TFGENZOO.flows.flowmodel module

class TFGENZOO.flows.flowmodel.BasicGlow(K: int = 5, L: int = 3, resblk_kwargs: Dict = None, conditional: bool = False)

Bases: tensorflow.python.keras.engine.training.Model

call(x, zaux=None, inverse=False, training=True)

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Parameters

• inputs – A tensor or list of tensors.

• training – Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

• mask – A mask or list of masks. A mask can be either a tensor or None (no mask).

Returns

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

forward(x, training)

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(x, zaux, training)

class TFGENZOO.flows.flowmodel.SingleFlow(K: int = 5, L: int = 1, resblk_kwargs: Dict = None)

Bases: tensorflow.python.keras.engine.training.Model

call(x, zaux=None, inverse=False, training=True)

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Parameters

• inputs – A tensor or list of tensors.

• training – Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

• mask – A mask or list of masks. A mask can be either a tensor or None (no mask).

Returns

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

forward(x, training)

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(x, zaux, training)

class TFGENZOO.flows.flowmodel.SqueezeFactorOut(L=3)

Bases: tensorflow.python.keras.engine.training.Model

call(x, zaux=None, inverse=False)

Calls the model on new inputs.

In this case call just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Parameters

• inputs – A tensor or list of tensors.

• training – Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

• mask – A mask or list of masks. A mask can be either a tensor or None (no mask).

Returns

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

forward(x)

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(x, zaux)

TFGENZOO.flows.flowmodel.basic_flow_Test()

TFGENZOO.flows.flowmodel.basic_glow_Test()

TFGENZOO.flows.flowmodel.main()

TFGENZOO.flows.flowmodel.squeeze_factor_Test()