pyerualjetwork 4.3.9b0__py3-none-any.whl → 4.3.9b2__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.9b0"
+__version__ = "4.3.9b2"
 __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/plan.py

@@ -44,7 +44,7 @@ def fit(
     y_train,
     activation_potentiation=['linear'],
     W=None,
-    normalization=False,
+    auto_normalization=False,
     dtype=np.float32
 ):
     """
@@ -60,7 +60,7 @@ def fit(
 
         W (numpy.ndarray): If you want to re-continue or update model
 
-        normalization (bool, optional): Normalization may solves overflow problem. Default: False
+        auto_normalization (bool, optional): Normalization may solves overflow problem. Default: False
 
         dtype (numpy.dtype): Data type for the arrays. np.float32 by default. Example: np.float64 or np.float16. [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not reccomended!] (optional)
 
@@ -74,8 +74,8 @@ def fit(
 
     weight = np.zeros((len(y_train[0]), len(x_train[0].ravel()))).astype(dtype, copy=False) if W is None else W
 
-    if normalization is True: x_train = normalization(apply_activation(x_train, activation_potentiation))
-    elif normalization is False: x_train = apply_activation(x_train, activation_potentiation)
+    if auto_normalization is True: x_train = normalization(apply_activation(x_train, activation_potentiation))
+    elif auto_normalization is False: x_train = apply_activation(x_train, activation_potentiation)
     else: raise ValueError('normalization parameter only be True or False')
     
     weight += y_train.T @ x_train
@@ -84,7 +84,7 @@ def fit(
 
 
 def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1, pop_size=None,
-           neural_web_history=False, show_current_activations=False, normalization=False,
+           neural_web_history=False, show_current_activations=False, auto_normalization=False,
            neurons_history=False, early_stop=False, loss='categorical_crossentropy', show_history=False,
            interval=33.33, target_acc=None, target_loss=None,
            start_this_act=None, start_this_W=None, dtype=np.float32):
@@ -136,6 +136,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
         show_history (bool, optional): If True, displays the training history after optimization. Default is False.
 
+        auto_normalization (bool, optional): Normalization may solves overflow problem. Default: False
+
         loss (str, optional): For visualizing and monitoring. PLAN neural networks doesn't need any loss function in training. options: ('categorical_crossentropy' or 'binary_crossentropy') Default is 'categorical_crossentropy'.
 
         interval (int, optional): The interval at which evaluations are conducted during training. (33.33 = 30 FPS, 16.67 = 60 FPS) Default is 100.
@@ -229,7 +231,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
             
             if fit_start is True and i == 0 and j < activation_potentiation_len:
                 act_pop[j] = activation_potentiation[j]
-                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[j], normalization=normalization, dtype=dtype)
+                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[j], auto_normalization=auto_normalization, dtype=dtype)
                 weight_pop[j] = W
             
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activation_potentiation=act_pop[j])

pyerualjetwork/plan_cuda.py

@@ -44,7 +44,7 @@ def fit(
     y_train,
     activation_potentiation=['linear'],
     W=None,
-    normalization=False,
+    auto_normalization=False,
     dtype=cp.float32
 ):
     """
@@ -60,7 +60,7 @@ def fit(
 
         W (cupy.ndarray, optional): If you want to re-continue or update model
         
-        normalization (bool, optional): Normalization may solves overflow problem. Default: False
+        auto_normalization (bool, optional): Normalization may solves overflow problem. Default: False
 
         dtype (cupy.dtype, optional): Data type for the arrays. cp.float32 by default. Example: cp.float64 or cp.float16. [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not reccomended!] (optional)
 
@@ -73,8 +73,8 @@ def fit(
 
     weight = cp.zeros((len(y_train[0]), len(x_train[0].ravel()))).astype(dtype, copy=False) if W is None else W
 
-    if normalization is True: x_train = normalization(apply_activation(x_train, activation_potentiation))
-    elif normalization is False: x_train = apply_activation(x_train, activation_potentiation)
+    if auto_normalization is True: x_train = normalization(apply_activation(x_train, activation_potentiation))
+    elif auto_normalization is False: x_train = apply_activation(x_train, activation_potentiation)
     else: raise ValueError('normalization parameter only be True or False')
     
     weight += y_train.T @ x_train
@@ -83,7 +83,7 @@ def fit(
 
 
 def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1, pop_size=None,
-           neural_web_history=False, show_current_activations=False,
+           neural_web_history=False, show_current_activations=False, auto_normalization=False,
            neurons_history=False, early_stop=False, loss='categorical_crossentropy', show_history=False,
            interval=33.33, target_acc=None, target_loss=None,
            start_this_act=None, start_this_W=None, dtype=cp.float32, memory='gpu'):
@@ -136,6 +136,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
         loss (str, optional): For visualizing and monitoring. PLAN neural networks doesn't need any loss function in training. options: ('categorical_crossentropy' or 'binary_crossentropy') Default is 'categorical_crossentropy'.
 
+        auto_normalization (bool, optional): Normalization may solves overflow problem. Default: False
+        
         interval (int, optional): The interval at which evaluations are conducted during training. (33.33 = 30 FPS, 16.67 = 60 FPS) Default is 100.
     
         target_acc (int, optional): The target accuracy to stop training early when achieved. Default is None.
@@ -240,7 +242,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
             if fit_start is True and i == 0 and j < activation_potentiation_len:
                 act_pop[j] = activation_potentiation[j]
-                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[-1], dtype=dtype)
+                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[j], auto_normalization=auto_normalization, dtype=dtype)
                 weight_pop[j] = W
     
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activation_potentiation=act_pop[j])

{pyerualjetwork-4.3.9b0.dist-info → pyerualjetwork-4.3.9b2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.9b0
+Version: 4.3.9b2
 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-4.3.9b0.dist-info → pyerualjetwork-4.3.9b2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=mDFCFvWAMM7y9Es2Aopu_-rSQcBNfw0hhrdFX9xyCiw,641
+pyerualjetwork/__init__.py,sha256=Xq17ymoPeZ0UU0jM2XmXY2oG85-nGR6-4scDvbFco4I,641
 pyerualjetwork/activation_functions.py,sha256=bKf00lsuuLJNO-4vVp4OqBi4zJ-qZ8L3v-vl52notkY,7721
 pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
 pyerualjetwork/data_operations.py,sha256=Flteouu6rfSo2uHMqBHuzO02dXmbNa-I5qWmUpGTZ5Y,14760
@@ -11,14 +11,14 @@ pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,607
 pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
 pyerualjetwork/model_operations.py,sha256=MCSCNYiiICRVZITobtS3ZIWmH5Q9gjyELuH32sAdgg4,12649
 pyerualjetwork/model_operations_cuda.py,sha256=NT01BK5nrDYE7H1x3KnSI8gmx0QTGGB0mP_LqEb1uuU,13157
-pyerualjetwork/plan.py,sha256=rd6BOj6xU7m-nQgLQ0tH5oY5a78tTwW5spsX4niFUKU,23362
-pyerualjetwork/plan_cuda.py,sha256=NJq_KSbl7Q7wlie2NH7ApwJ36hfmzocXra36tgcO28w,24197
+pyerualjetwork/plan.py,sha256=yqtiPUTpvO-Ty8SRJd5RFdbIKMgGGGkMVxdgbVHhfjQ,23503
+pyerualjetwork/plan_cuda.py,sha256=4_AXa1IvDcqvHiK7CKbQXJBlO-UP6eVtK-ubDHmLGWk,24395
 pyerualjetwork/planeat.py,sha256=Lq5R0aMS4UIdZdbUKsKDv5g0WLwYryomR3IQYb8vAa4,37573
 pyerualjetwork/planeat_cuda.py,sha256=SG7Oq1F2m3lJBbG9cgmu7q_ApmwSn2SvTpcbtEVAoDE,37630
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=08O5uEewuYiovZRX1uHWEHjn19LcnhndWYvqVN74xs0,28290
 pyerualjetwork/visualizations_cuda.py,sha256=PYRqj4QYUbuYMYcNwO8yaTPB-jK7E6kZHhTrAi0lwPU,28749
-pyerualjetwork-4.3.9b0.dist-info/METADATA,sha256=pCQACKItpMxqwMfYJl3EHXsa7kA_ZwkWuz8e-FtDKcE,7476
-pyerualjetwork-4.3.9b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.3.9b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.3.9b0.dist-info/RECORD,,
+pyerualjetwork-4.3.9b2.dist-info/METADATA,sha256=AQn9V-32uZrqHfQXYB0DBx47o_K5-dBBhGzCKysiKgw,7476
+pyerualjetwork-4.3.9b2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.3.9b2.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.3.9b2.dist-info/RECORD,,