TFGENZOO.flows.inv1x1conv module¶
-
class
TFGENZOO.flows.inv1x1conv.Inv1x1Conv(log_det_type: str = 'slogdet', **kwargs)[source]¶ Bases:
TFGENZOO.flows.flowbase.FlowComponentInvertible 1x1 Convolution Layer
- Sources:
https://arxiv.org/pdf/1807.03039.pdf https://github.com/openai/glow/blob/master/model.py#L457-L472
Note
- forward formula
- \[\begin{split}\forall i, j: z_{i, j} &= Wx_{i, j} \\ LogDetJacobian &= hw \log|det(W)|\\ , where &\\ W &\in \mathbb{R}^{c imes c}\\ x &\in \mathbb{R}^{b \times h\times w \times c}\ \ \ ({\rm batch, height, width, channel})\end{split}\]
- inverse formula
- \[\begin{split}\forall i, j: x_{i, j} &= W^{-1} z_{i, j}\\ InverseLogDetJacobian &= - h w \log|det(W)|\\ , where &\\ W &\in \mathbb{R}^{c\times c}\\ x &\in \mathbb{R}^{b \times h\times w \times c}\ \ \ ({\rm batch, height, width, channel})\end{split}\]
Examples
>>> import tensorflow as tf >>> from TFGENZOO.flows import Inv1x1Conv >>> ic = Inv1x1Conv() >>> ic.build([None, 16, 16, 4]) >>> ic.get_config() {'name': 'inv1x1_conv_1', 'trainable': {}, 'dtype': 'float32'} >>> inputs = tf.keras.Input([16, 16, 4]) >>> tf.keras.Model(inputs, ic(inputs)).summary() Layer (type) Output Shape Param # ================================================================= input_3 (InputLayer) [(None, 16, 16, 4)] 0 _________________________________________________________________ inv1x1_conv_1 (Inv1x1Conv) ((None, 16, 16, 4), (None 17 ================================================================= Total params: 17 Trainable params: 0 Non-trainable params: 17 _________________________________________________________________
-
build(input_shape: tensorflow.python.framework.tensor_shape.TensorShape)[source]¶ 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).
-
get_config()[source]¶ 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.
-
class
TFGENZOO.flows.inv1x1conv.Inv1x1Conv2DWithMask(**kwargs)[source]¶ Bases:
TFGENZOO.flows.flowbase.FlowComponentInvertible 1x1 Convolution Layer (2D) with Mask
- Sources:
https://arxiv.org/pdf/1807.03039.pdf https://github.com/openai/glow/blob/master/model.py#L457-L472
Note
- forward formula
- \[\begin{split}\forall i: z_{i} &= Wx_{i} \\ LogDetJacobian &= t \log|det(W)|\\ , where &\\ W &\in \mathbb{R}^{c imes c}\\ x &\in \mathbb{R}^{b \times h\times w \times c}\ \ \ ({\rm batch, timestep, channel})\end{split}\]
- inverse formula
- \[\begin{split}\forall i: x_{i} &= W^{-1} z_{i}\\ InverseLogDetJacobian &= - t \log|det(W)|\\ , where &\\ W &\in \mathbb{R}^{c\times c}\\ x &\in \mathbb{R}^{b \times t\times c}\ \ \ ({\rm batch, timestep, channel})\end{split}\]
- mask notes
- mask shape is [B, T, M] where M may be 1reference glow-tts
-
build(input_shape: tensorflow.python.framework.tensor_shape.TensorShape)[source]¶ 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, mask: tensorflow.python.framework.ops.Tensor = None, **kwargs)[source]¶ - Parameters
x (tf.Tensor) – base 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)
Notes
- mask’s example
- [[[True], [True], [True], [False],[[True], [False], [False], [False],[[True], [True], [True], [True]],[[True], [True], [True], [True]]]
-
get_config()[source]¶ 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.