pyerualjetwork 4.3.9b2__tar.gz → 4.3.9b4__tar.gz

{pyerualjetwork-4.3.9b2 → pyerualjetwork-4.3.9b4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.9b2
+Version: 4.3.9b4
 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-4.3.9b2 → pyerualjetwork-4.3.9b4}/pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.9b2"
+__version__ = "4.3.9b4"
 __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-4.3.9b2 → pyerualjetwork-4.3.9b4}/pyerualjetwork/plan.py

@@ -188,12 +188,6 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
     # Initialize visualization components
     viz_objects = initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train)
 
-    # Initialize progress bar
-    if batch_size == 1:
-        ncols = 78
-    else:
-        ncols = 49
-
     # Initialize variables
     best_acc = 0
     best_f1 = 0
@@ -204,7 +198,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
     loss_list = []
     target_pop = []
 
-    progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
+    progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=78, bar_format=bar_format_learner)
 
     if fit_start is False or pop_size > activation_potentiation_len:
         weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=pop_size, dtype=dtype)
@@ -357,9 +351,6 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
             progress.update(1)
 
-        best_acc_per_gen_list.append(best_acc)
-        loss_list.append(best_loss)
-
         if batch_size != 1:
             train_model = evaluate(x_train, y_train, best_weights, final_activations)
             
@@ -373,6 +364,13 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
             postfix_dict[f"{data} Accuracy"] = np.round(train_model[get_acc()], 4)
             postfix_dict[f"{data} Loss"] = np.round(train_loss, 4)
             progress.set_postfix(postfix_dict)
+            
+            best_acc_per_gen_list.append(train_model[get_acc()])
+            loss_list.append(train_loss)
+
+        else:
+            best_acc_per_gen_list.append(best_acc)
+            loss_list.append(best_loss)
 
         weight_pop, act_pop = optimizer(np.array(weight_pop, copy=False, dtype=dtype), act_pop, i, np.array(target_pop, dtype=dtype, copy=False), bar_status=False)
         target_pop = []

{pyerualjetwork-4.3.9b2 → pyerualjetwork-4.3.9b4}/pyerualjetwork/plan_cuda.py

@@ -196,12 +196,6 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
     # Initialize visualization components
     viz_objects = initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train)
 
-    # Initialize progress bar
-    if batch_size == 1:
-        ncols = 76
-    else:
-        ncols = 49
-
     # Initialize variables
     best_acc = 0
     best_f1 = 0
@@ -212,7 +206,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
     loss_list = []
     target_pop = []
 
-    progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
+    progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=78, bar_format=bar_format_learner)
 
     if fit_start is False or pop_size > activation_potentiation_len:
         weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=pop_size, dtype=dtype)
@@ -367,22 +361,26 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                     return best_weights, best_model[get_preds()], best_acc, final_activations
 
             progress.update(1)
-
-        best_acc_per_gen_list.append(best_acc)
-        loss_list.append(best_loss)
         
         if batch_size != 1:
             train_model = evaluate(x_train, y_train, best_weights, final_activations)
             
             if loss == 'categorical_crossentropy':
-                train_loss = categorical_crossentropy(y_true_batch=transfer_to_gpu(y_train_batch, dtype=y_train_batch.dtype), y_pred_batch=train_model[get_preds_softmax()])
+                train_loss = categorical_crossentropy(y_true_batch=transfer_to_gpu(y_train, dtype=y_train.dtype), y_pred_batch=train_model[get_preds_softmax()])
             else:
-                train_loss = binary_crossentropy(y_true_batch=transfer_to_gpu(y_train_batch, dtype=y_train_batch.dtype), y_pred_batch=train_model[get_preds_softmax()])
+                train_loss = binary_crossentropy(y_true_batch=transfer_to_gpu(y_train, dtype=y_train.dtype), y_pred_batch=train_model[get_preds_softmax()])
 
             postfix_dict[f"{data} Accuracy"] = cp.round(train_model[get_acc()], 4)
             postfix_dict[f"{data} Loss"] = cp.round(train_loss, 4)
             progress.set_postfix(postfix_dict)
 
+            best_acc_per_gen_list.append(train_model[get_acc()])
+            loss_list.append(train_loss)
+
+        else:
+            best_acc_per_gen_list.append(best_acc)
+            loss_list.append(best_loss)
+
         weight_pop, act_pop = optimizer(cp.array(weight_pop, copy=False, dtype=dtype), act_pop, i, cp.array(target_pop, dtype=dtype, copy=False), bar_status=False)
         target_pop = []
 

{pyerualjetwork-4.3.9b2 → pyerualjetwork-4.3.9b4}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.9b2
+Version: 4.3.9b4
 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-4.3.9b2 → pyerualjetwork-4.3.9b4}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 # Setting Up
 setup(
     name="pyerualjetwork",
-    version="4.3.9b2",
+    version="4.3.9b4",
     author="Hasan Can Beydili",
     author_email="tchasancan@gmail.com",
     description=(