pyerualjetwork 4.3.8.dev14__tar.gz → 4.3.8.dev15__tar.gz

{pyerualjetwork-4.3.8.dev14 → pyerualjetwork-4.3.8.dev15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.8.dev14
+Version: 4.3.8.dev15
 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.dev14 → pyerualjetwork-4.3.8.dev15}/pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.8dev14"
+__version__ = "4.3.8dev15"
 __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.dev14 → pyerualjetwork-4.3.8.dev15}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.8.dev14
+Version: 4.3.8.dev15
 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.dev14 → pyerualjetwork-4.3.8.dev15}/pyerualjetwork.egg-info/SOURCES.txt

@@ -38,6 +38,7 @@ pyerualjetwork_afterburner/metrics.py
 pyerualjetwork_afterburner/metrics_cuda.py
 pyerualjetwork_afterburner/model_operations.py
 pyerualjetwork_afterburner/model_operations_cuda.py
+pyerualjetwork_afterburner/parallel.py
 pyerualjetwork_afterburner/plan.py
 pyerualjetwork_afterburner/plan_cuda.py
 pyerualjetwork_afterburner/planeat.py

{pyerualjetwork-4.3.8.dev14 → pyerualjetwork-4.3.8.dev15}/pyerualjetwork_afterburner/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.8dev14-afterburner"
+__version__ = "4.3.8dev15-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.dev15/pyerualjetwork_afterburner/parallel.py

@@ -0,0 +1,118 @@
+import multiprocessing as mp
+from functools import partial
+import random
+from .planeat import mutation, cross_over, second_parent_selection
+
+def run_process(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):
+    
+    process_func = partial(process_single, policy=policy, best_weight=best_weight, 
+                           best_activations=best_activations, good_weights=good_weights, 
+                           good_activations=good_activations, bad_weights=bad_weights, 
+                           bad_activations=bad_activations, best_fitness=best_fitness, 
+                           normalized_fitness=normalized_fitness, child_W=child_W, 
+                           child_act=child_act, mutated_W=mutated_W, mutated_act=mutated_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,
+                           fitness_bias=fitness_bias,
+                           epsilon=epsilon,
+                           bad_genomes_mutation_prob=bad_genomes_mutation_prob,
+                           activation_mutate_prob=activation_mutate_prob,
+                           activation_mutate_add_prob=activation_mutate_add_prob,
+                           activation_mutate_delete_prob=activation_mutate_delete_prob,
+                           activation_mutate_change_prob=activation_mutate_change_prob,
+                           weight_mutate_prob=weight_mutate_prob,
+                           weight_mutate_threshold=weight_mutate_threshold,
+                           activation_mutate_threshold=activation_mutate_threshold)
+
+    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
+
+
+    return child_W, child_act, mutated_W, mutated_act
+
+
+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:
+        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)
+
+    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:
+        genome_W = good_weights[i]
+        genome_act = good_activations[i]
+        fitness_index = int(len(bad_weights) / 2 + i)
+    else:
+        genome_W = bad_weights[i]
+        genome_act = bad_activations[i]
+        fitness_index = i
+
+    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)

{pyerualjetwork-4.3.8.dev14 → pyerualjetwork-4.3.8.dev15}/pyerualjetwork_afterburner/planeat_cuda.py

@@ -221,6 +221,8 @@ def evolver(weights,
       - The function returns the updated weights and activations after processing based on the chosen strategy, policy, and mutation parameters.
 """
     
+   from .parallel import run_process
+
 ### ERROR AND CONFIGURATION CHECKS:
    if strategy == 'normal_selective':
       if bad_genomes_mutation_prob is None: bad_genomes_mutation_prob = 0.7 # EFFECTS MUTATION
@@ -294,39 +296,18 @@ def evolver(weights,
 
    mutated_W = cp.copy(bad_weights)
    mutated_act = bad_activations.copy()
-
-   mp.set_start_method("spawn", force=True)
    
-   process_func = partial(process_single, policy=policy, best_weight=best_weight, 
-                     best_activations=best_activations, good_weights=good_weights, 
-                     good_activations=good_activations, bad_weights=bad_weights, 
-                     bad_activations=bad_activations, best_fitness=best_fitness, 
-                     normalized_fitness=normalized_fitness, child_W=child_W, 
-                     child_act=child_act, mutated_W=mutated_W, mutated_act=mutated_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,
-                     fitness_bias=fitness_bias,
-                     epsilon=epsilon,
-                     bad_genomes_mutation_prob=bad_genomes_mutation_prob,
-                     activation_mutate_prob=activation_mutate_prob,
-                     activation_mutate_add_prob=activation_mutate_add_prob,
-                     activation_mutate_delete_prob=activation_mutate_delete_prob,
-                     activation_mutate_change_prob=activation_mutate_change_prob,
-                     weight_mutate_prob=weight_mutate_prob,
-                     weight_mutate_threshold=weight_mutate_threshold,
-                     activation_mutate_threshold=activation_mutate_threshold)
+   child_W, child_act, mutated_W, mutated_act = run_process(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)
    
-   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
@@ -371,75 +352,6 @@ 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, 
-                   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:
-        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)
-
-    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:
-        genome_W = good_weights[i]
-        genome_act = good_activations[i]
-        fitness_index = int(len(bad_weights) / 2 + i)
-    else:
-        genome_W = bad_weights[i]
-        genome_act = bad_activations[i]
-        fitness_index = i
-
-    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):
    """
     Evaluates the performance of a population of genomes, applying different activation functions 

{pyerualjetwork-4.3.8.dev14 → pyerualjetwork-4.3.8.dev15}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 # Setting Up
 setup(
     name="pyerualjetwork",
-    version="4.3.8dev14",
+    version="4.3.8dev15",
     author="Hasan Can Beydili",
     author_email="tchasancan@gmail.com",
     description=(