pyerualjetwork 5.21b3__tar.gz → 5.22__tar.gz

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.21b3
+Version: 5.22
 Summary: PyereualJetwork is a GPU-accelerated machine learning library in Python for professionals and researchers. It features PLAN, MLP, Deep Learning training, and ENE (Eugenic NeuroEvolution) for genetic optimization, applicable to genetic algorithms or Reinforcement Learning (RL). The library includes data pre-processing, visualizations, model saving/loading, prediction, evaluation, training, and detailed or simplified memory management.
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/pyerualjetwork/__init__.py

@@ -42,7 +42,7 @@ PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
 - Contact: tchasancan@gmail.com
 """
 
-__version__ = "5.21b3"
+__version__ = "5.22"
 __update__ = """* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES
 * PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main
 * PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/pyerualjetwork/activation_functions_cuda.py

@@ -1,4 +1,5 @@
 import cupy as cp
+import numpy as np
 from scipy.special import expit, softmax
 import warnings
 
@@ -198,10 +199,16 @@ def apply_activation(Input, activation_list):
         'spiral': spiral_activation,
         'circular': circular_activation
     }
+    
+    try:
+        
+        valid_mask = cp.array([act in activation_functions for act in activation_list])
+        valid_activations = np.array(activation_list)[valid_mask.get()]
 
-    valid_mask = cp.array([act in activation_functions for act in activation_list])
-    valid_activations = cp.array(activation_list)[valid_mask]
-
-    activation_outputs = cp.array([activation_functions[act](origin_input) for act in valid_activations])
+        activation_outputs = cp.array([activation_functions[act](origin_input) for act in valid_activations])
 
-    return cp.sum(activation_outputs, axis=0)
+        return cp.sum(activation_outputs, axis=0)
+        
+    except Exception as e:
+        warnings.warn(f"Error in activation processing: {str(e)}", RuntimeWarning)
+        return Input

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/pyerualjetwork/neu_cpu.py

@@ -340,17 +340,17 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
 
             if fitness >= best_fitness:
 
-                best_fitness = fitness
-                best_acc = acc
-                best_loss = train_loss
+                best_fitness = copy.copy(fitness)
+                best_acc = copy.copy(acc)
+                best_loss = copy.copy(train_loss)
                 best_weight = np.copy(weight_pop[j]) if model_type == 'PLAN' else copy.deepcopy(weight_pop[j])
-                best_model = model
+                best_model = copy.deepcopy(model)
 
                 final_activations = act_pop[j].copy() if isinstance(act_pop[j], list) else act_pop[j]
                 if model_type == 'PLAN': final_activations = [final_activations[0]] if len(set(final_activations)) == 1 else final_activations # removing if all same
 
                 if batch_size == 1:
-                    postfix_dict[f"{data} Accuracy"] = np.round(best_acc, 4)
+                    postfix_dict[f"{data} Accuracy"] = np.round(best_acc)
                     postfix_dict[f"{data} Loss"] = np.round(train_loss, 4)
                     progress.set_postfix(postfix_dict)
 

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/pyerualjetwork/neu_cuda.py

@@ -351,11 +351,11 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
 
             if fitness >= best_fitness:
 
-                best_fitness = fitness
-                best_acc = acc
-                best_loss = train_loss
+                best_fitness = copy.copy(fitness)
+                best_acc = copy.copy(acc)
+                best_loss = copy.copy(train_loss)
                 best_weight = cp.copy(weight_pop[j]) if model_type == 'PLAN' else copy.deepcopy(weight_pop[j])
-                best_model = model
+                best_model = copy.deepcopy(model)
 
                 final_activations = act_pop[j].copy() if isinstance(act_pop[j], list) else act_pop[j]
                 if model_type == 'PLAN': final_activations = [final_activations[0]] if len(set(final_activations)) == 1 else final_activations # removing if all same

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.21b3
+Version: 5.22
 Summary: PyereualJetwork is a GPU-accelerated machine learning library in Python for professionals and researchers. It features PLAN, MLP, Deep Learning training, and ENE (Eugenic NeuroEvolution) for genetic optimization, applicable to genetic algorithms or Reinforcement Learning (RL). The library includes data pre-processing, visualizations, model saving/loading, prediction, evaluation, training, and detailed or simplified memory management.
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-5.21b3 → pyerualjetwork-5.22}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 # Setting Up
 setup(
     name="pyerualjetwork",
-    version="5.21b3",
+    version="5.22",
     author="Hasan Can Beydili",
     author_email="tchasancan@gmail.com",
     description=(