pyerualjetwork 4.1.9b1__py3-none-any.whl → 4.2.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -48,7 +48,7 @@ for package_name in package_names:
48
48
 
49
49
  print(f"PyerualJetwork is ready to use with {err} errors")
50
50
 
51
- __version__ = "4.1.9b1"
51
+ __version__ = "4.2.0"
52
52
  __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf\n* YouTube tutorials: https://www.youtube.com/@HasanCanBeydili"
53
53
 
54
54
  def print_version(__version__):
@@ -11,7 +11,7 @@ def encode_one_hot(y_train, y_test=None, summary=False):
11
11
  Args:
12
12
  y_train (numpy.ndarray): Train label data.
13
13
  y_test (numpy.ndarray): Test label data one-hot encoded. (optional).
14
- summary (bool): If True, prints the class-to-index mapping. Default: False
14
+ summary (bool, optional): If True, prints the class-to-index mapping. Default: False
15
15
 
16
16
  Returns:
17
17
  tuple: One-hot encoded y_train and (if given) y_test.
pyerualjetwork/plan.py CHANGED
@@ -3,6 +3,8 @@
3
3
 
4
4
  MAIN MODULE FOR PLAN
5
5
 
6
+ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes
7
+
6
8
  PLAN document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PLAN/PLAN.pdf
7
9
  PYERUALJETWORK document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
8
10
 
@@ -16,7 +18,6 @@ PYERUALJETWORK document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
16
18
  import numpy as np
17
19
  from colorama import Fore
18
20
  import math
19
- import random
20
21
 
21
22
  ### LIBRARY IMPORTS ###
22
23
  from .ui import loading_bars, initialize_loading_bar
@@ -177,7 +178,7 @@ def learner(x_train, y_train, optimizer, x_test=None, y_test=None, strategy='acc
177
178
  neural_web_history=False, show_current_activations=False, auto_normalization=True,
178
179
  neurons_history=False, early_stop=False, loss='categorical_crossentropy', show_history=False,
179
180
  interval=33.33, target_acc=None, target_loss=None, except_this=None,
180
- only_this=None, start_this_act=None, start_this_W=None, target_fitness='max', pop_size=None, dtype=np.float32):
181
+ only_this=None, start_this_act=None, start_this_W=None, target_fitness='max', dtype=np.float32):
181
182
  """
182
183
  Optimizes the activation functions for a neural network by leveraging train data to find
183
184
  the most accurate combination of activation potentiation for the given dataset using genetic algorithm NEAT (Neuroevolution of Augmenting Topologies). But modifided for PLAN version. Created by me: PLANEAT.
@@ -282,15 +283,6 @@ def learner(x_train, y_train, optimizer, x_test=None, y_test=None, strategy='acc
282
283
  if gen is None:
283
284
  gen = len(activation_potentiation)
284
285
 
285
- default_act_list_length = len(activation_potentiation)
286
-
287
- if pop_size is not None and pop_size > len(activation_potentiation):
288
- for i in range(pop_size - len(activation_potentiation)):
289
- rand_index = random.randint(0, len(default_act_list_length)-1)
290
- activation_potentiation.append(all_activations()[rand_index])
291
-
292
- elif pop_size is not None and pop_size < len(activation_potentiation): raise ValueError(f"'pop_size' must be greater then activation_potentiation list length. But your act pot list length: {len(activation_potentiation)}")
293
-
294
286
  if strategy != 'accuracy' and strategy != 'f1' and strategy != 'recall' and strategy != 'precision': raise ValueError("Strategy parameter only be 'accuracy' or 'f1' or 'recall' or 'precision'.")
295
287
 
296
288
  if start_this_act is None and len(activation_potentiation) % 2 != 0: raise ValueError("Activation length must be even number. Please use 'except_this' parameter and except some activation. For example: except_this=['linear']")
@@ -3,6 +3,8 @@
3
3
 
4
4
  MAIN MODULE FOR PLAN_CUDA
5
5
 
6
+ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes
7
+
6
8
  PLAN document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PLAN/PLAN.pdf
7
9
  PYERUALJETWORK document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
8
10
 
@@ -14,7 +16,6 @@ PYERUALJETWORK document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
14
16
  """
15
17
 
16
18
  import cupy as cp
17
- import numpy as np
18
19
  from colorama import Fore
19
20
  import math
20
21