pyerualjetwork 4.3.8.dev7__tar.gz → 4.3.8.dev8__tar.gz

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.8.dev7
+Version: 4.3.8.dev8
 Summary: PyerualJetwork is a machine learning library supported with GPU(CUDA) acceleration written in Python for professionals and researchers including with PLAN algorithm, PLANEAT algorithm (genetic optimization). Also includes data pre-process and memory manegament
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.8dev7"
+__version__ = "4.3.8dev8"
 __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main\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"
 
 def print_version(__version__):

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.8.dev7
+Version: 4.3.8.dev8
 Summary: PyerualJetwork is a machine learning library supported with GPU(CUDA) acceleration written in Python for professionals and researchers including with PLAN algorithm, PLANEAT algorithm (genetic optimization). Also includes data pre-process and memory manegament
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/pyerualjetwork_afterburner/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.8dev7-afterburner"
+__version__ = "4.3.8dev8-afterburner"
 __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main\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"
 
 def print_version(__version__):

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/pyerualjetwork_afterburner/planeat_cuda.py

@@ -322,7 +322,14 @@ def evolver(weights,
                            weight_mutate_threshold=weight_mutate_threshold,
                            activation_mutate_threshold=activation_mutate_threshold)
       
-         pool.map(process_func, range(len(bad_weights)))
+      with mp.Pool() as pool:
+            results = pool.map(process_func, range(len(bad_weights)))
+         
+      for i, new_child_W, new_child_act, new_mutated_W, new_mutated_act in results:
+         child_W[i] = new_child_W
+         child_act[i] = new_child_act
+         mutated_W[i] = new_mutated_W
+         mutated_act[i] = new_mutated_act
 
    child_W[0] = best_weight
    child_act[0] = best_activations
@@ -367,39 +374,47 @@ def evolver(weights,
    return weights, activation_potentiations
 
 
-def process_single(i, policy, best_weight, best_activations, good_weights, good_activations, 
-                  bad_weights, bad_activations, best_fitness, normalized_fitness, child_W, child_act,
-                  mutated_W, mutated_act, cross_over_mode, 
-                  activation_selection_add_prob, activation_selection_change_prob,
-                  activation_selection_threshold, bad_genomes_selection_prob, fitness_bias,
-                  epsilon, bad_genomes_mutation_prob, activation_mutate_prob,
-                  activation_mutate_add_prob, activation_mutate_delete_prob,
-                  activation_mutate_change_prob, weight_mutate_prob, weight_mutate_threshold,
-                  activation_mutate_threshold):
+def process_single(i, policy, best_weight, best_activations, 
+                   good_weights, good_activations, 
+                   bad_weights, bad_activations, 
+                   best_fitness, normalized_fitness, 
+                   cross_over_mode, 
+                   activation_selection_add_prob, activation_selection_change_prob,
+                   activation_selection_threshold, 
+                   bad_genomes_selection_prob, fitness_bias,
+                   epsilon, bad_genomes_mutation_prob, 
+                   activation_mutate_prob, activation_mutate_add_prob,
+                   activation_mutate_delete_prob, activation_mutate_change_prob,
+                   weight_mutate_prob, weight_mutate_threshold,
+                   activation_mutate_threshold):
+
     if policy == 'aggressive':
         first_parent_W = best_weight
         first_parent_act = best_activations
     elif policy == 'explorer':
         first_parent_W = good_weights[i]
         first_parent_act = good_activations[i]
-    else: 
+    else:
         raise ValueError("policy parameter must be: 'aggressive' or 'explorer'")
         
-    second_parent_W, second_parent_act, s_i = second_parent_selection(good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
-    child_W[i], child_act[i] = cross_over(first_parent_W,
-                                         second_parent_W,
-                                         first_parent_act,
-                                         second_parent_act,
-                                         cross_over_mode=cross_over_mode,
-                                         activation_selection_add_prob=activation_selection_add_prob,
-                                         activation_selection_change_prob=activation_selection_change_prob,
-                                         activation_selection_threshold=activation_selection_threshold,
-                                         bad_genomes_selection_prob=bad_genomes_selection_prob,
-                                         first_parent_fitness=best_fitness,
-                                         fitness_bias=fitness_bias,
-                                         second_parent_fitness=normalized_fitness[s_i],
-                                         epsilon=epsilon
-                                         )
+    second_parent_W, second_parent_act, s_i = second_parent_selection(
+        good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
+
+    new_child_W, new_child_act = cross_over(
+        first_parent_W,
+        second_parent_W,
+        first_parent_act,
+        second_parent_act,
+        cross_over_mode=cross_over_mode,
+        activation_selection_add_prob=activation_selection_add_prob,
+        activation_selection_change_prob=activation_selection_change_prob,
+        activation_selection_threshold=activation_selection_threshold,
+        bad_genomes_selection_prob=bad_genomes_selection_prob,
+        first_parent_fitness=best_fitness,
+        fitness_bias=fitness_bias,
+        second_parent_fitness=normalized_fitness[s_i],
+        epsilon=epsilon
+    )
 
     mutation_prob = random.uniform(0, 1)
     if mutation_prob > bad_genomes_mutation_prob:
@@ -411,18 +426,22 @@ def process_single(i, policy, best_weight, best_activations, good_weights, good_
         genome_act = bad_activations[i]
         fitness_index = i
 
-    mutated_W[i], mutated_act[i] = mutation(genome_W,
-                                           genome_act,
-                                           activation_mutate_prob=activation_mutate_prob,
-                                           activation_add_prob=activation_mutate_add_prob,
-                                           activation_delete_prob=activation_mutate_delete_prob,
-                                           activation_change_prob=activation_mutate_change_prob,
-                                           weight_mutate_prob=weight_mutate_prob,
-                                           weight_mutate_threshold=weight_mutate_threshold,
-                                           genome_fitness=normalized_fitness[fitness_index],
-                                           activation_mutate_threshold=activation_mutate_threshold,
-                                           epsilon=epsilon
-                                           )
+    new_mutated_W, new_mutated_act = mutation(
+        genome_W,
+        genome_act,
+        activation_mutate_prob=activation_mutate_prob,
+        activation_add_prob=activation_mutate_add_prob,
+        activation_delete_prob=activation_mutate_delete_prob,
+        activation_change_prob=activation_mutate_change_prob,
+        weight_mutate_prob=weight_mutate_prob,
+        weight_mutate_threshold=weight_mutate_threshold,
+        genome_fitness=normalized_fitness[fitness_index],
+        activation_mutate_threshold=activation_mutate_threshold,
+        epsilon=epsilon
+    )
+    
+    return (i, new_child_W, new_child_act, new_mutated_W, new_mutated_act)
+
 
 def evaluate(x_population, weights, activation_potentiations):
    """

{pyerualjetwork-4.3.8.dev7 → pyerualjetwork-4.3.8.dev8}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 # Setting Up
 setup(
     name="pyerualjetwork",
-    version="4.3.8dev7",
+    version="4.3.8dev8",
     author="Hasan Can Beydili",
     author_email="tchasancan@gmail.com",
     description=(