pyerualjetwork 4.2.2b4__py3-none-any.whl → 4.2.2b5__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.2b4"
+__version__ = "4.2.2b5"
 __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

@@ -173,8 +173,8 @@ def fit(
     return normalization(LTPW, dtype=dtype)
 
 
-def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_size=1,
-           neural_web_history=False, show_current_activations=False,
+def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1,
+           neural_web_history=False, show_current_activations=False, auto_normalization=True,
            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):
@@ -203,6 +203,7 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         model = plan.learner(x_train,
                              y_train,
                              optimizer=genetic_optimizer,
+                             fit_start=True,
                              strategy='accuracy',
                              show_history=True,
                              gen=15,
@@ -210,6 +211,8 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
                              interval=16.67)
         ```
 
+        fit_start (bool): If the fit_start parameter is set to True, the initial generation population undergoes a simple short training process using the PLAN algorithm. This allows for a very robust starting point, especially for large and complex datasets. However, for small or relatively simple datasets, it may result in unnecessary computational overhead. When fit_start is True, completing the first generation may take slightly longer (this increase in computational cost applies only to the first generation and does not affect subsequent generations). If fit_start is set to False, the initial population will be entirely random. Options: True or False. The fit_start parameter is MANDATORY and must be provided.
+
         strategy (str, optional): Learning strategy. (options: 'accuracy', 'f1', 'precision', 'recall'): 'accuracy', Maximizes train (or test if given) accuracy during learning. 'f1', Maximizes train (or test if given) f1 score during learning. 'precision', Maximizes train (or test if given) precision score during learning. 'recall', Maximizes train (or test if given) recall during learning. Default is 'accuracy'.
 
         gen (int, optional): The generation count for genetic optimization.
@@ -218,6 +221,8 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
         early_stop (bool, optional): If True, implements early stopping during training.(If accuracy not improves in two gen stops learning.) Default is False.
 
+        auto_normalization (bool, optional): IMPORTANT: auto_nomralization parameter works only if fit_start is True. Do not change this value if fit_start is False, because it doesnt matter.) If auto normalization=False this makes more faster training times and much better accuracy performance for some datasets. Default is True.
+
         show_current_activations (bool, optional): Should it display the activations selected according to the current strategies during learning, or not? (True or False) This can be very useful if you want to cancel the learning process and resume from where you left off later. After canceling, you will need to view the live training activations in order to choose the activations to be given to the 'start_this' parameter. Default is False
 
         show_history (bool, optional): If True, displays the training history after optimization. Default is False.
@@ -249,8 +254,9 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     data = 'Train'
 
-    activation_potentiation_len = len(all_activations())
-
+    activation_potentiation = all_activations()
+    activation_potentiation_len = len(activation_potentiation)
+   
     # Pre-checks
 
     x_train = x_train.astype(dtype, copy=False)
@@ -261,6 +267,7 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     if strategy != 'accuracy' and strategy != 'f1' and strategy != 'recall' and strategy != 'precision': raise ValueError("Strategy parameter only be 'accuracy' or 'f1' or 'recall' or 'precision'.")
     if target_acc is not None and (target_acc < 0 or target_acc > 1): raise ValueError('target_acc must be in range 0 and 1')
+    if fit_start is not True and fit_start is not False: raise ValueError('fit_start parameter only be True or False. Please read doc-string')
 
     # Initialize visualization components
     viz_objects = initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train)
@@ -272,9 +279,6 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         ncols = 89
 
     # Initialize variables
-    act_pop = []
-    weight_pop = []
-
     best_acc = 0
     best_f1 = 0
     best_recall = 0
@@ -286,11 +290,16 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
 
-    weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len)
+    if fit_start is False:
+        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len, dtype=dtype)
     
-    if start_this_act is not None and start_this_W is not None:
-        weight_pop[0] = start_this_W
-        act_pop[0] = start_this_act
+        if start_this_act is not None and start_this_W is not None:
+            weight_pop[0] = start_this_W
+            act_pop[0] = start_this_act
+
+    else:
+        weight_pop = []
+        act_pop = []
 
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
@@ -303,6 +312,12 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         for j in range(activation_potentiation_len):
 
             x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
+            
+            if fit_start is True and i == 0:
+                act_pop.append(activation_potentiation[j])
+                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[-1], train_bar=False, auto_normalization=auto_normalization, dtype=dtype)
+                weight_pop.append(W)
+            
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], loading_bar_status=False, activation_potentiation=act_pop[j], dtype=dtype)
             acc = model[get_acc()]
             

pyerualjetwork/plan_cuda.py

@@ -188,8 +188,8 @@ def fit(
     return normalization(LTPW, dtype=dtype)
 
 
-def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_size=1,
-           neural_web_history=False, show_current_activations=False,
+def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1,
+           neural_web_history=False, show_current_activations=False, auto_normalization=True,
            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'):
@@ -218,13 +218,15 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         model = plan_cuda.learner(x_train,
                                 y_train,
                                 optimizer=genetic_optimizer,
+                                fit_start=True,
                                 strategy='accuracy',
                                 show_history=True,
                                 gen=15,
                                 batch_size=0.05,
                                 interval=16.67)
         ```
-
+        fit_start (bool): If the fit_start parameter is set to True, the initial generation population undergoes a simple short training process using the PLAN algorithm. This allows for a very robust starting point, especially for large and complex datasets. However, for small or relatively simple datasets, it may result in unnecessary computational overhead. When fit_start is True, completing the first generation may take slightly longer (this increase in computational cost applies only to the first generation and does not affect subsequent generations). If fit_start is set to False, the initial population will be entirely random. Options: True or False. The fit_start parameter is MANDATORY and must be provided.
+        
         strategy (str, optional): Learning strategy. (options: 'accuracy', 'f1', 'precision', 'recall'): 'accuracy', Maximizes train (or test if given) accuracy during learning. 'f1', Maximizes train (or test if given) f1 score during learning. 'precision', Maximizes train (or test if given) precision score during learning. 'recall', Maximizes train (or test if given) recall during learning. Default is 'accuracy'.
 
         gen (int, optional): The generation count for genetic optimization.
@@ -233,6 +235,8 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
         early_stop (bool, optional): If True, implements early stopping during training.(If train accuracy not improves in two gen stops learning.) Default is False.
 
+        auto_normalization (bool, optional): IMPORTANT: auto_nomralization parameter works only if fit_start is True. Do not change this value if fit_start is False, because it doesnt matter.) If auto normalization=False this makes more faster training times and much better accuracy performance for some datasets. Default is True.
+
         show_current_activations (bool, optional): Should it display the activations selected according to the current strategies during learning, or not? (True or False) This can be very useful if you want to cancel the learning process and resume from where you left off later. After canceling, you will need to view the live training activations in order to choose the activations to be given to the 'start_this' parameter. Default is False
 
         show_history (bool, optional): If True, displays the training history after optimization. Default is False.
@@ -266,7 +270,8 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     data = 'Train'
 
-    activation_potentiation_len = len(all_activations())
+    activation_potentiation = all_activations()
+    activation_potentiation_len = len(activation_potentiation)
 
     y_train = optimize_labels(y_train, cuda=True)
 
@@ -279,7 +284,7 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
     elif memory == 'cpu':
         x_train = transfer_to_cpu(x_train, dtype=dtype)
         y_train = transfer_to_cpu(y_train, dtype=y_train.dtype)
-        
+
         from .data_operations import batcher
 
     else:
@@ -287,7 +292,8 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     if strategy != 'accuracy' and strategy != 'f1' and strategy != 'recall' and strategy != 'precision': raise ValueError("Strategy parameter only be 'accuracy' or 'f1' or 'recall' or 'precision'.")
     if target_acc is not None and (target_acc < 0 or target_acc > 1): raise ValueError('target_acc must be in range 0 and 1')
-    
+    if fit_start is not True and fit_start is not False: raise ValueError('fit_start parameter only be True or False. Please read doc-string')
+
     # Initialize visualization components
     viz_objects = initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train)
 
@@ -298,9 +304,6 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         ncols = 99
 
     # Initialize variables
-    act_pop = []
-    weight_pop = []
-    
     best_acc = 0
     best_f1 = 0
     best_recall = 0
@@ -312,11 +315,16 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
 
     progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
 
-    weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len)
+    if fit_start is False:
+        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len, dtype=dtype)
     
-    if start_this_act is not None and start_this_W is not None:
-        weight_pop[0] = start_this_W
-        act_pop[0] = start_this_act
+        if start_this_act is not None and start_this_W is not None:
+            weight_pop[0] = start_this_W
+            act_pop[0] = start_this_act
+
+    else:
+        weight_pop = []
+        act_pop = []
 
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
@@ -329,6 +337,12 @@ def learner(x_train, y_train, optimizer, strategy='accuracy', gen=None, batch_si
         for j in range(activation_potentiation_len):
 
             x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
+            
+            if fit_start is True and i == 0:
+                act_pop.append(activation_potentiation[j])
+                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[-1], train_bar=False, auto_normalization=auto_normalization, dtype=dtype)
+                weight_pop.append(W)
+
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], loading_bar_status=False, activation_potentiation=act_pop[j], dtype=dtype, memory=memory)
             acc = model[get_acc()]
             

{pyerualjetwork-4.2.2b4.dist-info → pyerualjetwork-4.2.2b5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.2b4
+Version: 4.2.2b5
 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-4.2.2b4.dist-info → pyerualjetwork-4.2.2b5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=W84gU5_QHLqxGImXR7xeq2n_LiBCqtoHJTEGoLUPilI,641
+pyerualjetwork/__init__.py,sha256=jCSoAWmX1GCN4tOGRp2UsvgxojBEUi4abZxyxQ2ygl8,641
 pyerualjetwork/activation_functions.py,sha256=WWOdMd5pI6ZKe-ieKCIsKAYPQODHuXYxx7tzhA5xjes,11767
 pyerualjetwork/activation_functions_cuda.py,sha256=KmXJ5Cdig46XAMYakXFPEOlxSxtFJjD21-i3nGtxPjE,11807
 pyerualjetwork/data_operations.py,sha256=pb5CqJ0Th6fCjTNMCtqQMiwH3KezTxAijacglsKUxmY,14730
@@ -11,14 +11,14 @@ pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,607
 pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
 pyerualjetwork/model_operations.py,sha256=RKqnh7-MByFosxqme4q4jC1lOndX26O-OVXYV6ZxoEE,12965
 pyerualjetwork/model_operations_cuda.py,sha256=XnKKq54ZLaqCm-NaJ6d8IToACKcKg2Ttq6moowVRRWo,13365
-pyerualjetwork/plan.py,sha256=mACNJnHlPkeqsHDYw0BVDXp8PCOlwWsF-1KD4a2Bk7U,30431
-pyerualjetwork/plan_cuda.py,sha256=G4Lo7FnfHfmiv1mZdbT0-BWtjoWUyxViRj6xAj4Hwlc,31784
+pyerualjetwork/plan.py,sha256=tyV-Xtg6u_aVvPmBAdLct7GnTO73xbp9SHe011Tact0,32186
+pyerualjetwork/plan_cuda.py,sha256=uzLwJP31zy9qH5QUmbOFH6cv20h_8gwCpvubQTlYB-o,33517
 pyerualjetwork/planeat.py,sha256=hMSyrSPipOxKgOqyoAiZtniVgxPQxc4rRsvEEMOS2Ng,40757
 pyerualjetwork/planeat_cuda.py,sha256=9uopmM-gTZpSb0EOExrOZPT8FF5BqDdEfCX0zYQb9QU,40712
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=QaYSIyVkJZ8NqpBKArQKkI1y37nCQo_KIM98IMssnRc,28766
 pyerualjetwork/visualizations_cuda.py,sha256=F60vQ92AXlMgBka3InXnOtGoM25vQJAlBIU2AlYTwks,29200
-pyerualjetwork-4.2.2b4.dist-info/METADATA,sha256=z6eJ-HSJllMFcpo08y8wg7Ad1cyX0B04egOQqIjwSog,7914
-pyerualjetwork-4.2.2b4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.2b4.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.2b4.dist-info/RECORD,,
+pyerualjetwork-4.2.2b5.dist-info/METADATA,sha256=iCMk-fDHiW4yLCHSnWuDx7hJuGtdwWWD_MAUAoVmAmc,7914
+pyerualjetwork-4.2.2b5.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.2b5.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.2b5.dist-info/RECORD,,