Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 040b8e1

Browse files
PyGAD 2.9.0
Changes in PyGAD 2.9.0 (06 December 2020): 1. The fitness values of the initial population are considered in the `best_solutions_fitness` attribute. 2. 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. 3. Scattered crossover is supported. To use it, assign the `crossover_type` parameter the value `"scattered"`. 4. NumPy arrays are now supported by the `gene_space` parameter. 5. 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`.
1 parent 7d31893 commit 040b8e1

File tree

4 files changed

+175
-104
lines changed

4 files changed

+175
-104
lines changed

‎docs/source/Footer.rst

Lines changed: 74 additions & 34 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
1-
.. _header-n298:
1+
.. _header-n0:
22

33
Release History
44
===============
55

6-
.. _header-n300:
6+
.. _header-n2:
77

88
PyGAD 1.0.17
99
------------
@@ -15,7 +15,7 @@ Release Date: 15 April 2020
1515
values for the solutions. This allows the project to be customized to
1616
any problem by building the right fitness function.
1717

18-
.. _header-n305:
18+
.. _header-n7:
1919

2020
PyGAD 1.0.20
2121
-------------
@@ -35,7 +35,7 @@ Release Date: 4 May 2020
3535
4. The code object ``__code__`` of the passed fitness function is
3636
checked to ensure it has the right number of parameters.
3737

38-
.. _header-n316:
38+
.. _header-n18:
3939

4040
PyGAD 2.0.0
4141
------------
@@ -61,7 +61,7 @@ Release Date: 13 May 2020
6161
is called after each generation. This helps the user to do
6262
post-processing or debugging operations after each generation.
6363

64-
.. _header-n327:
64+
.. _header-n29:
6565

6666
PyGAD 2.1.0
6767
-----------
@@ -97,7 +97,7 @@ Release Date: 14 May 2020
9797

9898
2. Mutation is applied independently for the genes.
9999

100-
.. _header-n342:
100+
.. _header-n44:
101101

102102
PyGAD 2.2.1
103103
-----------
@@ -107,7 +107,7 @@ Release Date: 17 May 2020
107107
1. Adding 2 extra modules (pygad.nn and pygad.gann) for building and
108108
training neural networks with the genetic algorithm.
109109

110-
.. _header-n347:
110+
.. _header-n49:
111111

112112
PyGAD 2.2.2
113113
-----------
@@ -141,7 +141,7 @@ The new gene value is **0.1**.
141141
``crossover_type`` parameters of the pygad.GA class constructor. When
142142
``None``, this means the step is bypassed and has no action.
143143

144-
.. _header-n360:
144+
.. _header-n62:
145145

146146
PyGAD 2.3.0
147147
-----------
@@ -166,7 +166,7 @@ Release date: 1 June 2020
166166
6. The name of the ``pygad.nn.train_network()`` function is changed to
167167
``pygad.nn.train()``.
168168

169-
.. _header-n375:
169+
.. _header-n77:
170170

171171
PyGAD 2.4.0
172172
-----------
@@ -204,7 +204,7 @@ through more generations because no further improvement is possible.
204204
if ga_instance.best_solution()[1] >= 70:
205205
return "stop"
206206
207-
.. _header-n385:
207+
.. _header-n87:
208208

209209
PyGAD 2.5.0
210210
-----------
@@ -300,7 +300,7 @@ If the user did not assign the initial population to the
300300
randomly based on the ``gene_space`` parameter. Moreover, the mutation
301301
is applied based on this parameter.
302302

303-
.. _header-n413:
303+
.. _header-n115:
304304

305305
PyGAD 2.6.0
306306
------------
@@ -318,7 +318,7 @@ Release Date: 6 August 2020
318318
``on_fitness``, ``on_parents``, ``on_crossover``, ``on_mutation``,
319319
``on_generation``, and ``on_stop``.
320320

321-
.. _header-n422:
321+
.. _header-n124:
322322

323323
PyGAD 2.7.0
324324
-----------
@@ -377,7 +377,7 @@ parameter or set it to ``"classification"`` (default value). In this
377377
case, the activation function of the last layer can be set to any type
378378
(e.g. softmax).
379379

380-
.. _header-n446:
380+
.. _header-n148:
381381

382382
PyGAD 2.7.1
383383
-----------
@@ -387,7 +387,7 @@ Release Date: 11 September 2020
387387
1. A bug fix when the ``problem_type`` argument is set to
388388
``regression``.
389389

390-
.. _header-n451:
390+
.. _header-n153:
391391

392392
PyGAD 2.7.2
393393
-----------
@@ -397,7 +397,7 @@ Release Date: 14 September 2020
397397
1. Bug fix to support building and training regression neural networks
398398
with multiple outputs.
399399

400-
.. _header-n456:
400+
.. _header-n158:
401401

402402
PyGAD 2.8.0
403403
-----------
@@ -407,7 +407,7 @@ Release Date: 20 September 2020
407407
1. Support of a new module named ``kerasga`` so that the Keras models
408408
can be trained by the genetic algorithm using PyGAD.
409409

410-
.. _header-n597:
410+
.. _header-n163:
411411

412412
PyGAD 2.8.1
413413
-----------
@@ -420,7 +420,35 @@ Release Date: 3 October 2020
420420
Management, Faculty of Engineering, Alexandria University,
421421
Egypt <https://www.linkedin.com/in/hamadakassem>`__.
422422

423-
.. _header-n596:
423+
.. _header-n168:
424+
425+
PyGAD 2.9.0
426+
------------
427+
428+
Release Date: 06 December 2020
429+
430+
1. The fitness values of the initial population are considered in the
431+
``best_solutions_fitness`` attribute.
432+
433+
2. An optional parameter named ``save_best_solutions`` is added. It
434+
defaults to ``False``. When it is ``True``, then the best solution
435+
after each generation is saved into an attribute named
436+
``best_solutions``. If ``False``, then no solutions are saved and the
437+
``best_solutions`` attribute will be empty.
438+
439+
3. Scattered crossover is supported. To use it, assign the
440+
``crossover_type`` parameter the value ``"scattered"``.
441+
442+
4. NumPy arrays are now supported by the ``gene_space`` parameter.
443+
444+
5. The following parameters (``gene_type``, ``crossover_probability``,
445+
``mutation_probability``, ``delay_after_gen``) can be assigned to a
446+
numeric value of any of these data types: ``int``, ``float``,
447+
``numpy.int``, ``numpy.int8``, ``numpy.int16``, ``numpy.int32``,
448+
``numpy.int64``, ``numpy.float``, ``numpy.float16``,
449+
``numpy.float32``, or ``numpy.float64``.
450+
451+
.. _header-n303:
424452

425453
PyGAD Projects at GitHub
426454
========================
@@ -430,7 +458,7 @@ https://pypi.org/project/pygad. PyGAD is built out of a number of
430458
open-source GitHub projects. A brief note about these projects is given
431459
in the next subsections.
432460

433-
.. _header-n463:
461+
.. _header-n170:
434462

435463
`GeneticAlgorithmPython <https://github.com/ahmedfgad/GeneticAlgorithmPython>`__
436464
--------------------------------------------------------------------------------
@@ -441,7 +469,7 @@ GitHub Link: https://github.com/ahmedfgad/GeneticAlgorithmPython
441469
is the first project which is an open-source Python 3 project for
442470
implementing the genetic algorithm based on NumPy.
443471

444-
.. _header-n466:
472+
.. _header-n173:
445473

446474
`NumPyANN <https://github.com/ahmedfgad/NumPyANN>`__
447475
----------------------------------------------------
@@ -455,7 +483,7 @@ neural network without using a training algorithm. Currently, it only
455483
supports classification and later regression will be also supported.
456484
Moreover, only one class is supported per sample.
457485

458-
.. _header-n469:
486+
.. _header-n176:
459487

460488
`NeuralGenetic <https://github.com/ahmedfgad/NeuralGenetic>`__
461489
--------------------------------------------------------------
@@ -468,7 +496,7 @@ projects
468496
`GeneticAlgorithmPython <https://github.com/ahmedfgad/GeneticAlgorithmPython>`__
469497
and `NumPyANN <https://github.com/ahmedfgad/NumPyANN>`__.
470498

471-
.. _header-n472:
499+
.. _header-n179:
472500

473501
`NumPyCNN <https://github.com/ahmedfgad/NumPyCNN>`__
474502
----------------------------------------------------
@@ -480,7 +508,7 @@ convolutional neural networks using NumPy. The purpose of this project
480508
is to only implement the **forward pass** of a convolutional neural
481509
network without using a training algorithm.
482510

483-
.. _header-n475:
511+
.. _header-n182:
484512

485513
`CNNGenetic <https://github.com/ahmedfgad/CNNGenetic>`__
486514
--------------------------------------------------------
@@ -492,7 +520,19 @@ convolutional neural networks using the genetic algorithm. It uses the
492520
`GeneticAlgorithmPython <https://github.com/ahmedfgad/GeneticAlgorithmPython>`__
493521
project for building the genetic algorithm.
494522

495-
.. _header-n478:
523+
.. _header-n325:
524+
525+
`KerasGA <https://github.com/ahmedfgad/KerasGA>`__
526+
--------------------------------------------------
527+
528+
GitHub Link: https://github.com/ahmedfgad/KerasGA
529+
530+
`KerasGA <https://github.com/ahmedfgad/KerasGA>`__ trains Keras models
531+
using the genetic algorithm. It uses the
532+
`GeneticAlgorithmPython <https://github.com/ahmedfgad/GeneticAlgorithmPython>`__
533+
project for building the genetic algorithm.
534+
535+
.. _header-n185:
496536

497537
Submitting Issues
498538
=================
@@ -509,7 +549,7 @@ is not working properly or to ask for questions.
509549
If this is not a proper option for you, then check the **Contact Us**
510550
section for more contact details.
511551

512-
.. _header-n482:
552+
.. _header-n189:
513553

514554
Ask for Feature
515555
===============
@@ -526,7 +566,7 @@ to ahmed.f.gad@gmail.com.
526566

527567
Also check the **Contact Us** section for more contact details.
528568

529-
.. _header-n486:
569+
.. _header-n193:
530570

531571
Projects Built using PyGAD
532572
==========================
@@ -545,15 +585,15 @@ Within your message, please send the following details:
545585

546586
- Preferably, a link that directs the readers to your project
547587

548-
.. _header-n497:
588+
.. _header-n204:
549589

550590
For More Information
551591
====================
552592

553593
There are different resources that can be used to get started with the
554594
genetic algorithm and building it in Python.
555595

556-
.. _header-n499:
596+
.. _header-n206:
557597

558598
Tutorial: Implementing Genetic Algorithm in Python
559599
--------------------------------------------------
@@ -577,7 +617,7 @@ good resource to start with coding the genetic algorithm.
577617

578618
|image0|
579619

580-
.. _header-n510:
620+
.. _header-n217:
581621

582622
Tutorial: Introduction to Genetic Algorithm
583623
-------------------------------------------
@@ -596,7 +636,7 @@ which is available at these links:
596636

597637
|image1|
598638

599-
.. _header-n520:
639+
.. _header-n227:
600640

601641
Tutorial: Build Neural Networks in Python
602642
-----------------------------------------
@@ -616,7 +656,7 @@ available at these links:
616656

617657
|image2|
618658

619-
.. _header-n530:
659+
.. _header-n237:
620660

621661
Tutorial: Optimize Neural Networks with Genetic Algorithm
622662
---------------------------------------------------------
@@ -636,7 +676,7 @@ available at these links:
636676

637677
|image3|
638678

639-
.. _header-n540:
679+
.. _header-n247:
640680

641681
Tutorial: Building CNN in Python
642682
--------------------------------
@@ -662,7 +702,7 @@ good resource to start with coding CNNs.
662702

663703
|image4|
664704

665-
.. _header-n553:
705+
.. _header-n260:
666706

667707
Tutorial: Derivation of CNN from FCNN
668708
-------------------------------------
@@ -681,7 +721,7 @@ which is available at these links:
681721

682722
|image5|
683723

684-
.. _header-n563:
724+
.. _header-n270:
685725

686726
Book: Practical Computer Vision Applications Using Deep Learning with CNNs
687727
--------------------------------------------------------------------------
@@ -707,7 +747,7 @@ Find the book at these links:
707747
.. figure:: https://user-images.githubusercontent.com/16560492/78830077-ae7c2800-79e7-11ea-980b-53b6bd879eeb.jpg
708748
:alt:
709749

710-
.. _header-n578:
750+
.. _header-n285:
711751

712752
Contact Us
713753
==========

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /