pyerualjetwork 4.2.2b7__py3-none-any.whl → 4.2.2b8__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.2b7"
+__version__ = "4.2.2b8"
 __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

@@ -298,8 +298,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
             act_pop[0] = start_this_act
 
     else:
-        weight_pop = [0] * activation_potentiation_len
-        act_pop = [0] * activation_potentiation_len
+        weight_pop = []
+        act_pop = []
 
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
@@ -314,9 +314,9 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
             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[j] = activation_potentiation[j]
-                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[j], train_bar=False, auto_normalization=auto_normalization, dtype=dtype)
-                weight_pop[j] = W
+                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()]
@@ -448,7 +448,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         best_acc_per_gen_list.append(best_acc)
         loss_list.append(best_loss)
 
-        weight_pop, act_pop = optimizer(weight_pop, act_pop, i, np.array(target_pop, dtype=dtype, copy=False), bar_status=False)
+        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 = []
 
         # Early stopping check

pyerualjetwork/plan_cuda.py

@@ -325,7 +325,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
     else:
         weight_pop = [0] * activation_potentiation_len
         act_pop = [0] * activation_potentiation_len
-        
+
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
         progress.set_postfix(postfix_dict)
@@ -339,9 +339,9 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
             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[j] = activation_potentiation[j]
-                W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[j], train_bar=False, auto_normalization=auto_normalization, dtype=dtype)
-                weight_pop[j] = W
+                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()]
@@ -473,7 +473,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         best_acc_per_gen_list.append(best_acc)
         loss_list.append(best_loss)
         
-        weight_pop, act_pop = optimizer(weight_pop, act_pop, i, cp.array(target_pop, dtype=dtype, copy=False), bar_status=False)
+        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 = []
 
         # Early stopping check

{pyerualjetwork-4.2.2b7.dist-info → pyerualjetwork-4.2.2b8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.2b7
+Version: 4.2.2b8
 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-4.2.2b7.dist-info → pyerualjetwork-4.2.2b8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=IqIUtgpCoSH1nzhkVeXdgxb_pVEc5sqnDG8buT6V9YE,641
+pyerualjetwork/__init__.py,sha256=0Id4J2KzevWmG5jp6CTWKK1Q8ocFLbeykDNdeD3YE2w,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=ziNRJu3_gjhUkpT62UY1jF4Fp1Go3lKzRYMTFNpV-kE,32241
-pyerualjetwork/plan_cuda.py,sha256=eb_VXp8Ko-EMBvjZnjyEbiFNeFME8fWAGKUzbrBAsyI,33581
+pyerualjetwork/plan.py,sha256=-Dz9yuqnx8sS5i9R6ihapXB1AEnqwDtaJ_GT-U-Qn6g,32221
+pyerualjetwork/plan_cuda.py,sha256=tfSld2_ywbO4E7kWarXHRHDHrYnhncqPAbugibP83uQ,33615
 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-4.2.2b7.dist-info/METADATA,sha256=Gmqa7h7GEftgIRXymUN5J6PFcpKKVKobH_RAqTL1nus,7914
-pyerualjetwork-4.2.2b7.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.2b7.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.2b7.dist-info/RECORD,,
+pyerualjetwork-4.2.2b8.dist-info/METADATA,sha256=rFdR676Cso9h1TtZusy4e1SlOj4XhPHSB7H0yRi9r-U,7914
+pyerualjetwork-4.2.2b8.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.2b8.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.2b8.dist-info/RECORD,,