pyerualjetwork 5b1__py3-none-any.whl → 5b3__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -38,7 +38,7 @@ PyerualJetwork document: https://github.com/HCB06/Anaplan/blob/main/Welcome_to_A
 - Contact: tchasancan@gmail.com
 """
 
-__version__ = "5b1"
+__version__ = "5b3"
 __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/neu.py

@@ -178,7 +178,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     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')
 
-    if neurons is not []:
+    if neurons != []:
         fit_start = False
         weight_evolve = True
         is_mlp = True

pyerualjetwork/neu_cuda.py

@@ -59,7 +59,7 @@ bar_format_learner = loading_bars()[1]
 def plan_fit(
     x_train,
     y_train,
-    activation_functions=['linear'],
+    activations=['linear'],
     W=None,
     auto_normalization=False,
     dtype=cp.float32
@@ -70,7 +70,7 @@ def plan_fit(
     plan_fit Args:
         :param (aray-like[cupy]) x_train: (aray-like[cupy]): List or cupy array of input data.
         :param (aray-like[cupy]) y_train: List or cupy array of target labels. (one hot encoded)
-        :param (list) activation_functions: For deeper PLAN networks, activation function parameters. For more information please run this code: nn.activations_list() default: [None] (optional)
+        :param (list) activations: For deeper PLAN networks, activation function parameters. For more information please run this code: nn.activations_list() default: [None] (optional)
         W (cupy.ndarray, optional): If you want to re-continue or update model
         auto_normalization (bool, optional): Normalization may solves overflow problem. Default: False
         dtype (cupy.dtype, optional): Data type for the arrays. cp.float32 by default. Example: cp.float64 or cp.float16.
@@ -84,8 +84,8 @@ def plan_fit(
 
     weight = cp.zeros((len(y_train[0]), len(x_train[0].ravel()))).astype(dtype, copy=False) if W is None else W
 
-    if auto_normalization is True: x_train = normalization(apply_activation(x_train, activation_functions))
-    elif auto_normalization is False: x_train = apply_activation(x_train, activation_functions)
+    if auto_normalization is True: x_train = normalization(apply_activation(x_train, activations))
+    elif auto_normalization is False: x_train = apply_activation(x_train, activations)
     else: raise ValueError('normalization parameter only be True or False')
     
     weight += y_train.T @ x_train
@@ -96,7 +96,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
            weight_evolve=True, neural_web_history=False, show_current_activations=False, auto_normalization=False, target_acc=None,
            neurons_history=False, early_stop=False, show_history=False, loss='categorical_crossentropy',
            interval=33.33, target_loss=None, loss_impact=0.1, acc_impact=0.9,
-           start_this_act=None, start_this_W=None, neurons=[], activation_functions=[], dtype=cp.float32, memory='gpu'):
+           start_this_act=None, start_this_W=None, neurons=[], activations=[], dtype=cp.float32, memory='gpu'):
     """
     Optimizes the activation functions for a neural network by leveraging train data to find 
     the most accurate combination of activation potentiation(or activation function) & weight values for the given dataset.
@@ -146,7 +146,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     :param start_this_act: (list, optional): To resume a previously canceled or interrupted training from where it left off, or to continue from that point with a different strategy, provide the list of activation functions selected up to the learned portion to this parameter. Default is None
     :param start_this_W: (cupy.array, optional): To resume a previously canceled or interrupted training from where it left off, or to continue from that point with a different strategy, provide the weight matrix of this genome. Default is None
     :param neurons: (list[int], optional): If you dont want train PLAN model this parameter represents neuron count of each hidden layer for MLP. Number of elements --> Layer count. Default: [] (No hidden layer) --> architecture setted to PLAN, if not --> architecture setted to MLP.
-    :param activation_functions: (list[str], optional): If you dont want train PLAN model this parameter represents activation function of each hidden layer for MLP. if neurons is not [] --> uses default: ['linear'] * len(neurons). if neurons is [] --> uses [].
+    :param activations: (list[str], optional): If you dont want train PLAN model this parameter represents activation function of each hidden layer for MLP. if neurons is not [] --> uses default: ['linear'] * len(neurons). if neurons is [] --> uses [].
     :param dtype: (cupy.dtype): Data type for the Weight matrices. np.float32 by default. Example: cp.float64 or cp.float16.
     :param memory: (str): The memory parameter determines whether the dataset to be processed on the GPU will be stored in the CPU's RAM or the GPU's RAM. Options:  'gpu', 'cpu'. Default: 'gpu'.
 
@@ -159,15 +159,15 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     data = 'Train'
 
     except_this = ['spiral', 'circular']
-    activation_functions = [item for item in all_activations() if item not in except_this]
-    activation_functions_len = len(activation_functions)
+    activations = [item for item in all_activations() if item not in except_this]
+    activations_len = len(activations)
 
-    if pop_size is None: pop_size = activation_functions_len
+    if pop_size is None: pop_size = activations_len
     y_train = optimize_labels(y_train, cuda=True)
 
-    if pop_size < activation_functions_len: raise ValueError(f"pop_size must be higher or equal to {activation_functions_len}")
+    if pop_size < activations_len: raise ValueError(f"pop_size must be higher or equal to {activations_len}")
 
-    if gen is None: gen = activation_functions_len
+    if gen is None: gen = activations_len
 
     if memory == 'gpu':
         x_train = transfer_to_gpu(x_train, dtype=x_train.dtype)
@@ -187,7 +187,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     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')
 
-    if neurons is not []:
+    if neurons != []:
         fit_start = False
         weight_evolve = True
         is_mlp = True
@@ -208,10 +208,10 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     loss_list = []
     target_pop = []
 
-    progress = initialize_loading_bar(total=activation_functions_len, desc="", ncols=79, bar_format=bar_format_learner)
+    progress = initialize_loading_bar(total=activations_len, desc="", ncols=79, bar_format=bar_format_learner)
 
-    if fit_start is False or pop_size > activation_functions_len:
-        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), neurons=neurons, activation_functions=activation_functions, population_size=pop_size, dtype=dtype)
+    if fit_start is False or pop_size > activations_len:
+        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), neurons=neurons, activations=activations, population_size=pop_size, dtype=dtype)
         
     else:
         weight_pop = [0] * pop_size
@@ -237,18 +237,18 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
             x_train_batch = cp.array(x_train_batch, dtype=x_train_batch.dtype, copy=False)
             y_train_batch = cp.array(y_train_batch, dtype=y_train.dtype)
 
-            if fit_start is True and i == 0 and j < activation_functions_len:
+            if fit_start is True and i == 0 and j < activations_len:
                 if start_this_act is not None and j == 0:
                     pass
                 else:
-                    act_pop[j] = activation_functions[j]
-                    W = plan_fit(x_train_batch, y_train_batch, activation_functions=act_pop[j], auto_normalization=auto_normalization, dtype=dtype)
+                    act_pop[j] = activations[j]
+                    W = plan_fit(x_train_batch, y_train_batch, activations=act_pop[j], auto_normalization=auto_normalization, dtype=dtype)
                     weight_pop[j] = W
                     
             if weight_evolve is False:
-                weight_pop[j] = plan_fit(x_train_batch, y_train_batch, activation_functions=act_pop[j], auto_normalization=auto_normalization, dtype=dtype) 
+                weight_pop[j] = plan_fit(x_train_batch, y_train_batch, activations=act_pop[j], auto_normalization=auto_normalization, dtype=dtype) 
             
-            model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activation_functions=act_pop[j], auto_normalization=auto_normalization, is_mlp=is_mlp)
+            model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activations=act_pop[j], auto_normalization=auto_normalization, is_mlp=is_mlp)
             acc = model[get_acc()]
  
             if loss == 'categorical_crossentropy':
@@ -306,7 +306,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
                 if target_acc is not None and best_acc >= target_acc:
                     progress.close()
                     train_model = evaluate(x_train, y_train, W=best_weight, 
-                                        activation_functions=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
+                                        activations=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
                     if loss == 'categorical_crossentropy':
                         train_loss = categorical_crossentropy(y_true_batch=y_train, 
                                                            y_pred_batch=train_model[get_preds_softmax()])
@@ -326,7 +326,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
                 if target_loss is not None and best_loss <= target_loss:
                     progress.close()
                     train_model = evaluate(x_train, y_train, W=best_weight,
-                                        activation_functions=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
+                                        activations=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
 
                     if loss == 'categorical_crossentropy':
                         train_loss = categorical_crossentropy(y_true_batch=y_train, 
@@ -378,7 +378,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
             if best_acc_per_gen_list[i] == best_acc_per_gen_list[i-1]:
                 progress.close()
                 train_model = evaluate(x_train, y_train, W=best_weight, 
-                                    activation_functions=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
+                                    activations=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
                 
             if loss == 'categorical_crossentropy':
                 train_loss = categorical_crossentropy(y_true_batch=y_train, 
@@ -399,7 +399,7 @@ def learn(x_train, y_train, optimizer, fit_start=True, gen=None, batch_size=1, p
     # Final evaluation
     progress.close()
     train_model = evaluate(x_train, y_train, W=best_weight,
-                        activation_functions=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
+                        activations=final_activations, auto_normalization=auto_normalization, is_mlp=is_mlp)
 
     if loss == 'categorical_crossentropy':
         train_loss = categorical_crossentropy(y_true_batch=y_train, 
@@ -420,7 +420,7 @@ def evaluate(
     x_test,
     y_test,
     W,
-    activation_functions=['linear'],
+    activations=['linear'],
     auto_normalization=False,
     is_mlp=False
 ) -> tuple:
@@ -434,7 +434,7 @@ def evaluate(
         
         W (cp.ndarray): Neural net weight matrix.
         
-        activation_functions (list): Activation list. Default = ['linear'].
+        activations (list): Activation list. Default = ['linear'].
 
         auto_normalization (bool, optional): Normalization for x_test ? Default = False.
         
@@ -446,15 +446,15 @@ def evaluate(
 
     if auto_normalization: x_test = normalization(x_test, dtype=x_test.dtype)
 
-    if isinstance(activation_functions, str):
-        activation_functions = [activation_functions]
-    elif isinstance(activation_functions, list):
-        activation_functions = [item if isinstance(item, list) or isinstance(item, str) else [item] for item in activation_functions]
+    if isinstance(activations, str):
+        activations = [activations]
+    elif isinstance(activations, list):
+        activations = [item if isinstance(item, list) or isinstance(item, str) else [item] for item in activations]
 
     if is_mlp:
         layer = x_test
         for i in range(len(W)):
-            if i != len(W) - 1 and i != 0: layer = apply_activation(layer, activation_functions[i])
+            if i != len(W) - 1 and i != 0: layer = apply_activation(layer, activations[i])
 
             layer = layer @ W[i].T
 
@@ -462,7 +462,7 @@ def evaluate(
 
     else:
 
-        x_test = apply_activation(x_test, activation_functions)
+        x_test = apply_activation(x_test, activations)
         result = x_test @ W.T
 
     max_vals = cp.max(result, axis=1, keepdims=True)

pyerualjetwork/visualizations.py

@@ -86,16 +86,16 @@ def draw_model_architecture(model_name, model_path=''):
     Visualizes the architecture of a neural network model with multiple inputs based on activation functions.
     """
     
-    from .model_operations import load_model, get_scaler, get_act_pot, get_weights
+    from .model_operations import load_model, get_scaler, get_act, get_weights
     
     model = load_model(model_name=model_name, model_path=model_path)
     
     W = model[get_weights()]
-    activation_potentiation = model[get_act_pot()]
+    activations = model[get_act()]
     scaler_params = model[get_scaler()]
     
     # Calculate dimensions based on number of activation functions
-    num_activations = len(activation_potentiation)
+    num_activations = len(activations)
     input_groups = num_activations  # Number of input groups equals number of activations
     num_inputs = W.shape[1]
 
@@ -138,7 +138,7 @@ def draw_model_architecture(model_name, model_path=''):
         for i in range(num_inputs):
             plt.plot(*pos[f'input_{group}_{i}'], 'o', color='lightgreen', markersize=20)
             plt.text(pos[f'input_{group}_{i}'][0] - 0.05, pos[f'input_{group}_{i}'][1], 
-                    f'Input #{i+1} ({activation_potentiation[group]})', ha='right', va='center')
+                    f'Input #{i+1} ({activations[group]})', ha='right', va='center')
             
             # Draw connections from input to summed input directly
             plt.plot([pos[f'input_{group}_{i}'][0], pos[f'summed_{i}'][0]],
@@ -325,7 +325,7 @@ def draw_activations(x_train, activation):
         return x_train
 
 
-def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation):
+def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
     
     from .metrics import metrics, confusion_matrix, roc_curve
     from .ui import loading_bars, initialize_loading_bar
@@ -433,7 +433,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
 
         for i in range(len(grid_full)):
 
-            Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
+            Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activations=activations))
             predict_progress.update(1)
 
         predict_progress.close()
@@ -453,7 +453,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
     plt.show()
 
 
-def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=None):
+def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
     
     from .model_operations import predict_model_ram
     from .data_operations import decode_one_hot
@@ -473,7 +473,7 @@ def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=Non
     Z = [None] * len(grid_full)
 
     for i in range(len(grid_full)):
-        Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
+        Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activations=activations))
 
     Z = np.array(Z, dtype=np.int32)
     Z = Z.reshape(xx.shape)
@@ -667,9 +667,9 @@ def update_weight_visualization_for_fit(ax, LTPW, artist2):
 """
 
 """ DISABLED
-def update_decision_boundary_for_fit(ax, x_val, y_val, activation_potentiation, LTPW, artist1):
+def update_decision_boundary_for_fit(ax, x_val, y_val, activations, LTPW, artist1):
 
-    art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activation_potentiation, LTPW, artist=artist1, ax=ax)
+    art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activations, LTPW, artist=artist1, ax=ax)
     artist1.append([*art1_1.collections, art1_2])
 """
 

pyerualjetwork/visualizations_cuda.py

@@ -87,16 +87,16 @@ def draw_model_architecture(model_name, model_path=''):
     Visualizes the architecture of a neural network model with multiple inputs based on activation functions.
     """
     
-    from .model_operations_cuda import load_model, get_scaler, get_act_pot, get_weights
+    from .model_operations_cuda import load_model, get_scaler, get_act, get_weights
     
     model = load_model(model_name=model_name, model_path=model_path)
     
     W = model[get_weights()]
-    activation_potentiation = model[get_act_pot()]
+    activations = model[get_act()]
     scaler_params = model[get_scaler()]
     
     # Calculate dimensions based on number of activation functions
-    num_activations = len(activation_potentiation)
+    num_activations = len(activations)
     input_groups = num_activations  # Number of input groups equals number of activations
     num_inputs = W.shape[1]
 
@@ -139,7 +139,7 @@ def draw_model_architecture(model_name, model_path=''):
         for i in range(num_inputs):
             plt.plot(*pos[f'input_{group}_{i}'], 'o', color='lightgreen', markersize=20)
             plt.text(pos[f'input_{group}_{i}'][0] - 0.05, pos[f'input_{group}_{i}'][1], 
-                    f'Input #{i+1} ({activation_potentiation[group]})', ha='right', va='center')
+                    f'Input #{i+1} ({activations[group]})', ha='right', va='center')
             
             # Draw connections from input to summed input directly
             plt.plot([pos[f'input_{group}_{i}'][0], pos[f'summed_{i}'][0]],
@@ -326,7 +326,7 @@ def draw_activations(x_train, activation):
         return x_train
 
 
-def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation):
+def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
     
     from .metrics_cuda import metrics, confusion_matrix, roc_curve
     from .ui import loading_bars, initialize_loading_bar
@@ -432,7 +432,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
 
     for i in range(len(grid_full)):
 
-        Z[i] = cp.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
+        Z[i] = cp.argmax(predict_model_ram(grid_full[i], W=W, activations=activations))
         predict_progress.update(1)
 
     predict_progress.close()
@@ -449,7 +449,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
     plt.show()
 
     
-def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=None):
+def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
     
     from .model_operations_cuda import predict_model_ram
     from .data_operations_cuda import decode_one_hot
@@ -469,7 +469,7 @@ def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=Non
     Z = [None] * len(grid_full)
 
     for i in range(len(grid_full)):
-        Z[i] = cp.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
+        Z[i] = cp.argmax(predict_model_ram(grid_full[i], W=W, activations=activations))
 
     Z = cp.array(Z, dtype=cp.int32)
     Z = Z.reshape(xx.shape)
@@ -638,8 +638,8 @@ def update_neural_web_for_fit(W, ax, G, artist):
 """
 
 """ DISABLED
-def update_decision_boundary_for_fit(ax, x_val, y_val, activation_potentiation, LTPW, artist1):
-    art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activation_potentiation, LTPW, artist=artist1, ax=ax)
+def update_decision_boundary_for_fit(ax, x_val, y_val, activations, LTPW, artist1):
+    art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activations, LTPW, artist=artist1, ax=ax)
     artist1.append([*art1_1.collections, art1_2])
 """
 

{pyerualjetwork-5b1.dist-info → pyerualjetwork-5b3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5b1
+Version: 5b3
 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-5b1.dist-info → pyerualjetwork-5b3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=risqkmpkcIsXvkm8BW4g3KW5_BUXwku_WY6PYtyh7as,2631
+pyerualjetwork/__init__.py,sha256=oRByBl-TW3JDnYYencDENYU_PkCV_f8piVIkK641M4g,2631
 pyerualjetwork/activation_functions.py,sha256=X7Kv8qv8oZq8hvTdUiV-GkFjKHRlKIQypRPXh6gdkm4,7614
 pyerualjetwork/activation_functions_cuda.py,sha256=pefklsl9QuSVbKwiUUHeF_ExN0bICH7QIF1MfoMU40Q,7665
 pyerualjetwork/data_operations.py,sha256=LKmLfl43zSCCuP2cWkBM-D6GtlhxXQggsNvZNUwHDe4,16347
@@ -14,12 +14,12 @@ pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,607
 pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
 pyerualjetwork/model_operations.py,sha256=F5qYAU578yrS1cUCwsaPJnqgfEAEUD_50vspakypTGY,15971
 pyerualjetwork/model_operations_cuda.py,sha256=lgYAEGUERTMU7TEWRVKaa3yk_IOt4Jo9RJP9lDsNREU,17206
-pyerualjetwork/neu.py,sha256=IppweAhAgImRLy9qrAp61VtGW7F18ckpJY8PdhI24-w,24952
-pyerualjetwork/neu_cuda.py,sha256=3NnpiQPwqcbbkQSLZNyCSZLJdb5DS_Q0_fEAzPYkEYU,26327
+pyerualjetwork/neu.py,sha256=bNl8nnL5R3WS8vNWxFbVzeX9eeGgownHdebbsKKNfvU,24948
+pyerualjetwork/neu_cuda.py,sha256=0hUCQ02tLFg1cGuqOxT3jfBx3W28hIL6nhEu4m2LeY8,25999
 pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
-pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
-pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
-pyerualjetwork-5b1.dist-info/METADATA,sha256=W2DBL6Mgzo3C-7Hwp4m9ASfpsw43PBGs5gcaBL6D2TE,7503
-pyerualjetwork-5b1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-5b1.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-5b1.dist-info/RECORD,,
+pyerualjetwork/visualizations.py,sha256=4DpboCi1GnJjKRVQ0RdGyQyHagZQTLUbCgSI7UHzd6o,28212
+pyerualjetwork/visualizations_cuda.py,sha256=7lYrkOdrjwQGB3T4k_vI8UDxsm_TRjzaSSg9GhlNczs,28667
+pyerualjetwork-5b3.dist-info/METADATA,sha256=jxcttUe0NJiI48xfRmAl4Ck0ZrodlOenv4UvkoPAVDI,7503
+pyerualjetwork-5b3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-5b3.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-5b3.dist-info/RECORD,,