TensorFlow Generator

This module defines the TFGenerator class that generates TF code for neural networks based on the B-UML model.

class besser.generators.nn.tf.tf_code_generator.TFGenerator(model: NN, output_dir: str | None = None, generation_type: str = 'subclassing')[source]

Bases: NNCodeGenerator

TFGenerator is a class that inherits from NNCodeGenerator. It generates TF code for neural networks training and evaluation based on the B-UML input model.

Parameters:

  • model (NN) – An instance of the NN Model class representing the B-UML model.

  • setup_layer (SetupLayerSyntax) – The class that defines the syntax of layers.

  • setup_tensorop (Callable) – The function that defines the syntax of tensorops.

  • output_dir (str, optional) – The output directory where the generated code will be saved. Defaults to None.

  • file_name (str) – The name of the file where the generated code is stored.

  • template_dir (str) – The name of the jinja template directory.

  • generation_type (str) – ‘subclassing’ or ‘sequential’.

_abc_impl = <_abc._abc_data object>