pyerualjetwork 4.6.6__py3-none-any.whl → 4.6.8b0__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.6.6"
+__version__ = "4.6.8b0"
 __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/activation_functions.py

@@ -7,7 +7,7 @@ import warnings
 
 def all_activations():
     
-    activations_list = ['linear', 'sigmoid', 'relu', 'tanh', 'circular', 'spiral', 'swish', 'sin_plus', 'mod_circular', 'tanh_circular', 'leaky_relu', 'softplus', 'elu', 'gelu', 'selu', 'sinakt', 'p_squared', 'sglu', 'dlrelu', 'exsig', 'acos', 'gla', 'srelu', 'qelu', 'isra', 'waveakt', 'arctan', 'bent_identity', 'sech', 'softsign', 'pwl', 'cubic', 'gaussian', 'sine', 'tanh_square', 'mod_sigmoid', 'quartic', 'square_quartic', 'cubic_quadratic', 'exp_cubic', 'sine_square', 'logarithmic', 'scaled_cubic', 'sine_offset']
+    activations_list = ['linear', 'sigmoid', 'relu', 'tanh', 'circular', 'spiral', 'swish', 'sin_plus', 'mod_circular', 'tanh_circular', 'leaky_relu', 'softplus', 'elu', 'gelu', 'selu', 'sinakt', 'p_squared', 'sglu', 'dlrelu', 'exsig', 'acos', 'gla', 'srelu', 'qelu', 'isra', 'waveakt', 'arctan', 'bent_identity', 'sech', 'softsign', 'pwl', 'cubic', 'gaussian', 'sine', 'tanh_square', 'mod_sigmoid', 'quartic', 'square_quartic', 'cubic_quadratic', 'sine_square', 'logarithmic', 'scaled_cubic', 'sine_offset']
     
     return activations_list
 
@@ -279,7 +279,7 @@ def apply_activation(Input, activation_list):
 
         activation_outputs = np.array([activation_functions[act](origin_input) for act in valid_activations])
 
-        return Input + np.sum(activation_outputs, axis=0)
+        return np.sum(activation_outputs, axis=0)
         
     except Exception as e:
         warnings.warn(f"Error in activation processing: {str(e)}", RuntimeWarning)

pyerualjetwork/activation_functions_cuda.py

@@ -6,7 +6,7 @@ import warnings
 
 def all_activations():
     
-    activations_list = ['linear', 'sigmoid', 'relu', 'tanh', 'circular', 'spiral', 'swish', 'sin_plus', 'mod_circular', 'tanh_circular', 'leaky_relu', 'softplus', 'elu', 'gelu', 'selu', 'sinakt', 'p_squared', 'sglu', 'dlrelu', 'exsig', 'acos', 'gla', 'srelu', 'qelu', 'isra', 'waveakt', 'arctan', 'bent_identity', 'sech', 'softsign', 'pwl', 'cubic', 'gaussian', 'sine', 'tanh_square', 'mod_sigmoid', 'quartic', 'square_quartic', 'cubic_quadratic', 'exp_cubic', 'sine_square', 'logarithmic', 'scaled_cubic', 'sine_offset']
+    activations_list = ['linear', 'sigmoid', 'relu', 'tanh', 'circular', 'spiral', 'swish', 'sin_plus', 'mod_circular', 'tanh_circular', 'leaky_relu', 'softplus', 'elu', 'gelu', 'selu', 'sinakt', 'p_squared', 'sglu', 'dlrelu', 'exsig', 'acos', 'gla', 'srelu', 'qelu', 'isra', 'waveakt', 'arctan', 'bent_identity', 'sech', 'softsign', 'pwl', 'cubic', 'gaussian', 'sine', 'tanh_square', 'mod_sigmoid', 'quartic', 'square_quartic', 'cubic_quadratic', 'sine_square', 'logarithmic', 'scaled_cubic', 'sine_offset']
     
     return activations_list
 
@@ -202,9 +202,6 @@ def square_quartic(x):
 def cubic_quadratic(x):
     return x**3 * (x**2)
 
-def exp_cubic(x):
-    return cp.exp(x**3)
-
 def sine_square(x):
     return cp.sin(x)**2
 
@@ -266,7 +263,6 @@ def apply_activation(Input, activation_list):
         'quartic': quartic,
         'square_quartic': square_quartic,
         'cubic_quadratic': cubic_quadratic,
-        'exp_cubic': exp_cubic,
         'sine_square': sine_square,
         'logarithmic': logarithmic,
         'scaled_cubic': lambda x: scaled_cubic(x, 1.0),
@@ -282,7 +278,7 @@ def apply_activation(Input, activation_list):
 
         activation_outputs = cp.array([activation_functions[act](origin_input) for act in valid_activations])
 
-        return Input + cp.sum(activation_outputs, axis=0)
+        return cp.sum(activation_outputs, axis=0)
         
     except Exception as e:
         warnings.warn(f"Error in activation processing: {str(e)}", RuntimeWarning)

pyerualjetwork/data_operations.py

@@ -379,22 +379,24 @@ dtype=np.float32):
 
 
 def non_neg_normalization(
-    Input, 
+    Input,
     dtype=np.float32
 ):
     """
     Normalizes the input data [0-1] range.
-
     Args:
         Input (numpy): Input data to be normalized.
-
-        dtype (numpy.dtype): Data type for the arrays. cp.float32 by default. Example: cp.float64 or cp.float16.
-
+        dtype (numpy.dtype): Data type for the arrays. np.float32 by default. Example: np.float64 or np.float16.
     Returns:
         (numpy) Scaled input data after normalization.
     """
+    Input = Input.astype(dtype, copy=False)
+    MaxAbs = np.max(np.abs(Input))
 
-    MaxAbs = np.max(np.abs(Input.astype(dtype, copy=False)))
+    if np.all(Input == Input.flat[0]):
+        randomization = np.random.random(Input.shape).astype(dtype)
+        return randomization
+    
     return (Input + MaxAbs) / (2 * MaxAbs)
 
 

pyerualjetwork/data_operations_cuda.py

@@ -420,22 +420,24 @@ def normalization(
 
 
 def non_neg_normalization(
-    Input, 
-    dtype=cp.float32
+    Input,
+    dtype=np.float32
 ):
     """
     Normalizes the input data [0-1] range.
-
     Args:
         Input (cupy): Input data to be normalized.
-
         dtype (cupy.dtype): Data type for the arrays. cp.float32 by default. Example: cp.float64 or cp.float16.
-
     Returns:
         (cupy) Scaled input data after normalization.
     """
+    Input = Input.astype(dtype, copy=False)
+    MaxAbs = cp.max(cp.abs(Input))
 
-    MaxAbs = cp.max(cp.abs(Input.astype(dtype, copy=False)))
+    if cp.all(Input == Input.flat[0]):
+        randomization = cp.random.random(Input.shape).astype(dtype)
+        return randomization
+    
     return (Input + MaxAbs) / (2 * MaxAbs)
 
 

pyerualjetwork/model_operations.py

@@ -55,6 +55,13 @@ def save_model(model_name,
     if model_type != 'PLAN' and model_type != 'MLP':
         raise ValueError("model_type parameter must be 'PLAN' or 'MLP'.")
 
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+    else:
+        activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+
+    activation = activation_potentiation.copy()
+
     if test_acc != None:
         test_acc= float(test_acc)
 
@@ -82,6 +89,7 @@ def save_model(model_name,
             sys.exit()
 
     elif model_type == 'MLP':
+
         class_count = W[-1].shape[0]
         
         NeuronCount.append(np.shape(W[0])[1])
@@ -95,33 +103,34 @@ def save_model(model_name,
                 print(Fore.RED + "ERROR: Weight matrices have a problem from: save_model" + Style.RESET_ALL)
                 sys.exit()
 
+    
         SynapseCount.append(' ')
         
-        activation_potentiation.append('')
-        activation_potentiation.insert(0, '')
+        activation.append('')
+        activation.insert(0, '')
         
-    if isinstance(activation_potentiation, str):
-        activation_potentiation = [activation_potentiation]
-        activation_potentiation.append('')
+    if len(activation) == 1 and model_type == 'PLAN':
+        activation = [activation]
+        activation.append('')
 
-    if len(activation_potentiation) > len(NeuronCount):
-        for i in range(len(activation_potentiation) - len(NeuronCount)):
+    if len(activation) > len(NeuronCount):
+        for i in range(len(activation) - len(NeuronCount)):
             NeuronCount.append('')
-         
-    if len(activation_potentiation) > len(SynapseCount):
-        for i in range(len(activation_potentiation) - len(SynapseCount)):
+        
+    if len(activation) > len(SynapseCount):
+        for i in range(len(activation) - len(SynapseCount)):
             SynapseCount.append('')
 
 
     if scaler_params != None:
 
-        if len(scaler_params) > len(activation_potentiation):
+        if len(scaler_params) > len(activation):
 
-            activation_potentiation += ['']
+            activation += ['']
 
-        elif len(activation_potentiation) > len(scaler_params):
+        elif len(activation) > len(scaler_params):
 
-            for i in range(len(activation_potentiation) - len(scaler_params)):
+            for i in range(len(activation) - len(scaler_params)):
 
                 scaler_params.append(' ')
 
@@ -136,70 +145,62 @@ def save_model(model_name,
             'WEIGHTS FORMAT': weights_format,
             'MODEL PATH': model_path,
             'STANDARD SCALER': scaler_params,
-            'ACTIVATION POTENTIATION': activation_potentiation
+            'ACTIVATION POTENTIATION': activation
             }
 
     df = pd.DataFrame(data)
     df.to_pickle(model_path + model_name + '.pkl')
 
-    if isinstance(W, list): max_file = len(W)
-    else: max_file = 1
-
-    for i in range(max_file):
-
-        if max_file > 1: weight = W[i]
-        else: weight = W
+    try:
 
-        try:
+        if weights_type == 'txt' and weights_format == 'f':
 
-            if weights_type == 'txt' and weights_format == 'f':
+                np.savetxt(model_path + model_name + f'_weights.txt',  W, fmt='%f')
 
-                    np.savetxt(model_path + model_name + f'weights{i}.txt',  weight, fmt='%f')
+        if weights_type == 'txt' and weights_format == 'raw':
 
-            if weights_type == 'txt' and weights_format == 'raw':
+                np.savetxt(model_path + model_name + f'_weights.txt',  W)
 
-                    np.savetxt(model_path + model_name + f'weights{i}.txt',  weight)
+        ###
 
-            ###
+        
+        if weights_type == 'pkl' and weights_format == 'f':
 
-            
-            if weights_type == 'pkl' and weights_format == 'f':
+            with open(model_path + model_name + f'_weights.pkl', 'wb') as f:
+                pickle.dump(W.astype(float), f)
 
-                with open(model_path + model_name + f'weights{i}.pkl', 'wb') as f:
-                    pickle.dump(weight.astype(float), f)
+        if weights_type == 'pkl' and weights_format =='raw':
+        
+            with open(model_path + model_name + f'_weights.pkl', 'wb') as f:
+                pickle.dump(W, f)
 
-            if weights_type == 'pkl' and weights_format =='raw':
-            
-                with open(model_path + model_name + f'weights{i}.pkl', 'wb') as f:
-                    pickle.dump(weight, f)
+        ###
 
-            ###
+        if weights_type == 'npy' and weights_format == 'f':
 
-            if weights_type == 'npy' and weights_format == 'f':
+                np.save(model_path + model_name + f'_weights.npy',  W, W.astype(float))
 
-                    np.save(model_path + model_name + f'weights{i}.npy',  weight, weight.astype(float))
+        if weights_type == 'npy' and weights_format == 'raw':
 
-            if weights_type == 'npy' and weights_format == 'raw':
+                np.save(model_path + model_name + f'_weights.npy',  W)
 
-                    np.save(model_path + model_name + f'weights{i}.npy',  weight)
+        ###
 
-            ###
+        if weights_type == 'mat' and weights_format == 'f':
 
-            if weights_type == 'mat' and weights_format == 'f':
+                w = {'w': W.astype(float)}
+                io.savemat(model_path + model_name + f'_weights.mat', w)
 
-                    w = {'w': weight.astype(float)}
-                    io.savemat(model_path + model_name + f'weights{i}.mat', w)
+        if weights_type == 'mat' and weights_format == 'raw':
+                
+                w = {'w': W}
+                io.savemat(model_path + model_name + f'_weights.mat', w)
 
-            if weights_type == 'mat' and weights_format == 'raw':
-                    
-                    w = {'w': weight}
-                    io.savemat(model_path + model_name + f'weights{i}.mat', w)
+    except:
 
-        except:
+        print(Fore.RED + "ERROR: Model Weights not saved. Check the Weight parameters. SaveFilePath expl: 'C:/Users/hasancanbeydili/Desktop/denemePLAN/' from: save_model" + Style.RESET_ALL)
+        sys.exit()
 
-            print(Fore.RED + "ERROR: Model Weights not saved. Check the Weight parameters. SaveFilePath expl: 'C:/Users/hasancanbeydili/Desktop/denemePLAN/' from: save_model" + Style.RESET_ALL)
-            sys.exit()
-    
     if show_info:
         print(df)
     
@@ -258,33 +259,26 @@ def load_model(model_name,
     model_name = str(df['MODEL NAME'].iloc[0])
     model_type = str(df['MODEL TYPE'].iloc[0])
     WeightType = str(df['WEIGHTS TYPE'].iloc[0])
-    layers = list(df['NEURON COUNT'])
-
-    if model_type == 'MLP': max_file = len(layers)-1
-    else: max_file = 1
-
-    W = []
-
-    for i in range(max_file):
-         
-        if WeightType == 'txt':
-                W.append(np.loadtxt(model_path + model_name + f'weights{i}.txt'))
-        elif WeightType == 'npy':
-                W.append(np.load(model_path + model_name + f'weights{i}.npy'))
-        elif WeightType == 'mat':
-                W.append(sio.loadmat(model_path + model_name + f'weights{i}.mat'))
-        elif WeightType == 'pkl':
-            with open(model_path + model_name + f'weights{i}.pkl', 'rb') as f:
-                W = pickle.load(f)
-        else:
-
-            raise ValueError(
-                Fore.RED + "Incorrect weight type value. Value must be 'txt', 'npy', 'pkl' or 'mat' from: load_model." + Style.RESET_ALL)
-            
-        if WeightType == 'mat':
-            W[-1] = W[-1]['w']
 
-    if model_type == 'PLAN': W = np.array(W[0], dtype=W[0].dtype)
+    if model_type == 'MLP': allow_pickle = True
+    else: allow_pickle = False
+
+    if WeightType == 'txt':
+            W = (np.loadtxt(model_path + model_name + f'_weights.txt'))
+    elif WeightType == 'npy':
+            W = (np.load(model_path + model_name + f'_weights.npy', allow_pickle=allow_pickle))
+    elif WeightType == 'mat':
+            W = (sio.loadmat(model_path + model_name + f'_weights.mat'))
+    elif WeightType == 'pkl':
+        with open(model_path + model_name + f'_weights.pkl', 'rb') as f:
+            W = pickle.load(f)
+    else:
+
+        raise ValueError(
+            Fore.RED + "Incorrect weight type value. Value must be 'txt', 'npy', 'pkl' or 'mat' from: load_model." + Style.RESET_ALL)
+        
+    if WeightType == 'mat':
+        W = W['w']
 
     return W, None, None, activation_potentiation, scaler_params, None, model_type
 
@@ -320,6 +314,11 @@ def predict_model_ssd(Input, model_name, model_path='', dtype=np.float32):
         W = model[get_weights()]
         model_type = model[get_model_type()]
 
+        if isinstance(activation_potentiation, str):
+            activation_potentiation = [activation_potentiation]
+        else:
+            activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+            
         Input = standard_scaler(None, Input, scaler_params)
 
         if model_type == 'MLP':
@@ -343,7 +342,7 @@ def predict_model_ssd(Input, model_name, model_path='', dtype=np.float32):
         sys.exit()
 
 
-def reverse_predict_model_ssd(output, model_name, model_path='', dtype=np.float32):
+def reverse_predict_model_ssd(output, model_name, model_path=''):
 
     """
     reverse prediction function from storage
@@ -355,8 +354,6 @@ def reverse_predict_model_ssd(output, model_name, model_path='', dtype=np.float3
 
         model_path (str): Path of the model. Default: ''
 
-        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!]
-        
     Returns:
         ndarray: Input from the model.
     """
@@ -401,6 +398,11 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
     
         Input = standard_scaler(None, Input, scaler_params)
         
+        if isinstance(activation_potentiation, str):
+            activation_potentiation = [activation_potentiation]
+        else:
+            activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+            
         if is_mlp:
             
             layer = Input
@@ -421,7 +423,7 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
         print(Fore.RED + "ERROR: Unexpected input or wrong model parameters from: predict_model_ram." + Style.RESET_ALL)
         sys.exit()
 
-def reverse_predict_model_ram(output, W, dtype=np.float32):
+def reverse_predict_model_ram(output, W):
 
     """
     reverse prediction function from memory
@@ -432,8 +434,6 @@ def reverse_predict_model_ram(output, W, dtype=np.float32):
 
         W (list of ndarrays): Weights of the model.
 
-        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!]
-
     Returns:
         ndarray: Input from the model.
     """

pyerualjetwork/model_operations_cuda.py

@@ -59,6 +59,13 @@ def save_model(model_name,
     if model_type != 'PLAN' and model_type != 'MLP':
         raise ValueError("model_type parameter must be 'PLAN' or 'MLP'.")
 
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+    else:
+        activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+
+    activation = activation_potentiation.copy()
+
     if test_acc is not None:
         test_acc= float(test_acc)
 
@@ -101,30 +108,30 @@ def save_model(model_name,
 
         SynapseCount.append(' ')
         
-        activation_potentiation.append('')
-        activation_potentiation.insert(0, '')
+        activation.append('')
+        activation.insert(0, '')
 
-    if isinstance(activation_potentiation, str):
-        activation_potentiation = [activation_potentiation]
-        activation_potentiation.append('')
+    if len(activation) == 1 and model_type == 'PLAN':
+        activation = [activation]
+        activation.append('')
 
-    if len(activation_potentiation) > len(NeuronCount):
-        for i in range(len(activation_potentiation) - len(NeuronCount)):
+    if len(activation) > len(NeuronCount):
+        for i in range(len(activation) - len(NeuronCount)):
             NeuronCount.append('')
          
-    if len(activation_potentiation) > len(SynapseCount):
-        for i in range(len(activation_potentiation) - len(SynapseCount)):
+    if len(activation) > len(SynapseCount):
+        for i in range(len(activation) - len(SynapseCount)):
             SynapseCount.append('')
 
     if scaler_params != None:
 
-        if len(scaler_params) > len(activation_potentiation):
+        if len(scaler_params) > len(activation):
 
-            activation_potentiation += ['']
+            activation += ['']
 
-        elif len(activation_potentiation) > len(scaler_params):
+        elif len(activation) > len(scaler_params):
 
-            for i in range(len(activation_potentiation) - len(scaler_params)):
+            for i in range(len(activation) - len(scaler_params)):
 
                 scaler_params.append(' ')
 
@@ -142,70 +149,62 @@ def save_model(model_name,
             'WEIGHTS FORMAT': weights_format,
             'MODEL PATH': model_path,
             'STANDARD SCALER': scaler_params,
-            'ACTIVATION POTENTIATION': activation_potentiation
+            'ACTIVATION POTENTIATION': activation
             }
 
     df = pd.DataFrame(data)
     df.to_pickle(model_path + model_name + '.pkl')
 
-    if isinstance(W, list): max_file = len(W)
-    else: max_file = 1
-
-    for i in range(max_file):
+    try:
 
-        if max_file > 1: weight = W[i]
-        else: weight = W
+        if weights_type == 'txt' and weights_format == 'f':
 
-        try:
+                cp.savetxt(model_path + model_name + f'_weights.txt',  W, fmt='%f')
 
-            if weights_type == 'txt' and weights_format == 'f':
+        if weights_type == 'txt' and weights_format == 'raw':
 
-                    cp.savetxt(model_path + model_name + f'weights{i}.txt',  weight, fmt='%f')
+                cp.savetxt(model_path + model_name + f'_weights.txt',  W)
 
-            if weights_type == 'txt' and weights_format == 'raw':
+        ###
 
-                    cp.savetxt(model_path + model_name + f'weights{i}.txt',  weight)
-
-            ###
+        
+        if weights_type == 'pkl' and weights_format == 'f':
 
-            
-            if weights_type == 'pkl' and weights_format == 'f':
+            with open(model_path + model_name + f'_weights.pkl', 'wb') as f:
+                pickle.dump(W.astype(float), f)
 
-                with open(model_path + model_name + f'weights{i}.pkl', 'wb') as f:
-                    pickle.dump(weight.astype(float), f)
+        if weights_type == 'pkl' and weights_format =='raw':
+        
+            with open(model_path + model_name + f'_weights.pkl', 'wb') as f:
+                pickle.dump(W, f)
 
-            if weights_type == 'pkl' and weights_format =='raw':
-            
-                with open(model_path + model_name + f'weights{i}.pkl', 'wb') as f:
-                    pickle.dump(weight, f)
+        ###
 
-            ###
+        if weights_type == 'npy' and weights_format == 'f':
 
-            if weights_type == 'npy' and weights_format == 'f':
+                cp.save(model_path + model_name + f'_weights.npy',  W, W.astype(float))
 
-                    cp.save(model_path + model_name + f'weights{i}.npy',  weight, weight.astype(float))
+        if weights_type == 'npy' and weights_format == 'raw':
 
-            if weights_type == 'npy' and weights_format == 'raw':
+                cp.save(model_path + model_name + f'_weights.npy',  W)
 
-                    cp.save(model_path + model_name + f'weights{i}.npy',  weight)
+        ###
 
-            ###
+        if weights_type == 'mat' and weights_format == 'f':
 
-            if weights_type == 'mat' and weights_format == 'f':
+                w = {'w': W.astype(float)}
+                io.savemat(model_path + model_name + f'_weights.mat', w)
 
-                    w = {'w': weight.astype(float)}
-                    io.savemat(model_path + model_name + f'weights{i}.mat', w)
+        if weights_type == 'mat' and weights_format == 'raw':
+                
+                w = {'w': W}
+                io.savemat(model_path + model_name + f'_weights.mat', w)
 
-            if weights_type == 'mat' and weights_format == 'raw':
-                    
-                    w = {'w': weight}
-                    io.savemat(model_path + model_name + f'weights{i}.mat', w)
+    except:
 
-        except:
+        print(Fore.RED + "ERROR: Model Weights not saved. Check the Weight parameters. SaveFilePath expl: 'C:/Users/hasancanbeydili/Desktop/denemePLAN/' from: save_model" + Style.RESET_ALL)
+        sys.exit()
 
-            print(Fore.RED + "ERROR: Model Weights not saved. Check the Weight parameters. SaveFilePath expl: 'C:/Users/hasancanbeydili/Desktop/denemePLAN/' from: save_model" + Style.RESET_ALL)
-            sys.exit()
-    
     if show_info:
         print(df)
     
@@ -266,33 +265,26 @@ def load_model(model_name,
     model_name = str(df['MODEL NAME'].iloc[0])
     model_type = str(df['MODEL TYPE'].iloc[0])
     WeightType = str(df['WEIGHTS TYPE'].iloc[0])
-    layers = list(df['NEURON COUNT'])
-
-    if model_type == 'MLP': max_file = len(layers)-1
-    else: max_file = 1
-
-    W = []
-
-    for i in range(max_file):
-
-        if WeightType == 'txt':
-                W.append(cp.loadtxt(model_path + model_name + f'weights{i}.txt'))
-        elif WeightType == 'npy':
-                W.append(cp.load(model_path + model_name + f'weights{i}.npy'))
-        elif WeightType == 'mat':
-                W.append(sio.loadmat(model_path + model_name + f'weights{i}.mat'))
-        elif WeightType == 'pkl':
-            with open(model_path + model_name + f'weights{i}.pkl', 'rb') as f:
-                W = pickle.load(f)
-        else:
-
-            raise ValueError(
-                Fore.RED + "Incorrect weight type value. Value must be 'txt', 'npy', 'pkl' or 'mat' from: load_model." + Style.RESET_ALL)
-            
-        if WeightType == 'mat':
-            W[-1] = W[-1]['w']
 
-    if model_type == 'PLAN': W = cp.array(W[0], dtype=W[0].dtype)
+    if model_type == 'MLP': allow_pickle = True
+    else: allow_pickle = False
+
+    if WeightType == 'txt':
+            W = (cp.loadtxt(model_path + model_name + f'_weights.txt'))
+    elif WeightType == 'npy':
+            W = (cp.load(model_path + model_name + f'_weights.npy', allow_pickle=allow_pickle))
+    elif WeightType == 'mat':
+            W = (sio.loadmat(model_path + model_name + f'_weights.mat'))
+    elif WeightType == 'pkl':
+        with open(model_path + model_name + f'_weights.pkl', 'rb') as f:
+            W = pickle.load(f)
+    else:
+
+        raise ValueError(
+            Fore.RED + "Incorrect weight type value. Value must be 'txt', 'npy', 'pkl' or 'mat' from: load_model." + Style.RESET_ALL)
+        
+    if WeightType == 'mat':
+        W = W['w']
 
     return W, None, None, activation_potentiation, scaler_params, None, model_type
 
@@ -330,6 +322,11 @@ def predict_model_ssd(Input, model_name, model_path='', dtype=cp.float32):
         W = model[get_weights()]
         model_type = model[get_model_type()]
 
+        if isinstance(activation_potentiation, str):
+            activation_potentiation = [activation_potentiation]
+        else:
+            activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+
         Input = standard_scaler(None, Input, scaler_params)
 
         if model_type == 'MLP':
@@ -410,7 +407,12 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
     from .activation_functions_cuda import apply_activation
 
     try:
-    
+        
+        if isinstance(activation_potentiation, str):
+            activation_potentiation = [activation_potentiation]
+        else:
+            activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+            
         Input = standard_scaler(None, Input, scaler_params)
         
         if is_mlp:

pyerualjetwork/plan.py

@@ -404,6 +404,11 @@ def evaluate(
 
     if auto_normalization: x_test = normalization(x_test, dtype=x_test.dtype)
 
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+    else:
+        activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+
     x_test = apply_activation(x_test, activation_potentiation)
     
     result = x_test @ W.T

pyerualjetwork/plan_cuda.py

@@ -413,6 +413,11 @@ def evaluate(
 
     if auto_normalization: x_test = normalization(x_test, dtype=x_test.dtype)
 
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+    else:
+        activation_potentiation = [item if isinstance(item, list) else [item] for item in activation_potentiation]
+
     x_test = apply_activation(x_test, activation_potentiation)
     
     result = x_test @ W.T

{pyerualjetwork-4.6.6.dist-info → pyerualjetwork-4.6.8b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.6.6
+Version: 4.6.8b0
 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-4.6.8b0.dist-info/RECORD

@@ -0,0 +1,25 @@
+pyerualjetwork/__init__.py,sha256=u-vA_SDH_vmQI2fEUzbCFlIJG84uHxcir0gEXc-UvgQ,1281
+pyerualjetwork/activation_functions.py,sha256=0fNOHXd490HC6gadKwb0AuBjw34dWq3GRZkg5iWO27c,7621
+pyerualjetwork/activation_functions_cuda.py,sha256=X5-dtYBkGp35kyL21eLR7mbYUdttxElu-WqXmwmkV9E,7672
+pyerualjetwork/data_operations.py,sha256=XKYG9-mLa3qKAXUjejuD7V8aJKjpl5PdQwKzPFjpKgs,15437
+pyerualjetwork/data_operations_cuda.py,sha256=zqiHXDRtC8qDlVlN6lLoZn9uQgkm40aKFfFjWjurCxQ,17538
+pyerualjetwork/fitness_functions.py,sha256=urRdeMvUhNgWxD4ZGHCRdQlIf9cTWYMvF3_aVBojRqY,1235
+pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
+pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
+pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
+pyerualjetwork/memory_operations.py,sha256=0yCOHcgiNyF4ccMcRlL1Q9F_byG4nzjhmkbpXE_yU6E,13401
+pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
+pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
+pyerualjetwork/model_operations.py,sha256=SYMXYNFFLz2YUvmp9lSKXd2L1vCwhyL_AUjL3UYCkZw,15134
+pyerualjetwork/model_operations_cuda.py,sha256=GE_71JLTItAFXz8iW60QeO4XKJ8fGeHgxETmHtW9drc,16204
+pyerualjetwork/plan.py,sha256=cjVblo8TxTHX-GZPvgQvJZ34nOmzxSvtCrQi9K-Mhog,23268
+pyerualjetwork/plan_cuda.py,sha256=ZEU_b_EoA-zPk7Gn94L_XBZz1v4mn8DOUsjTNV6fp8Q,24230
+pyerualjetwork/planeat.py,sha256=prbkUIrD37Y_b7MmTuGg4rGHXfqHIjLFMbs7TnnEy9E,44645
+pyerualjetwork/planeat_cuda.py,sha256=i6WDHkUEAMK7IHNBilM29xyYWq2qvPNpF9idcAkC1EU,44650
+pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
+pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
+pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
+pyerualjetwork-4.6.8b0.dist-info/METADATA,sha256=nB7S7mpl1snTt4T8QzTSs8ShpPEpny_at6JXeqW5h2c,7507
+pyerualjetwork-4.6.8b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.6.8b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.6.8b0.dist-info/RECORD,,

pyerualjetwork-4.6.6.dist-info/RECORD

@@ -1,25 +0,0 @@
-pyerualjetwork/__init__.py,sha256=uKOppTDMmBVI819Q_jQUWyvm_UZH3QzdKF3q9SCfXU0,1279
-pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
-pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
-pyerualjetwork/data_operations.py,sha256=Y_RdxkjLEszFgeo4VDWIX1keF2syP-88KesLXA5sRyY,15280
-pyerualjetwork/data_operations_cuda.py,sha256=9tyD3Bbv5__stuUampgh3_GbMhb_kmTTJmZi7BJsvuA,17381
-pyerualjetwork/fitness_functions.py,sha256=urRdeMvUhNgWxD4ZGHCRdQlIf9cTWYMvF3_aVBojRqY,1235
-pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
-pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
-pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
-pyerualjetwork/memory_operations.py,sha256=0yCOHcgiNyF4ccMcRlL1Q9F_byG4nzjhmkbpXE_yU6E,13401
-pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
-pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
-pyerualjetwork/model_operations.py,sha256=fr64XCwgl1YRh5nP3sEkvQORKHb-2lF_a4KjclNkZfY,15522
-pyerualjetwork/model_operations_cuda.py,sha256=-Kv8fYqHSU0L9FalOsQ7EWCwCEwjgUySObyueOqCH_o,16134
-pyerualjetwork/plan.py,sha256=UyIvPmvHCHwczlc9KHolE4y6CPEeBfhnRN5yznSbnoM,23028
-pyerualjetwork/plan_cuda.py,sha256=iteqgv7x9Z2Pj4vGOZs6HXS3r0bNaF_smr7ZXaOdRnw,23990
-pyerualjetwork/planeat.py,sha256=prbkUIrD37Y_b7MmTuGg4rGHXfqHIjLFMbs7TnnEy9E,44645
-pyerualjetwork/planeat_cuda.py,sha256=i6WDHkUEAMK7IHNBilM29xyYWq2qvPNpF9idcAkC1EU,44650
-pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
-pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
-pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
-pyerualjetwork-4.6.6.dist-info/METADATA,sha256=nrasvgqmd7Tb2-NEqbkmaS4FWNIaHmyttYaLLzKm0_Q,7505
-pyerualjetwork-4.6.6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.6.6.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.6.6.dist-info/RECORD,,