pyerualjetwork 5.21b3__py3-none-any.whl → 5.23__py3-none-any.whl

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__ = "5.23"
 __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/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/ene_cpu.py

@@ -350,14 +350,14 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = np.copy(good_weights[-1]) if is_mlp is False else copy.deepcopy(good_weights[-1])
+   best_w = np.copy(good_weights[-1]) if is_mlp is False else copy.deepcopy(good_weights[-1])
 
    good_activations = list(activations[slice_center:])
    bad_activations = list(activations[:slice_center])
    best_activations = good_activations[-1].copy() if isinstance(good_activations[-1], list) else good_activations[-1]
 
    
-### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
+### ENE IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
    
    bar_format = loading_bars()[0]
    
@@ -377,7 +377,7 @@ def evolver(weights,
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
-         first_parent_W = np.copy(best_weight)
+         first_parent_W = np.copy(best_w)
          first_parent_act = best_activations
          first_parent_fitness = best_fitness
 
@@ -489,7 +489,7 @@ def evolver(weights,
    activations = child_act + mutated_act
 
    if save_best_genome:
-      weights[0] = best_weight
+      weights[0] = best_w
       activations[0] = best_activations
    
    ### INFO PRINTING CONSOLE

pyerualjetwork/ene_cuda.py

@@ -359,7 +359,7 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = cp.copy(good_weights[-1])
+   best_w = cp.copy(good_weights[-1])
 
    good_activations = list(activations[slice_center:])
    bad_activations = list(activations[:slice_center])
@@ -386,7 +386,7 @@ def evolver(weights,
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
-         first_parent_W = best_weight
+         first_parent_W = best_w
          first_parent_act = best_activations
          first_parent_fitness = best_fitness
 
@@ -507,7 +507,7 @@ def evolver(weights,
    activations = child_act + mutated_act
 
    if save_best_genome:
-      weights[0] = best_weight
+      weights[0] = best_w
       activations[0] = best_activations
 
    ### INFO PRINTING CONSOLE

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/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.dist-info → pyerualjetwork-5.23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.21b3
+Version: 5.23
 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.dist-info → pyerualjetwork-5.23.dist-info}/RECORD

@@ -1,10 +1,10 @@
-pyerualjetwork/__init__.py,sha256=aRxGI8UCxFA-7jU1KO9dkcKGbvv7vEeu2a7bsJFyFnA,2735
+pyerualjetwork/__init__.py,sha256=qIF9HJ9AxMRQJGKHVldVEvqUGLLxXWsE9a5APx8bdFg,2733
 pyerualjetwork/activation_functions_cpu.py,sha256=qP_Ipi2-c5tyJ7Jb9gWJZCj2AgeOIzLBdoEqQOUXD-s,5885
-pyerualjetwork/activation_functions_cuda.py,sha256=tjizlWkpXlA5DR8yD5CGI1b6j2yCn8vdrMrUMm6_r8I,5491
+pyerualjetwork/activation_functions_cuda.py,sha256=7ZN54w4VP0MtFh0LjAUHsuPNgVOxrKeqEwa_zNbRp4g,5699
 pyerualjetwork/data_operations_cpu.py,sha256=HemqiYfSdlQKTTYNzpCh_9lTtS3AimMI4DvqJBAGjGw,16186
 pyerualjetwork/data_operations_cuda.py,sha256=5zgyJGPjQuHyx6IHNkRwMguYhm-GcI6Hal49WNvw-bM,18536
-pyerualjetwork/ene_cpu.py,sha256=2y5__d-vx7t5Ajs4IPuNnQe8ULR39Km_KQFNIUnalGA,45167
-pyerualjetwork/ene_cuda.py,sha256=dWavZydKL9b5BAGL430SuWs1TenMelbFtltoEAXKkJY,45673
+pyerualjetwork/ene_cpu.py,sha256=EI0GmfSNwfebQ11Qdc8KPD7-Gp7578uWSei5mzdf3pk,45148
+pyerualjetwork/ene_cuda.py,sha256=5OvuIlEKnoXlv7AGkWbFLDO0EtN343ZHRpDWwC4KzwQ,45658
 pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
 pyerualjetwork/help.py,sha256=FcX8mxo1_mvoqONVXY0Kn7S09CDkhi0jwNmn8g9mYZc,804
 pyerualjetwork/issue_solver.py,sha256=iY6hSsBxYI5l82RwnXQp2DrRUJyksk_7U9GUSnt2YfU,3117
@@ -15,12 +15,12 @@ pyerualjetwork/metrics_cpu.py,sha256=vbfMwS0ay2heMSa0GNo-ydLjQ8cfexbLwaREp4FKAtY
 pyerualjetwork/metrics_cuda.py,sha256=PWyJyexeqlPKb09LAcF55JvhZVeXLCu3P_siYq5m2gg,5065
 pyerualjetwork/model_operations_cpu.py,sha256=Y0uPkLVbdodP7lC-fOPdja3RWi2J9z2rwWIS2pxzotU,20523
 pyerualjetwork/model_operations_cuda.py,sha256=B6vNYmqvrEJ3ZMGE1RWeJYn3V-JCsXhCHvS-aX4bWuU,21254
-pyerualjetwork/neu_cpu.py,sha256=4jjW9xIuB5WKJRMAR0BgkUra3OYERfUhehbqeYFgiIA,31197
-pyerualjetwork/neu_cuda.py,sha256=nK74JgfyJDbaPmSR1CmtZc_PaSKk0FeFmNcWHe5-8U0,32354
+pyerualjetwork/neu_cpu.py,sha256=X-AyTRSqBi29c3zxXO0nI2QRVZy8_UGR_nLkW06RCzE,31242
+pyerualjetwork/neu_cuda.py,sha256=wrgFSCaQeF6b3Bu7teLjCaYVNT9rdU4mVk3tYSKuG54,32402
 pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
 pyerualjetwork/visualizations_cpu.py,sha256=StyD1Hl1Gt55EMqR6tO3yVJZdPyGkOgCnQ75Zn8K6J8,28252
 pyerualjetwork/visualizations_cuda.py,sha256=7lYrkOdrjwQGB3T4k_vI8UDxsm_TRjzaSSg9GhlNczs,28667
-pyerualjetwork-5.21b3.dist-info/METADATA,sha256=Y4mrOstyyOAnOK0UBps6Rii24PVywgDNn_Lpcu8eBmA,8135
-pyerualjetwork-5.21b3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-5.21b3.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-5.21b3.dist-info/RECORD,,
+pyerualjetwork-5.23.dist-info/METADATA,sha256=ER2rHvFUdwwB8SUtRtV4EaimhnrlHrA1G_6erLB17Rg,8133
+pyerualjetwork-5.23.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-5.23.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-5.23.dist-info/RECORD,,