Release notes from GeneticAlgorithmPython

PyGAD 2.10.2

2021-01-15T16:18:02Z

A bug fix when save_best_solutions=True. Refer to this issue for more information: ahmedfgad#25

PyGAD 2.10.1 Documentation

2021-01-11T02:46:01Z

In the gene_space parameter, any None value (regardless of its index or axis), is replaced by a randomly generated number based on the 3 parameters init_range_low, init_range_high, and gene_type. So, the None value in [..., None, ...] or [..., [..., None, ...], ...] are replaced with random values. This gives more freedom in building the space of values for the genes.
All the numbers passed to the gene_space parameter are casted to the type specified in the gene_type parameter.
The numpy.uint data type is supported for the parameters that accept integer values.
In the pygad.kerasga module, the model_weights_as_vector() function uses the trainable attribute of the model's layers to only return the trainable weights in the network. So, only the trainable layers with their trainable attribute set to True (trainable=True), which is the default value, have their weights evolved. All non-trainable layers with the trainable attribute set to False (trainable=False) will not be evolved. Thanks to Prof. Tamer A. Farrag for pointing about that at GitHub.

2.10.0: Link to TorchGA project at GitHub

2021-01-04T02:09:26Z

Link to TorchGA project at GitHub: https://github.com/ahmedfgad/TorchGA

PyGAD 2.9.0

2020-12-05T23:29:23Z

Changes in PyGAD 2.9.0 (06 December 2020):

The fitness values of the initial population are considered in the best_solutions_fitness attribute.
An optional parameter named save_best_solutions is added. It defaults to False. When it is True, then the best solution after each generation is saved into an attribute named best_solutions. If False, then no solutions are saved and the best_solutions attribute will be empty.
Scattered crossover is supported. To use it, assign the crossover_type parameter the value "scattered".
NumPy arrays are now supported by the gene_space parameter.
The following parameters (gene_type, crossover_probability, mutation_probability, delay_after_gen) can be assigned to a numeric value of any of these data types: int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.float, numpy.float16, numpy.float32, or numpy.float64.

2.8.1: Bug fix in applying crossover

2020-10-03T03:53:38Z

Bug fix in applying the crossover operation when the crossover_probability parameter is used.
Thanks to Eng. Hamada Kassem, RA/TA, Construction Engineering and Management, Faculty of Engineering, Alexandria University, Egypt: https://www.linkedin.com/in/hamadakassem

2.8.0

2020-09-20T21:49:13Z

Train Keras models using PyGAD (pygad.kerasga)

2.7.2

2020-09-14T16:49:47Z

Add files via upload

2.7.1

2020-09-14T16:49:47Z

Add files via upload

2.7.0

2020-09-11T18:03:47Z

Add files via upload

2.6.0

2020-08-06T13:42:11Z

Add files via upload