 = x1

  z2 = (x2 + shift) * scale

  z = concat([z1, z2])

  LogDetJacobian = sum(log(scale))

• inverse formula

  [z1, z2] = split(x)

  log_scale, shift = NN([z1, c])

  scale = exp(log_scale)

  x1 = z1

  x2 = z2 / scale - shift

  z = concat([x1, x2])

  InverseLogDetJacobian = - sum(log(scale))

• implementation notes

  in Glow’s Paper, scale is calculated by exp(log_scale),

  but IN IMPLEMENTATION, scale is done by sigmoid(log_scale + 2.0)

  where c is the conditional input for WaveGlow or cINN

  https://arxiv.org/abs/1907.02392

• TODO notes

  cINN uses double coupling, but our coupling is single coupling

  
  

  scale > 0 because exp(x) > 0

• mask notes

  mask shape is [B, T, M] where M may be 1

  reference glow-tts

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).

forward(x: tensorflow.python.framework.ops.Tensor, cond: tensorflow.python.framework.ops.Tensor, mask: tensorflow.python.framework.ops.Tensor = None, **kwargs)

Parameters

• x (tf.Tensor) – base input tensor [B, T, C]

• cond (tf.Tensor) – conditional input tensor [B, T, C’]

• mask (tf.Tensor) – mask input tensor [B, T, M] where M may be 1

Returns

latent variable tensor [B, T, C] ldj (tf.Tensor): log det jacobian [B]

Return type

z (tf.Tensor)

Note

• mask’s example

  [[True, True, True, False],

  [True, False, False, False],

  [True, True, True, True],

  [True, True, True, True]]

inverse(z: tensorflow.python.framework.ops.Tensor, cond: tensorflow.python.framework.ops.Tensor, mask: tensorflow.python.framework.ops.Tensor = None, **kwargs)

TFGENZOO.flows.cond_affine_coupling.filter_kwargs(d: Dict)