pyerualjetwork 2.7.4__py3-none-any.whl → 2.7.6__py3-none-any.whl

plan/plan.py

@@ -142,8 +142,6 @@ def fit(
 
         for Lindex, Layer in enumerate(layers):
 
-            neural_layer = normalization(neural_layer)
-
             if Layer == 'fex':
                 STPW[Lindex] = fex(neural_layer, STPW[Lindex], True, y[index], activation_potentiation)
 
@@ -493,64 +491,66 @@ def evaluate(
     Returns:
         tuple: A tuple containing the predicted labels and the accuracy of the model.
     """
+    try:
+        layers = ['fex']
 
-    layers = ['fex']
-
-    Wc = [0] * len(W)  # Wc = Weight copy
-    true = 0
-    y_preds = [-1] * len(y_test)
-    acc_list = []
-    
-    for i, w in enumerate(W):
-        Wc[i] = np.copy(w)
-        
+        Wc = [0] * len(W)  # Wc = Weight copy
+        true = 0
+        y_preds = [-1] * len(y_test)
+        acc_list = []
         
-    if bar_status == True:
+        for i, w in enumerate(W):
+            Wc[i] = np.copy(w)
+            
+            
+        if bar_status == True:
 
-        test_progress = tqdm(total=len(x_test),leave=False, desc='Testing',ncols=120)
-        acc_bar = tqdm(total=1, desc="Test Accuracy", ncols=120)
+            test_progress = tqdm(total=len(x_test),leave=False, desc='Testing',ncols=120)
+            acc_bar = tqdm(total=1, desc="Test Accuracy", ncols=120)
+            
         
-    
-    for inpIndex, Input in enumerate(x_test):
-        Input = np.array(Input)
-        Input = Input.ravel()
-        neural_layer = Input
+        for inpIndex, Input in enumerate(x_test):
+            Input = np.array(Input)
+            Input = Input.ravel()
+            neural_layer = Input
 
-        for index, Layer in enumerate(layers):
+            for index, Layer in enumerate(layers):
 
-            neural_layer = normalization(neural_layer)
+                if Layer == 'fex':
+                    neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
 
-            if Layer == 'fex':
-                neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
 
+            for i, w in enumerate(Wc):
+                W[i] = np.copy(w)
+            RealOutput = np.argmax(y_test[inpIndex])
+            PredictedOutput = np.argmax(neural_layer)
+            if RealOutput == PredictedOutput:
+                true += 1
+            acc = true / len(y_test)
 
-        for i, w in enumerate(Wc):
-            W[i] = np.copy(w)
-        RealOutput = np.argmax(y_test[inpIndex])
-        PredictedOutput = np.argmax(neural_layer)
-        if RealOutput == PredictedOutput:
-            true += 1
-        acc = true / len(y_test)
 
+            acc_list.append(acc)
+            y_preds[inpIndex] = PredictedOutput
+            
+            if bar_status == True:
+                test_progress.update(1)
+                if inpIndex == 0:
+                    acc_bar.update(acc)
+                    
+                else:
+                    acc = acc - acc_list[inpIndex - 1]
+                    acc_bar.update(acc)
 
-        acc_list.append(acc)
-        y_preds[inpIndex] = PredictedOutput
+        if show_metrices == True:
+            plot_evaluate(y_test, y_preds, acc_list)
         
-        if bar_status == True:
-            test_progress.update(1)
-            if inpIndex == 0:
-                acc_bar.update(acc)
-                
-            else:
-                acc = acc - acc_list[inpIndex - 1]
-                acc_bar.update(acc)
-
-    if show_metrices == True:
-        plot_evaluate(y_test, y_preds, acc_list)
+        
+        for i, w in enumerate(Wc):
+            W[i] = np.copy(w)
     
+    except:
     
-    for i, w in enumerate(Wc):
-        W[i] = np.copy(w)
+        print(Fore.RED + 'ERROR:' + infoTestModel + Style.RESET_ALL)
 
     return W, y_preds, acc
 
@@ -936,9 +936,7 @@ def predict_model_ssd(Input, model_name, model_path):
         neural_layer = np.array(neural_layer)
         neural_layer = neural_layer.ravel()
         for index, Layer in enumerate(layers):
-
-            neural_layer = normalization(neural_layer)
-
+        
             if Layer == 'fex':
                 neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
             elif Layer == 'cat':
@@ -985,8 +983,6 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=None
         neural_layer = neural_layer.ravel()
         for index, Layer in enumerate(layers):
 
-            neural_layer = normalization(neural_layer)
-
             if Layer == 'fex':
                 neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
             elif Layer == 'cat':
@@ -1099,7 +1095,7 @@ def synthetic_augmentation(x_train, y_train):
     return np.array(x_balanced), np.array(y_balanced)
 
 
-def standard_scaler(x_train, x_test, scaler_params=None):
+def standard_scaler(x_train, x_test=None, scaler_params=None):
     info_standard_scaler = """
   Standardizes training and test datasets. x_test may be None.
 
@@ -1107,7 +1103,7 @@ def standard_scaler(x_train, x_test, scaler_params=None):
     train_data: numpy.ndarray
       Training data
     test_data: numpy.ndarray
-      Test data
+      Test data (optional)
 
   Returns:
     list:
@@ -1161,7 +1157,7 @@ def standard_scaler(x_train, x_test, scaler_params=None):
 
     except:
         print(
-            Fore.RED + "ERROR: x_train and x_test must be list[numpyarray] from standard_scaler" + info_standard_scaler)
+            Fore.RED + "ERROR: x_train and x_test must be list[numpyarray] from standard_scaler" + info_standard_scaler + Style.RESET_ALL)
 
 
 def encode_one_hot(y_train, y_test):

{pyerualjetwork-2.7.4.dist-info → pyerualjetwork-2.7.6.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 2.7.4
-Summary: Optimized for Vs Code
+Version: 2.7.6
+Summary: Changes in standard_scaler function paramter: x_test default value=None. Now x_test parameter is optional
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
 Keywords: model evaluation,classifcation,potentiation learning artficial neural networks

pyerualjetwork-2.7.6.dist-info/RECORD

@@ -0,0 +1,6 @@
+plan/__init__.py,sha256=gmaz8lnQfl18MbOQwabBUPmShajK5S99jfyY-hQe8tc,502
+plan/plan.py,sha256=W313lck6zriETEMWyeC431ixdZQunOgque9iVPtjLks,52869
+pyerualjetwork-2.7.6.dist-info/METADATA,sha256=6BjTKUIx_jU1kacIXqY9nuDAHRWeAwzZbAO5M152tis,332
+pyerualjetwork-2.7.6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-2.7.6.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
+pyerualjetwork-2.7.6.dist-info/RECORD,,

pyerualjetwork-2.7.4.dist-info/RECORD

@@ -1,6 +0,0 @@
-plan/__init__.py,sha256=gmaz8lnQfl18MbOQwabBUPmShajK5S99jfyY-hQe8tc,502
-plan/plan.py,sha256=t4Vghx1DcMYYzdzzdnd3G_fJobkJvNXVYMKAORJW8is,52772
-pyerualjetwork-2.7.4.dist-info/METADATA,sha256=RJUQ5bKgoOSby1F9unDSKicejquxNMMZFRfdV1meZxY,248
-pyerualjetwork-2.7.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-2.7.4.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
-pyerualjetwork-2.7.4.dist-info/RECORD,,