pyerualjetwork 4.6b0__py3-none-any.whl → 4.6.1b0__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.6b0"
+__version__ = "4.6.1b0"
 __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/model_operations.py

@@ -36,7 +36,7 @@ def save_model(model_name,
         
         model_path: (str): Path where the model will be saved. For example: C:/Users/beydili/Desktop/denemePLAN/ default: ''
         
-        activation_potentiation: (list): For deeper PLAN networks, activation function parameters. For more information please run this code: plan.activations_list() default: ['linear']
+        activation_potentiation: (list[str]): For deeper PLAN networks, activation function parameters. Or activation function parameters for MLP layers. For more information please run this code: plan.activations_list() default: ['linear']
         
         weights_type: (str): Type of weights to save (options: 'txt', 'pkl', 'npy', 'mat'). default: 'npy'
         
@@ -66,26 +66,24 @@ def save_model(model_name,
         print(Fore.RED + "ERROR111: Weight Format Type must be 'd' or 'f' or 'raw' from: save_model" + Style.RESET_ALL)
         sys.exit()
 
+    NeuronCount = []
+    SynapseCount = []
+
     if model_type == 'PLAN':
         class_count = W.shape[0]
 
-        NeuronCount = 0
-        SynapseCount = 0
-
         try:
-                NeuronCount += np.shape(W)[0] + np.shape(W)[1]
-                SynapseCount += np.shape(W)[0] * np.shape(W)[1]
+            NeuronCount.append(np.shape(W)[1])
+            NeuronCount.append(np.shape(W)[0])
+            SynapseCount.append(np.shape(W)[0] * np.shape(W)[1])
         except:
 
-            print(Fore.RED + "ERROR: Weight matrices has a problem from: save_model" + Style.RESET_ALL)
+            print(Fore.RED + "ERROR: Weight matrices have a problem from: save_model" + Style.RESET_ALL)
             sys.exit()
 
     elif model_type == 'MLP':
         class_count = W[-1].shape[0]
         
-        NeuronCount = []
-        SynapseCount = []
-
         NeuronCount.append(np.shape(W[0])[1])
 
         for i in range(len(W)):
@@ -94,13 +92,26 @@ def save_model(model_name,
                     SynapseCount.append(np.shape(W[i])[0] * np.shape(W[i])[1])
             except:
 
-                print(Fore.RED + "ERROR: Weight matrices has a problem from: save_model" + Style.RESET_ALL)
+                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, '')
+        
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+        activation_potentiation.append('')
+
+    if len(activation_potentiation) > len(NeuronCount):
+        for i in range(len(activation_potentiation) - len(NeuronCount)):
+            NeuronCount.append('')
+         
+    if len(activation_potentiation) > len(SynapseCount):
+        for i in range(len(activation_potentiation) - len(SynapseCount)):
+            SynapseCount.append('')
+
 
     if scaler_params != None:
 
@@ -273,6 +284,8 @@ def load_model(model_name,
         if WeightType == 'mat':
             W[-1] = W[-1]['w']
 
+    if model_type == 'PLAN': W = np.array(W[0], dtype=W[0].dtype)
+
     return W, None, None, activation_potentiation, scaler_params, None, model_type
 
 
@@ -374,15 +387,15 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
         
         scaler_params (list): standard scaler params list: mean,std. (optional) Default: None.
         
-        activation_potentiation (list): ac list for deep PLAN. default: [None] ('linear') (optional)
+        activation_potentiation (list[str]): activation list for deep PLAN or activation list for MLP layers. Default: ['linear']
         
         is_mlp (bool, optional): Predict from PLAN model or MLP model ? Default: False (PLAN)
     Returns:
     ndarray: Output from the model.
     """
 
-    from data_operations import standard_scaler
-    from activation_functions import apply_activation
+    from .data_operations import standard_scaler
+    from .activation_functions import apply_activation
 
     try:
     

pyerualjetwork/model_operations_cuda.py

@@ -39,7 +39,7 @@ def save_model(model_name,
         
         model_path: (str): Path where the model will be saved. For example: C:/Users/beydili/Desktop/denemePLAN/ default: ''
        
-        activation_potentiation: (list): For deeper PLAN networks, activation function parameters. Or activation functions for MLP model layers. For more information please run this code: plan.activations_list() default: ['linear']
+        activation_potentiation: (list[str]): For deeper PLAN networks, activation function parameters. Or activation function parameters for MLP layers. For more information please run this code: plan.activations_list() default: ['linear']
         
         weights_type: (str): Type of weights to save (options: 'txt', 'pkl', 'npy', 'mat'). default: 'npy'
         
@@ -69,36 +69,34 @@ def save_model(model_name,
     if weights_format != 'd' and weights_format != 'f' and weights_format != 'raw':
         print(Fore.RED + "ERROR111: Weight Format Type must be 'd' or 'f' or 'raw' from: save_model" + Style.RESET_ALL)
         sys.exit()
+        
+    NeuronCount = []
+    SynapseCount = []
 
     if model_type == 'PLAN':
         class_count = W.shape[0]
-
-        NeuronCount = 0
-        SynapseCount = 0
-
+        
         try:
-                NeuronCount += cp.shape(W)[0] + cp.shape(W)[1]
-                SynapseCount += cp.shape(W)[0] * cp.shape(W)[1]
+            NeuronCount.append(cp.shape(W)[1])
+            NeuronCount.append(cp.shape(W)[0])
+            SynapseCount.append(cp.shape(W)[0] * cp.shape(W)[1])
         except:
 
-            print(Fore.RED + "ERROR: Weight matrices has a problem from: save_model" + Style.RESET_ALL)
+            print(Fore.RED + "ERROR: Weight matrices have a problem from: save_model" + Style.RESET_ALL)
             sys.exit()
 
     elif model_type == 'MLP':
         class_count = W[-1].shape[0]
         
-        NeuronCount = []
-        SynapseCount = []
-
         NeuronCount.append(cp.shape(W[0])[1])
 
         for i in range(len(W)):
             try:
-                    NeuronCount.append(cp.shape(W[i])[0])
-                    SynapseCount.append(cp.shape(W[i])[0] * cp.shape(W[i])[1])
+                NeuronCount.append(cp.shape(W[i])[0])
+                SynapseCount.append(cp.shape(W[i])[0] * cp.shape(W[i])[1])
             except:
 
-                print(Fore.RED + "ERROR: Weight matrices has a problem from: save_model" + Style.RESET_ALL)
+                print(Fore.RED + "ERROR: Weight matrices have a problem from: save_model" + Style.RESET_ALL)
                 sys.exit()
 
         SynapseCount.append(' ')
@@ -106,6 +104,18 @@ def save_model(model_name,
         activation_potentiation.append('')
         activation_potentiation.insert(0, '')
 
+    if isinstance(activation_potentiation, str):
+        activation_potentiation = [activation_potentiation]
+        activation_potentiation.append('')
+
+    if len(activation_potentiation) > len(NeuronCount):
+        for i in range(len(activation_potentiation) - len(NeuronCount)):
+            NeuronCount.append('')
+         
+    if len(activation_potentiation) > len(SynapseCount):
+        for i in range(len(activation_potentiation) - len(SynapseCount)):
+            SynapseCount.append('')
+
     if scaler_params != None:
 
         if len(scaler_params) > len(activation_potentiation):
@@ -282,7 +292,7 @@ def load_model(model_name,
         if WeightType == 'mat':
             W[-1] = W[-1]['w']
 
-    if model_type == 'PLAN': W = cp.array(W[0], dtype=W[0])
+    if model_type == 'PLAN': W = cp.array(W[0], dtype=W[0].dtype)
 
     return W, None, None, activation_potentiation, scaler_params, None, model_type
 
@@ -376,41 +386,34 @@ def reverse_predict_model_ssd(output, model_name, model_path='', dtype=cp.float3
         sys.exit()
 
 
-def predict_model_ssd(Input, model_name, model_path='', dtype=cp.float32):
+def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['linear'], is_mlp=False):
 
     """
     Function to make a prediction using a potentiation learning artificial neural network (PLAN).
-    from storage
+    from memory.
 
     Args:
-        Input (list or ndarray or cupyarray): Input data for the model (single vector or single matrix).
+        Input (list or ndarray): Input data for the model (single vector or single matrix).
         
-        model_name (str): Name of the model.
+        W (list of ndarrays): Weights of the model.
         
-        model_path (str): Path of the model. Default: ''
+        scaler_params (list): standard scaler params list: mean,std. (optional) Default: None.
         
-        dtype (cupy.dtype): Data type for the arrays. cp.float32 by default. Example: cp.float64, cp.float16. (optional)
+        activation_potentiation (list[str]): activation list for deep PLAN or activation list for MLP layers. Default: ['linear']
+        
+        is_mlp (bool, optional): Predict from PLAN model or MLP model ? Default: False (PLAN)
     Returns:
-        cupyarray: Output from the model.
+    cupyarray: Output from the model.
     """
-    
-    Input = cp.array(Input, dtype=dtype, copy=False)
-    
-    from .activation_functions_cuda import apply_activation
-    from .data_operations_cuda import standard_scaler
-    
-    try:
 
-        model = load_model(model_name, model_path)
-        
-        activation_potentiation = model[get_act_pot()]
-        scaler_params = model[get_scaler()]
-        W = model[get_weights()]
-        model_type = model[get_model_type()]
+    from .data_operations_cuda import standard_scaler
+    from .activation_functions_cuda import apply_activation
 
+    try:
+    
         Input = standard_scaler(None, Input, scaler_params)
-
-        if model_type == 'MLP':
+        
+        if is_mlp:
             
             layer = Input
             for i in range(len(W)):
@@ -425,9 +428,9 @@ def predict_model_ssd(Input, model_name, model_path='', dtype=cp.float32):
             result = Input @ W.T
 
             return result
-
+        
     except:
-        print(Fore.RED + "ERROR: Unexpected Output or wrong model parameters from: predict_model_ssd." + Style.RESET_ALL)
+        print(Fore.RED + "ERROR: Unexpected input or wrong model parameters from: predict_model_ram." + Style.RESET_ALL)
         sys.exit()
 
 

pyerualjetwork/planeat.py

@@ -86,6 +86,8 @@ def define_genomes(input_shape, output_shape, population_size, hidden=0, neurons
                population_weights[i][l][j,:] = apply_activation(population_weights[i][l][j,:], population_activations[i])
                population_weights[i][l][j,:] = normalization(population_weights[i][l][j,:], dtype=dtype)
 
+      return population_weights, population_activations
+   
    else:
       population_weights = [0] * population_size
       population_activations = [0] * population_size
@@ -105,7 +107,7 @@ def define_genomes(input_shape, output_shape, population_size, hidden=0, neurons
             population_weights[i][j,:] = apply_activation(population_weights[i][j,:], population_activations[i])
             population_weights[i][j,:] = normalization(population_weights[i][j,:], dtype=dtype)
 
-   return population_weights, population_activations
+      return np.array(population_weights, dtype=dtype), population_activations
 
 
 def evolver(weights, 

pyerualjetwork/planeat_cuda.py

@@ -88,6 +88,8 @@ def define_genomes(input_shape, output_shape, population_size, hidden=0, neurons
                population_weights[i][l][j,:] = apply_activation(population_weights[i][l][j,:], population_activations[i])
                population_weights[i][l][j,:] = normalization(population_weights[i][l][j,:], dtype=dtype)
 
+      return population_weights, population_activations
+
    else:
       population_weights = [0] * population_size
       population_activations = [0] * population_size
@@ -107,7 +109,7 @@ def define_genomes(input_shape, output_shape, population_size, hidden=0, neurons
             population_weights[i][j,:] = apply_activation(population_weights[i][j,:], population_activations[i])
             population_weights[i][j,:] = normalization(population_weights[i][j,:], dtype=dtype)
 
-   return population_weights, population_activations
+      return cp.array(population_weights, dtype=dtype), population_activations
 
 
 def evolver(weights, 

{pyerualjetwork-4.6b0.dist-info → pyerualjetwork-4.6.1b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.6b0
+Version: 4.6.1b0
 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-4.6b0.dist-info → pyerualjetwork-4.6.1b0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=KLgnJmN6LoSApf-e8QKuNBxyBM3QqRZOSsUEVy5jL58,1279
+pyerualjetwork/__init__.py,sha256=iS07tu-qBxUf0BbzlgGOwdjZJa2LhYDX-YwH6u-yY90,1281
 pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
 pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
 pyerualjetwork/data_operations.py,sha256=TxfpwHWUpJ2E7IVF2uSmigrwpVL_JxrvGPOrMg2lNuI,15981
@@ -10,16 +10,16 @@ pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqd
 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=aARz97TFaVX5lkdKSV-4cp3OT0KSiRUYO7ktpfCmr44,14854
-pyerualjetwork/model_operations_cuda.py,sha256=ZpnqaJYNb8Wyc5htEY0qXcZA4N9LLPDiHEBjrIqvGCI,15745
+pyerualjetwork/model_operations.py,sha256=ZjLQrYYbzBtTyEfrH9_gouq-m8r_XawRAO2ohkjYd4U,15500
+pyerualjetwork/model_operations_cuda.py,sha256=-ag0HjlNFxnhcVY2xHFYqQzxDxyzPfiXl0aTRUSVOnM,16112
 pyerualjetwork/plan.py,sha256=UyIvPmvHCHwczlc9KHolE4y6CPEeBfhnRN5yznSbnoM,23028
 pyerualjetwork/plan_cuda.py,sha256=iteqgv7x9Z2Pj4vGOZs6HXS3r0bNaF_smr7ZXaOdRnw,23990
-pyerualjetwork/planeat.py,sha256=RjTB2GN1Dp6Qbm6w5iDCEIR056KzQc4vyJ06Gce0iWQ,45193
-pyerualjetwork/planeat_cuda.py,sha256=cIkrjT9rjeyKhcrv3x_YXYqr2yeKe8yC1VblFqULg88,45241
+pyerualjetwork/planeat.py,sha256=hZIzDbdRjyCA-wdraD0yJyG-Y8J2KadEqlITs-M_jPQ,45281
+pyerualjetwork/planeat_cuda.py,sha256=uOvhTxG36jVu8_uHN8jSxGQqbwpSIPKqbXT1sFl0kU8,45326
 pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
 pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
 pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
-pyerualjetwork-4.6b0.dist-info/METADATA,sha256=xS9cCvZpXLGKrVHK0VSQP49HnPKeN5PoyDSscUXzDDo,7505
-pyerualjetwork-4.6b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.6b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.6b0.dist-info/RECORD,,
+pyerualjetwork-4.6.1b0.dist-info/METADATA,sha256=qLfRiea4Z7tUreDfotddrbNOawMDUWz5dCPotOz0u7w,7507
+pyerualjetwork-4.6.1b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.6.1b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.6.1b0.dist-info/RECORD,,