pyerualjetwork 5.46__tar.gz → 5.47b0__tar.gz

{pyerualjetwork-5.46 → pyerualjetwork-5.47b0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.46
+Version: 5.47b0
 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-5.46 → pyerualjetwork-5.47b0}/pyerualjetwork/__init__.py

@@ -42,7 +42,7 @@ PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
 - Contact: tchasancan@gmail.com
 """
 
-__version__ = "5.46"
+__version__ = "5.47b0"
 __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-5.46 → pyerualjetwork-5.47b0}/pyerualjetwork/cpu/visualizations.py

@@ -275,7 +275,7 @@ def draw_activations(x_train, activation):
         return x_train
 
 
-def plot_evaluate(x_test, y_test, y_preds, model, cuda=False):
+def plot_evaluate(x_test, y_test, y_preds, model, acc, cuda=False):
     
     if not cuda:
         from .metrics import metrics, confusion_matrix, roc_curve
@@ -287,8 +287,6 @@ def plot_evaluate(x_test, y_test, y_preds, model, cuda=False):
     
     from ..model_ops import predict_from_memory
 
-    acc = model.accuracy
-
     y_true = decode_one_hot(y_test)
     y_preds = decode_one_hot(y_preds)
     

{pyerualjetwork-5.46 → pyerualjetwork-5.47b0}/pyerualjetwork/nn.py

@@ -314,12 +314,17 @@ def learn(x_train, y_train, optimizer, template_model, gen, pop_size, fit_start=
       # TRANSFORMATION PLAN TO MLP FOR PTNN (in later generations)
         if model_type == 'PLAN' and transfer_learning:
             if i == gen_copy[0]:
+                
+                if cuda:
+                    array_type = cp
+                else:
+                    array_type = np
 
                 model_type = 'PTNN'
                 neurons = neurons_copy
 
                 for individual in range(len(weight_pop)):
-                    weight_pop[individual] = np.copy(best_weight)
+                    weight_pop[individual] = array_type.copy(best_weight)
                     activation_potentiations[individual] = final_activations.copy() if isinstance(final_activations, list) else final_activations
 
                 activation_potentiation = activation_potentiations[0]
@@ -333,13 +338,13 @@ def learn(x_train, y_train, optimizer, template_model, gen, pop_size, fit_start=
                 for l in range(1, len(weight_pop[0])):
                     original_shape = weight_pop[0][l].shape
 
-                    identity_matrix = np.eye(original_shape[0], original_shape[1], dtype=weight_pop[0][l].dtype)
+                    identity_matrix = array_type.eye(original_shape[0], original_shape[1], dtype=weight_pop[0][l].dtype)
                     weight_pop[0][l] = identity_matrix
                     
                 for l in range(len(weight_pop)):
-                    weight_pop[l][0] = np.copy(best_weight)
+                    weight_pop[l][0] = array_type.copy(best_weight)
 
-                best_weight = np.array(weight_pop[0], dtype=object)
+                best_weight = array_type.array(weight_pop[0], dtype=object)
                 final_activations = act_pop[0]
                 is_mlp = True
                 fit_start = False
@@ -684,6 +689,6 @@ def evaluate(
     softmax_preds = array_type.exp(result - max_vals) / array_type.sum(array_type.exp(result - max_vals), axis=1, keepdims=True)
     accuracy = (array_type.argmax(softmax_preds, axis=1) == array_type.argmax(y_test, axis=1)).mean()
 
-    if show_report: plot_evaluate(x_test, y_test, result, model=model, cuda=cuda)
+    if show_report: plot_evaluate(x_test, y_test, result, acc=accuracy, model=model, cuda=cuda)
 
     return W, result, accuracy, None, None, softmax_preds

{pyerualjetwork-5.46 → pyerualjetwork-5.47b0}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.46
+Version: 5.47b0
 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-5.46 → pyerualjetwork-5.47b0}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 # Setting Up
 setup(
     name="pyerualjetwork",
-    version="5.46",
+    version="5.47b0",
     author="Hasan Can Beydili",
     author_email="tchasancan@gmail.com",
     description=(