pyerualjetwork 5.27__py3-none-any.whl → 5.30__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- pyerualjetwork/__init__.py +10 -10
- pyerualjetwork/cpu/__init__.py +27 -0
- pyerualjetwork/{activation_functions_cpu.py → cpu/activation_functions.py} +38 -2
- pyerualjetwork/{data_operations_cpu.py → cpu/data_ops.py} +8 -8
- pyerualjetwork/{ene_cpu.py → cpu/ene.py} +4 -4
- pyerualjetwork/{metrics_cpu.py → cpu/metrics.py} +1 -1
- pyerualjetwork/{model_operations_cpu.py → cpu/model_ops.py} +8 -8
- pyerualjetwork/{neu_cpu.py → cpu/nn.py} +13 -13
- pyerualjetwork/{visualizations_cpu.py → cpu/visualizations.py} +11 -11
- pyerualjetwork/cuda/__init__.py +27 -0
- pyerualjetwork/{activation_functions_cuda.py → cuda/activation_functions.py} +38 -0
- pyerualjetwork/{data_operations_cuda.py → cuda/data_ops.py} +9 -9
- pyerualjetwork/{ene_cuda.py → cuda/ene.py} +4 -4
- pyerualjetwork/{metrics_cuda.py → cuda/metrics.py} +1 -1
- pyerualjetwork/{model_operations_cuda.py → cuda/model_ops.py} +8 -8
- pyerualjetwork/{neu_cuda.py → cuda/nn.py} +15 -15
- pyerualjetwork/{visualizations_cuda.py → cuda/visualizations.py} +11 -11
- pyerualjetwork/help.py +5 -5
- pyerualjetwork/issue_solver.py +2 -2
- pyerualjetwork/{memory_operations.py → memory_ops.py} +1 -1
- {pyerualjetwork-5.27.dist-info → pyerualjetwork-5.30.dist-info}/METADATA +1 -1
- pyerualjetwork-5.30.dist-info/RECORD +28 -0
- pyerualjetwork-5.27.dist-info/RECORD +0 -26
- /pyerualjetwork/{loss_functions_cpu.py → cpu/loss_functions.py} +0 -0
- /pyerualjetwork/{loss_functions_cuda.py → cuda/loss_functions.py} +0 -0
- {pyerualjetwork-5.27.dist-info → pyerualjetwork-5.30.dist-info}/WHEEL +0 -0
- {pyerualjetwork-5.27.dist-info → pyerualjetwork-5.30.dist-info}/top_level.txt +0 -0
pyerualjetwork/__init__.py
CHANGED
@@ -11,17 +11,17 @@ training, and both detailed and simplified memory management.
|
|
11
11
|
|
12
12
|
Library (CPU) Main Modules:
|
13
13
|
---------------------------
|
14
|
-
-
|
15
|
-
-
|
16
|
-
-
|
17
|
-
-
|
14
|
+
- cpu.nn
|
15
|
+
- cpu.ene
|
16
|
+
- cpu.data_ops
|
17
|
+
- cpu.model_ops
|
18
18
|
|
19
19
|
Library (GPU) Main Modules:
|
20
20
|
---------------------------
|
21
|
-
-
|
22
|
-
-
|
23
|
-
-
|
24
|
-
-
|
21
|
+
- cuda.nn
|
22
|
+
- cuda.ene
|
23
|
+
- cuda.data_ops
|
24
|
+
- cuda.model_ops
|
25
25
|
|
26
26
|
Memory Module:
|
27
27
|
--------------
|
@@ -35,14 +35,14 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
35
35
|
|
36
36
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
37
37
|
|
38
|
-
-
|
38
|
+
- Creator: Hasan Can Beydili
|
39
39
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
40
40
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
41
41
|
- Instagram: https://www.instagram.com/canbeydilj
|
42
42
|
- Contact: tchasancan@gmail.com
|
43
43
|
"""
|
44
44
|
|
45
|
-
__version__ = "5.
|
45
|
+
__version__ = "5.30"
|
46
46
|
__update__ = """* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES
|
47
47
|
* PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main
|
48
48
|
* PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
@@ -0,0 +1,27 @@
|
|
1
|
+
"""
|
2
|
+
CPU
|
3
|
+
===
|
4
|
+
The modules contained in this folder and their functions compute data on the central processing unit and store it in the CPU's RAM..
|
5
|
+
|
6
|
+
Modules in the folder:
|
7
|
+
----------------------
|
8
|
+
- activation_functions
|
9
|
+
- data_operations
|
10
|
+
- ene
|
11
|
+
- loss_functions
|
12
|
+
- metrics
|
13
|
+
- model_operations
|
14
|
+
- nn
|
15
|
+
- visualizations
|
16
|
+
|
17
|
+
Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes
|
18
|
+
|
19
|
+
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
20
|
+
|
21
|
+
- Creator: Hasan Can Beydili
|
22
|
+
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
23
|
+
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
24
|
+
- Instagram: https://www.instagram.com/canbeydilj
|
25
|
+
- Contact: tchasancan@gmail.com
|
26
|
+
|
27
|
+
"""
|
@@ -1,8 +1,45 @@
|
|
1
|
+
"""
|
2
|
+
|
3
|
+
Activation Functions on CPU
|
4
|
+
===========================
|
5
|
+
This module contains activation functions that run on the CPU.
|
6
|
+
|
7
|
+
|
8
|
+
Module functions:
|
9
|
+
-----------------
|
10
|
+
- 'sigmoid': Sigmoid,
|
11
|
+
- 'mod_circular': modular_circular_activation,
|
12
|
+
- 'tanh_circular': tanh_circular_activation,
|
13
|
+
- 'leaky_relu': leaky_relu,
|
14
|
+
- 'relu': Relu,
|
15
|
+
- 'gelu': gelu,
|
16
|
+
- 'tanh': tanh,
|
17
|
+
- 'sinakt': sinakt,
|
18
|
+
- 'p_squared': p_squared,
|
19
|
+
- 'sglu': lambda x: sglu(x, alpha=1.0),
|
20
|
+
- 'dlrelu': dlrelu,
|
21
|
+
- 'sin_plus': sin_plus,
|
22
|
+
- 'acos': lambda x: acos(x, alpha=1.0, beta=0.0),
|
23
|
+
- 'isra': isra,
|
24
|
+
- 'waveakt': waveakt,
|
25
|
+
- 'arctan': arctan,
|
26
|
+
- 'bent_identity': bent_identity,
|
27
|
+
- 'softsign': softsign,
|
28
|
+
- 'pwl': pwl,
|
29
|
+
- 'sine': sine,
|
30
|
+
- 'tanh_square': tanh_square,
|
31
|
+
- 'linear':,
|
32
|
+
- 'sine_square': sine_square,
|
33
|
+
- 'logarithmic': logarithmic,
|
34
|
+
- 'sine_offset': lambda x: sine_offset(x, 1.0),
|
35
|
+
- 'spiral': spiral_activation,
|
36
|
+
- 'circular': circular_activation
|
37
|
+
"""
|
38
|
+
|
1
39
|
import numpy as np
|
2
40
|
from scipy.special import expit, softmax
|
3
41
|
import warnings
|
4
42
|
|
5
|
-
|
6
43
|
# ACTIVATION FUNCTIONS -----
|
7
44
|
|
8
45
|
def all_activations():
|
@@ -71,7 +108,6 @@ def Relu(
|
|
71
108
|
|
72
109
|
return np.maximum(0, x)
|
73
110
|
|
74
|
-
|
75
111
|
def tanh(x):
|
76
112
|
return np.tanh(x)
|
77
113
|
|
@@ -21,7 +21,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
21
21
|
|
22
22
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
23
23
|
|
24
|
-
-
|
24
|
+
- Creator: Hasan Can Beydili
|
25
25
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
26
26
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
27
27
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -46,7 +46,7 @@ def encode_one_hot(y_train, y_test=None, summary=False):
|
|
46
46
|
Returns:
|
47
47
|
tuple: One-hot encoded y_train and (if given) y_test.
|
48
48
|
"""
|
49
|
-
from
|
49
|
+
from ..memory_ops import optimize_labels
|
50
50
|
|
51
51
|
classes = np.unique(y_train)
|
52
52
|
class_count = len(classes)
|
@@ -154,8 +154,8 @@ def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=np.float32
|
|
154
154
|
x_balanced -- Balanced input dataset (numpy array format)
|
155
155
|
y_balanced -- Balanced class labels (one-hot encoded, numpy array format)
|
156
156
|
"""
|
157
|
-
from
|
158
|
-
from
|
157
|
+
from ..ui import loading_bars, get_loading_bar_style
|
158
|
+
from ..memory_ops import transfer_to_cpu
|
159
159
|
|
160
160
|
x_train = transfer_to_cpu(x_train, dtype=dtype)
|
161
161
|
|
@@ -229,8 +229,8 @@ def auto_balancer(x_train, y_train, dtype=np.float32):
|
|
229
229
|
Returns:
|
230
230
|
tuple: A tuple containing balanced input data and labels.
|
231
231
|
"""
|
232
|
-
from
|
233
|
-
from
|
232
|
+
from ..ui import loading_bars, get_loading_bar_style
|
233
|
+
from ..memory_ops import transfer_to_cpu
|
234
234
|
|
235
235
|
x_train = transfer_to_cpu(x_train, dtype=dtype)
|
236
236
|
|
@@ -295,8 +295,8 @@ def synthetic_augmentation(x, y, dtype=np.float32):
|
|
295
295
|
Returns:
|
296
296
|
x_train_balanced, y_train_balanced (numpy array format)
|
297
297
|
"""
|
298
|
-
from
|
299
|
-
from
|
298
|
+
from ..ui import loading_bars, get_loading_bar_style
|
299
|
+
from ..memory_ops import transfer_to_cpu
|
300
300
|
|
301
301
|
x = transfer_to_cpu(x, dtype=dtype)
|
302
302
|
|
@@ -21,7 +21,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
21
21
|
|
22
22
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
23
23
|
|
24
|
-
-
|
24
|
+
- Creator: Hasan Can Beydili
|
25
25
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
26
26
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
27
27
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -34,9 +34,9 @@ import math
|
|
34
34
|
import copy
|
35
35
|
|
36
36
|
### LIBRARY IMPORTS ###
|
37
|
-
from .
|
38
|
-
from
|
39
|
-
from .
|
37
|
+
from .data_ops import non_neg_normalization
|
38
|
+
from ..ui import loading_bars, initialize_loading_bar
|
39
|
+
from .activation_functions import apply_activation, all_activations
|
40
40
|
|
41
41
|
def define_genomes(input_shape, output_shape, population_size, neurons=[], activation_functions=[], dtype=np.float32):
|
42
42
|
"""
|
@@ -13,7 +13,7 @@ def metrics(y_ts, test_preds, average='weighted'):
|
|
13
13
|
tuple: Precision, recall, F1 score.
|
14
14
|
"""
|
15
15
|
|
16
|
-
from .
|
16
|
+
from .data_ops import decode_one_hot
|
17
17
|
|
18
18
|
y_test_d = decode_one_hot(y_ts)
|
19
19
|
y_test_d = np.array(y_test_d)
|
@@ -38,7 +38,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
38
38
|
|
39
39
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
40
40
|
|
41
|
-
-
|
41
|
+
- Creator: Hasan Can Beydili
|
42
42
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
43
43
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
44
44
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -100,8 +100,8 @@ def save_model(model_name,
|
|
100
100
|
No return.
|
101
101
|
"""
|
102
102
|
|
103
|
-
from .
|
104
|
-
from
|
103
|
+
from .visualizations import draw_model_architecture
|
104
|
+
from .. import __version__
|
105
105
|
|
106
106
|
if model_type != 'PLAN' and model_type != 'MLP' and model_type != 'PTNN':
|
107
107
|
raise ValueError("model_type parameter must be 'PLAN', 'MLP' or 'PTNN'.")
|
@@ -303,7 +303,7 @@ def load_model(model_name,
|
|
303
303
|
lists: Weights, None, test_accuracy, activations, scaler_params, None, model_type, weight_type, weight_format, device_version, (list[df_elements])=Pandas DataFrame of the model
|
304
304
|
"""
|
305
305
|
|
306
|
-
from
|
306
|
+
from .. import __version__
|
307
307
|
|
308
308
|
try:
|
309
309
|
|
@@ -395,8 +395,8 @@ def predict_from_storage(Input, model_name, model_path=''):
|
|
395
395
|
ndarray: Output from the model.
|
396
396
|
"""
|
397
397
|
|
398
|
-
from .
|
399
|
-
from .
|
398
|
+
from .activation_functions import apply_activation
|
399
|
+
from .data_ops import standard_scaler
|
400
400
|
|
401
401
|
try:
|
402
402
|
|
@@ -505,8 +505,8 @@ def predict_from_memory(Input, W, scaler_params=None, activations=['linear'], ac
|
|
505
505
|
ndarray: Output from the model.
|
506
506
|
"""
|
507
507
|
|
508
|
-
from .
|
509
|
-
from .
|
508
|
+
from .data_ops import standard_scaler
|
509
|
+
from .activation_functions import apply_activation
|
510
510
|
|
511
511
|
if model_type != 'PLAN' and model_type != 'MLP' and model_type != 'PTNN': raise ValueError("model_type parameter must be 'PLAN', 'MLP' or 'PTNN'.")
|
512
512
|
|
@@ -2,7 +2,7 @@
|
|
2
2
|
"""
|
3
3
|
|
4
4
|
|
5
|
-
|
5
|
+
NN (Neural Networks) on CPU
|
6
6
|
============================
|
7
7
|
This module hosts functions for training and evaluating artificial neural networks on CPU for labeled classification tasks (for now).
|
8
8
|
|
@@ -40,7 +40,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
40
40
|
|
41
41
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
42
42
|
|
43
|
-
-
|
43
|
+
- Creator: Hasan Can Beydili
|
44
44
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
45
45
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
46
46
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -52,14 +52,14 @@ import copy
|
|
52
52
|
import random
|
53
53
|
|
54
54
|
### LIBRARY IMPORTS ###
|
55
|
-
from
|
56
|
-
from .
|
57
|
-
from .
|
58
|
-
from .
|
59
|
-
from
|
60
|
-
from .
|
61
|
-
from
|
62
|
-
from .
|
55
|
+
from ..ui import loading_bars, initialize_loading_bar
|
56
|
+
from .data_ops import normalization, batcher
|
57
|
+
from .activation_functions import apply_activation, all_activations
|
58
|
+
from .model_ops import get_acc, get_preds_softmax
|
59
|
+
from ..memory_ops import optimize_labels
|
60
|
+
from .loss_functions import categorical_crossentropy, binary_crossentropy
|
61
|
+
from ..fitness_functions import wals
|
62
|
+
from .visualizations import (
|
63
63
|
draw_neural_web,
|
64
64
|
display_visualizations_for_learner,
|
65
65
|
update_history_plots_for_learner,
|
@@ -179,7 +179,7 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
|
|
179
179
|
tuple: A list for model parameters: [Weight matrix, Train Preds, Train Accuracy, [Activations functions]].
|
180
180
|
"""
|
181
181
|
|
182
|
-
from .
|
182
|
+
from .ene import define_genomes
|
183
183
|
|
184
184
|
data = 'Train'
|
185
185
|
|
@@ -307,9 +307,9 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
|
|
307
307
|
progress.last_print_n = 0
|
308
308
|
progress.update(0)
|
309
309
|
|
310
|
-
|
310
|
+
x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
|
311
311
|
|
312
|
-
|
312
|
+
for j in range(pop_size):
|
313
313
|
|
314
314
|
if fit_start is True and i == 0:
|
315
315
|
if start_this_act is not None and j == 0:
|
@@ -86,7 +86,7 @@ def draw_model_architecture(model_name, model_path=''):
|
|
86
86
|
Visualizes the architecture of a neural network model with multiple inputs based on activation functions.
|
87
87
|
"""
|
88
88
|
|
89
|
-
from .
|
89
|
+
from .model_ops import load_model, get_scaler, get_act, get_weights
|
90
90
|
|
91
91
|
model = load_model(model_name=model_name, model_path=model_path)
|
92
92
|
|
@@ -182,7 +182,7 @@ def draw_model_architecture(model_name, model_path=''):
|
|
182
182
|
|
183
183
|
def draw_activations(x_train, activation):
|
184
184
|
|
185
|
-
from . import
|
185
|
+
from . import activation_functions as af
|
186
186
|
|
187
187
|
if activation == 'sigmoid':
|
188
188
|
result = af.Sigmoid(x_train)
|
@@ -327,10 +327,10 @@ def draw_activations(x_train, activation):
|
|
327
327
|
|
328
328
|
def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
|
329
329
|
|
330
|
-
from .
|
331
|
-
from
|
332
|
-
from .
|
333
|
-
from .
|
330
|
+
from .metrics import metrics, confusion_matrix, roc_curve
|
331
|
+
from ..ui import loading_bars, initialize_loading_bar
|
332
|
+
from .data_ops import decode_one_hot
|
333
|
+
from .model_ops import predict_model_ram
|
334
334
|
|
335
335
|
bar_format_normal = loading_bars()[0]
|
336
336
|
|
@@ -455,8 +455,8 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
|
|
455
455
|
|
456
456
|
def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
|
457
457
|
|
458
|
-
from .
|
459
|
-
from .
|
458
|
+
from .model_ops import predict_model_ram
|
459
|
+
from .data_ops import decode_one_hot
|
460
460
|
|
461
461
|
feature_indices = [0, 1]
|
462
462
|
|
@@ -513,8 +513,8 @@ def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
|
|
513
513
|
|
514
514
|
def plot_decision_space(x, y, y_preds=None, s=100, color='tab20'):
|
515
515
|
|
516
|
-
from .
|
517
|
-
from .
|
516
|
+
from .metrics import pca
|
517
|
+
from .data_ops import decode_one_hot
|
518
518
|
|
519
519
|
if x.shape[1] > 2:
|
520
520
|
|
@@ -707,7 +707,7 @@ def show():
|
|
707
707
|
|
708
708
|
def initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train):
|
709
709
|
|
710
|
-
from .
|
710
|
+
from .data_ops import find_closest_factors
|
711
711
|
viz_objects = {}
|
712
712
|
|
713
713
|
if show_history:
|
@@ -0,0 +1,27 @@
|
|
1
|
+
"""
|
2
|
+
CUDA
|
3
|
+
====
|
4
|
+
The modules contained in this folder and their functions compute data on a graphics processing unit with CUDA technology and a installed CUDA toolkit, storing it in the GPU's VRAM.
|
5
|
+
|
6
|
+
Modules in the folder:
|
7
|
+
----------------------
|
8
|
+
- activation_functions
|
9
|
+
- data_operations
|
10
|
+
- ene
|
11
|
+
- loss_functions
|
12
|
+
- metrics
|
13
|
+
- model_operations
|
14
|
+
- nn
|
15
|
+
- visualizations
|
16
|
+
|
17
|
+
Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes
|
18
|
+
|
19
|
+
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
20
|
+
|
21
|
+
- Creator: Hasan Can Beydili
|
22
|
+
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
23
|
+
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
24
|
+
- Instagram: https://www.instagram.com/canbeydilj
|
25
|
+
- Contact: tchasancan@gmail.com
|
26
|
+
|
27
|
+
"""
|
@@ -1,3 +1,41 @@
|
|
1
|
+
"""
|
2
|
+
|
3
|
+
Activation Functions on CUDA
|
4
|
+
============================
|
5
|
+
This module contains activation functions that run on the CUDA GPU.
|
6
|
+
|
7
|
+
|
8
|
+
Module functions:
|
9
|
+
-----------------
|
10
|
+
- 'sigmoid': Sigmoid,
|
11
|
+
- 'mod_circular': modular_circular_activation,
|
12
|
+
- 'tanh_circular': tanh_circular_activation,
|
13
|
+
- 'leaky_relu': leaky_relu,
|
14
|
+
- 'relu': Relu,
|
15
|
+
- 'gelu': gelu,
|
16
|
+
- 'tanh': tanh,
|
17
|
+
- 'sinakt': sinakt,
|
18
|
+
- 'p_squared': p_squared,
|
19
|
+
- 'sglu': lambda x: sglu(x, alpha=1.0),
|
20
|
+
- 'dlrelu': dlrelu,
|
21
|
+
- 'sin_plus': sin_plus,
|
22
|
+
- 'acos': lambda x: acos(x, alpha=1.0, beta=0.0),
|
23
|
+
- 'isra': isra,
|
24
|
+
- 'waveakt': waveakt,
|
25
|
+
- 'arctan': arctan,
|
26
|
+
- 'bent_identity': bent_identity,
|
27
|
+
- 'softsign': softsign,
|
28
|
+
- 'pwl': pwl,
|
29
|
+
- 'sine': sine,
|
30
|
+
- 'tanh_square': tanh_square,
|
31
|
+
- 'linear':,
|
32
|
+
- 'sine_square': sine_square,
|
33
|
+
- 'logarithmic': logarithmic,
|
34
|
+
- 'sine_offset': lambda x: sine_offset(x, 1.0),
|
35
|
+
- 'spiral': spiral_activation,
|
36
|
+
- 'circular': circular_activation
|
37
|
+
"""
|
38
|
+
|
1
39
|
import cupy as cp
|
2
40
|
import numpy as np
|
3
41
|
from scipy.special import expit, softmax
|
@@ -21,7 +21,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
21
21
|
|
22
22
|
PyerualJetwork document: https://github.com/HCB06/Anaplan/blob/main/Welcome_to_Anaplan/ANAPLAN_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
23
23
|
|
24
|
-
-
|
24
|
+
- Creator: Hasan Can Beydili
|
25
25
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
26
26
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
27
27
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -47,7 +47,7 @@ def encode_one_hot(y_train, y_test=None, summary=False):
|
|
47
47
|
tuple: One-hot encoded y_train and (if given: y_test).
|
48
48
|
"""
|
49
49
|
|
50
|
-
from
|
50
|
+
from ..memory_ops import optimize_labels, transfer_to_cpu
|
51
51
|
|
52
52
|
y_train = transfer_to_cpu(y_train,dtype=y_train.dtype)
|
53
53
|
y_test = transfer_to_cpu(y_test,dtype=y_test.dtype)
|
@@ -113,7 +113,7 @@ def split(X, y, test_size, random_state=42, dtype=cp.float32, shuffle_in_cpu=Fal
|
|
113
113
|
Returns:
|
114
114
|
tuple: x_train, x_test, y_train, y_test as ordered training and testing data subsets.
|
115
115
|
"""
|
116
|
-
from
|
116
|
+
from ..memory_ops import transfer_to_gpu, optimize_labels
|
117
117
|
|
118
118
|
X = transfer_to_gpu(X, dtype=dtype)
|
119
119
|
y = optimize_labels(y, one_hot_encoded=False, cuda=True)
|
@@ -172,8 +172,8 @@ def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32
|
|
172
172
|
x_balanced -- Balanced input dataset (cupy array format)
|
173
173
|
y_balanced -- Balanced class labels (one-hot encoded, cupy array format)
|
174
174
|
"""
|
175
|
-
from
|
176
|
-
from
|
175
|
+
from ..ui import loading_bars, get_loading_bar_style
|
176
|
+
from ..memory_ops import transfer_to_gpu
|
177
177
|
|
178
178
|
bar_format = loading_bars()[0]
|
179
179
|
x_train = transfer_to_gpu(x_train, dtype=dtype)
|
@@ -261,8 +261,8 @@ def auto_balancer(x_train, y_train, dtype=cp.float32, shuffle_in_cpu=False):
|
|
261
261
|
tuple: A tuple containing balanced input data and labels.
|
262
262
|
"""
|
263
263
|
|
264
|
-
from
|
265
|
-
from
|
264
|
+
from ..ui import loading_bars, get_loading_bar_style
|
265
|
+
from ..memory_ops import transfer_to_gpu
|
266
266
|
|
267
267
|
x_train = transfer_to_gpu(x_train, dtype=dtype)
|
268
268
|
y_train = transfer_to_gpu(y_train, dtype=y_train.dtype)
|
@@ -331,8 +331,8 @@ def synthetic_augmentation(x_train, y_train, dtype=cp.float32, shuffle_in_cpu=Fa
|
|
331
331
|
Returns:
|
332
332
|
x_train_balanced, y_train_balanced (cupy array format)
|
333
333
|
"""
|
334
|
-
from
|
335
|
-
from
|
334
|
+
from ..ui import loading_bars, get_loading_bar_style
|
335
|
+
from ..memory_ops import transfer_to_gpu
|
336
336
|
|
337
337
|
x = transfer_to_gpu(x_train, dtype=dtype)
|
338
338
|
y = transfer_to_gpu(y_train, dtype=y_train.dtype)
|
@@ -21,7 +21,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
21
21
|
|
22
22
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
23
23
|
|
24
|
-
-
|
24
|
+
- Creator: Hasan Can Beydili
|
25
25
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
26
26
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
27
27
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -35,9 +35,9 @@ import math
|
|
35
35
|
import copy
|
36
36
|
|
37
37
|
### LIBRARY IMPORTS ###
|
38
|
-
from .
|
39
|
-
from
|
40
|
-
from .
|
38
|
+
from .data_ops import non_neg_normalization
|
39
|
+
from ..ui import loading_bars, initialize_loading_bar
|
40
|
+
from .activation_functions import apply_activation, all_activations
|
41
41
|
|
42
42
|
def define_genomes(input_shape, output_shape, population_size, neurons=[], activation_functions=[], dtype=cp.float32):
|
43
43
|
"""
|
@@ -39,7 +39,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
39
39
|
|
40
40
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
41
41
|
|
42
|
-
-
|
42
|
+
- Creator: Hasan Can Beydili
|
43
43
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
44
44
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
45
45
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -105,8 +105,8 @@ def save_model(model_name,
|
|
105
105
|
No return.
|
106
106
|
"""
|
107
107
|
|
108
|
-
from .
|
109
|
-
from
|
108
|
+
from .visualizations import draw_model_architecture
|
109
|
+
from .. import __version__
|
110
110
|
|
111
111
|
if model_type != 'PLAN' and model_type != 'MLP' and model_type != 'PTNN':
|
112
112
|
raise ValueError("model_type parameter must be 'PLAN', 'MLP' or 'PTNN'.")
|
@@ -316,7 +316,7 @@ def load_model(model_name,
|
|
316
316
|
lists: Weights, None, test_accuracy, activations, scaler_params, None, model_type, weight_type, weight_format, device_version, (list[df_elements])=Pandas DataFrame of the model
|
317
317
|
"""
|
318
318
|
|
319
|
-
from
|
319
|
+
from .. import __version__
|
320
320
|
|
321
321
|
try:
|
322
322
|
|
@@ -419,8 +419,8 @@ def predict_from_storage(Input, model_name, model_path='', dtype=cp.float32):
|
|
419
419
|
|
420
420
|
Input = cp.array(Input, dtype=dtype, copy=False)
|
421
421
|
|
422
|
-
from .
|
423
|
-
from .
|
422
|
+
from .activation_functions import apply_activation
|
423
|
+
from .data_ops import standard_scaler
|
424
424
|
|
425
425
|
try:
|
426
426
|
|
@@ -533,8 +533,8 @@ def predict_from_memory(Input, W, scaler_params=None, activations=['linear'], ac
|
|
533
533
|
cupyarray: Output from the model.
|
534
534
|
"""
|
535
535
|
|
536
|
-
from .
|
537
|
-
from .
|
536
|
+
from .data_ops import standard_scaler
|
537
|
+
from .activation_functions import apply_activation
|
538
538
|
|
539
539
|
if isinstance(activations, str):
|
540
540
|
activations = [activations]
|
@@ -2,7 +2,7 @@
|
|
2
2
|
"""
|
3
3
|
|
4
4
|
|
5
|
-
|
5
|
+
NN (Neural Networks) on CUDA
|
6
6
|
=============================
|
7
7
|
This module hosts functions for training and evaluating artificial neural networks on CUDA GPU for labeled classification tasks (for now).
|
8
8
|
|
@@ -41,7 +41,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
41
41
|
|
42
42
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
43
43
|
|
44
|
-
-
|
44
|
+
- Creator: Hasan Can Beydili
|
45
45
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
46
46
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
47
47
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -54,14 +54,14 @@ import copy
|
|
54
54
|
import random
|
55
55
|
|
56
56
|
### LIBRARY IMPORTS ###
|
57
|
-
from
|
58
|
-
from .
|
59
|
-
from .
|
60
|
-
from .
|
61
|
-
from
|
62
|
-
from .
|
63
|
-
from
|
64
|
-
from .
|
57
|
+
from ..ui import loading_bars, initialize_loading_bar
|
58
|
+
from .data_ops import normalization
|
59
|
+
from .activation_functions import apply_activation, all_activations
|
60
|
+
from .model_ops import get_acc, get_preds_softmax
|
61
|
+
from ..memory_ops import transfer_to_gpu, transfer_to_cpu, optimize_labels
|
62
|
+
from .loss_functions import categorical_crossentropy, binary_crossentropy
|
63
|
+
from ..fitness_functions import wals
|
64
|
+
from .visualizations import (
|
65
65
|
draw_neural_web,
|
66
66
|
display_visualizations_for_learner,
|
67
67
|
update_history_plots_for_learner,
|
@@ -176,7 +176,7 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
|
|
176
176
|
tuple: A list for model parameters: [Weight matrix, Train Preds, Train Accuracy, [Activations functions]]. You can acces this parameters in model_operations module. For example: model_operations.get_weights() for Weight matrix.
|
177
177
|
"""
|
178
178
|
|
179
|
-
from .
|
179
|
+
from .ene import define_genomes
|
180
180
|
|
181
181
|
data = 'Train'
|
182
182
|
|
@@ -197,13 +197,13 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
|
|
197
197
|
x_train = transfer_to_gpu(x_train, dtype=x_train.dtype)
|
198
198
|
y_train = transfer_to_gpu(y_train, dtype=y_train.dtype)
|
199
199
|
|
200
|
-
from .
|
200
|
+
from .data_ops import batcher
|
201
201
|
|
202
202
|
elif memory == 'cpu':
|
203
203
|
x_train = transfer_to_cpu(x_train, dtype=x_train.dtype)
|
204
204
|
y_train = transfer_to_cpu(y_train, dtype=y_train.dtype)
|
205
205
|
|
206
|
-
from .
|
206
|
+
from pyerualjetwork.cpu.data_ops import batcher
|
207
207
|
|
208
208
|
else:
|
209
209
|
raise ValueError("memory parameter must be 'cpu' or 'gpu'.")
|
@@ -316,9 +316,9 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
|
|
316
316
|
progress.last_print_n = 0
|
317
317
|
progress.update(0)
|
318
318
|
|
319
|
-
|
319
|
+
x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
|
320
320
|
|
321
|
-
|
321
|
+
for j in range(pop_size):
|
322
322
|
|
323
323
|
x_train_batch = cp.array(x_train_batch, dtype=x_train_batch.dtype, copy=False)
|
324
324
|
y_train_batch = cp.array(y_train_batch, dtype=y_train.dtype)
|
@@ -87,7 +87,7 @@ def draw_model_architecture(model_name, model_path=''):
|
|
87
87
|
Visualizes the architecture of a neural network model with multiple inputs based on activation functions.
|
88
88
|
"""
|
89
89
|
|
90
|
-
from .
|
90
|
+
from .model_ops import load_model, get_scaler, get_act, get_weights
|
91
91
|
|
92
92
|
model = load_model(model_name=model_name, model_path=model_path)
|
93
93
|
|
@@ -183,7 +183,7 @@ def draw_model_architecture(model_name, model_path=''):
|
|
183
183
|
|
184
184
|
def draw_activations(x_train, activation):
|
185
185
|
|
186
|
-
from . import
|
186
|
+
from . import activation_functions as af
|
187
187
|
|
188
188
|
if activation == 'sigmoid':
|
189
189
|
result = af.Sigmoid(x_train)
|
@@ -328,10 +328,10 @@ def draw_activations(x_train, activation):
|
|
328
328
|
|
329
329
|
def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
|
330
330
|
|
331
|
-
from .
|
332
|
-
from
|
333
|
-
from .
|
334
|
-
from .
|
331
|
+
from .metrics import metrics, confusion_matrix, roc_curve
|
332
|
+
from ..ui import loading_bars, initialize_loading_bar
|
333
|
+
from .data_ops import decode_one_hot
|
334
|
+
from .model_ops import predict_model_ram
|
335
335
|
|
336
336
|
bar_format_normal = loading_bars()[0]
|
337
337
|
|
@@ -451,8 +451,8 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activations):
|
|
451
451
|
|
452
452
|
def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
|
453
453
|
|
454
|
-
from .
|
455
|
-
from .
|
454
|
+
from .model_ops import predict_model_ram
|
455
|
+
from .data_ops import decode_one_hot
|
456
456
|
|
457
457
|
feature_indices = [0, 1]
|
458
458
|
|
@@ -509,8 +509,8 @@ def plot_decision_boundary(x, y, activations, W, artist=None, ax=None):
|
|
509
509
|
|
510
510
|
def plot_decision_space(x, y, y_preds=None, s=100, color='tab20'):
|
511
511
|
|
512
|
-
from .
|
513
|
-
from .
|
512
|
+
from .metrics import pca
|
513
|
+
from .data_ops import decode_one_hot
|
514
514
|
|
515
515
|
if x.shape[1] > 2:
|
516
516
|
|
@@ -699,7 +699,7 @@ def update_neuron_history_for_learner(LTPW, ax1, row, col, class_count, artist5,
|
|
699
699
|
|
700
700
|
def initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train):
|
701
701
|
|
702
|
-
from .
|
702
|
+
from .data_ops import find_closest_factors
|
703
703
|
viz_objects = {}
|
704
704
|
|
705
705
|
if show_history:
|
pyerualjetwork/help.py
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
from pyerualjetwork.
|
1
|
+
from pyerualjetwork.cuda.nn import all_activations
|
2
2
|
|
3
3
|
|
4
4
|
def activation_potentiation():
|
@@ -11,7 +11,7 @@ def activation_potentiation():
|
|
11
11
|
|
12
12
|
def docs_and_examples():
|
13
13
|
|
14
|
-
print('PLAN document: https://github.com/HCB06/
|
15
|
-
print('PLAN examples: https://github.com/HCB06/
|
16
|
-
print('
|
17
|
-
print('
|
14
|
+
print('PLAN & ENE document: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PLAN\n')
|
15
|
+
print('PLAN examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes\n')
|
16
|
+
print('ENE examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork/ExampleCodes/ENE\n')
|
17
|
+
print('PyerualJetwork document and examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJetwork')
|
pyerualjetwork/issue_solver.py
CHANGED
@@ -38,7 +38,7 @@ def update_model_to_v5(model_name, model_path, is_cuda):
|
|
38
38
|
|
39
39
|
if is_cuda:
|
40
40
|
|
41
|
-
from .
|
41
|
+
from pyerualjetwork.cuda.model_ops import (get_act,
|
42
42
|
get_weights,
|
43
43
|
get_scaler,
|
44
44
|
get_acc,
|
@@ -49,7 +49,7 @@ def update_model_to_v5(model_name, model_path, is_cuda):
|
|
49
49
|
save_model)
|
50
50
|
else:
|
51
51
|
|
52
|
-
from .
|
52
|
+
from pyerualjetwork.cpu.model_ops import (get_act,
|
53
53
|
get_weights,
|
54
54
|
get_scaler,
|
55
55
|
get_acc,
|
@@ -17,7 +17,7 @@ Examples: https://github.com/HCB06/PyerualJetwork/tree/main/Welcome_to_PyerualJe
|
|
17
17
|
|
18
18
|
PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf
|
19
19
|
|
20
|
-
-
|
20
|
+
- Creator: Hasan Can Beydili
|
21
21
|
- YouTube: https://www.youtube.com/@HasanCanBeydili
|
22
22
|
- Linkedin: https://www.linkedin.com/in/hasan-can-beydili-77a1b9270/
|
23
23
|
- Instagram: https://www.instagram.com/canbeydilj
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: pyerualjetwork
|
3
|
-
Version: 5.
|
3
|
+
Version: 5.30
|
4
4
|
Summary: PyereualJetwork is a GPU-accelerated machine learning library in Python for professionals and researchers. It features PLAN, MLP, Deep Learning training, and ENE (Eugenic NeuroEvolution) for genetic optimization, applicable to genetic algorithms or Reinforcement Learning (RL). The library includes data pre-processing, visualizations, model saving/loading, prediction, evaluation, training, and detailed or simplified memory management.
|
5
5
|
Author: Hasan Can Beydili
|
6
6
|
Author-email: tchasancan@gmail.com
|
@@ -0,0 +1,28 @@
|
|
1
|
+
pyerualjetwork/__init__.py,sha256=QGem2FufN_W5bOFfUM2NtYGX_TDV0iUrGuO1YsXu1oU,2704
|
2
|
+
pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
|
3
|
+
pyerualjetwork/help.py,sha256=Nyi0gHAN9ZnO4wgQLeENt0n7tSCZ3hJmjaJ853eGjCE,831
|
4
|
+
pyerualjetwork/issue_solver.py,sha256=3pZTGotS29sy3pIuGQoJFUePibtSzS-tNoU80T_Usgk,3131
|
5
|
+
pyerualjetwork/memory_ops.py,sha256=TUFh9SYWCKL6N-vNdWId_EwU313TuZomQCHOrltrD-4,14280
|
6
|
+
pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
|
7
|
+
pyerualjetwork/cpu/__init__.py,sha256=0yAYner_-v7SmT3P7JV2itU8xJUQdQpb40dhAMQiZkc,829
|
8
|
+
pyerualjetwork/cpu/activation_functions.py,sha256=BVr-iP7lOl_fm91Z3Aqr22Z9gigMZSPVwtAPWlfAcQs,6676
|
9
|
+
pyerualjetwork/cpu/data_ops.py,sha256=-XeMLRTQ5g7GMJdKYVMKJA7bSj6PbKEEpbQDRRhAIT4,16166
|
10
|
+
pyerualjetwork/cpu/ene.py,sha256=ZLCaCxkpAmFLdxDS2OH-S8fT4jKq4HNVCHgpIufb8lg,44322
|
11
|
+
pyerualjetwork/cpu/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
|
12
|
+
pyerualjetwork/cpu/metrics.py,sha256=WhZ8iEqWehaygPRADUlhA5j_Qv3UwqV_eMxpyRVkeVs,6070
|
13
|
+
pyerualjetwork/cpu/model_ops.py,sha256=ZoX2YV1KXySWI_IK-w-xH078OfGpA6ANLbqxtWDl3eI,20476
|
14
|
+
pyerualjetwork/cpu/nn.py,sha256=Xx7BlUMetRVgr9V59JVu6mnmASWejHMO71X5RAP4mVQ,31390
|
15
|
+
pyerualjetwork/cpu/visualizations.py,sha256=rOQsc-W8b71z7ovXSoF49lx4fmpvlaHLsyj9ejWnhnI,28164
|
16
|
+
pyerualjetwork/cuda/__init__.py,sha256=NbqvAS4jlMdoFdXa5_hi5ukXQ5zAZR_5BQ4QAqtiKug,879
|
17
|
+
pyerualjetwork/cuda/activation_functions.py,sha256=M-B8Vwo1IIDEWBkrL7RRzRuORhS7hcz9YgJ_uFM-UKs,6753
|
18
|
+
pyerualjetwork/cuda/data_ops.py,sha256=SiNodFNmWyTPY_KnKuAi9biPRdpTAYY3XM01bRSUPCs,18510
|
19
|
+
pyerualjetwork/cuda/ene.py,sha256=aSCPr9VFdgK2cxxfwuP7z0jbJL9gkKNM0rgu8ihLarQ,44830
|
20
|
+
pyerualjetwork/cuda/loss_functions.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
|
21
|
+
pyerualjetwork/cuda/metrics.py,sha256=PjDBoRvr6va8vRvDIJJGBO4-I4uumrk3NCM1Vz4NJTo,5054
|
22
|
+
pyerualjetwork/cuda/model_ops.py,sha256=R_jJAzhlWrlBnRRYjTiPa2_zYYCG23zMFIZfrZDEqNw,21202
|
23
|
+
pyerualjetwork/cuda/nn.py,sha256=xkTdnuKnKg2nieV_m0rH8XwJrxSD_39xFIcpaYtx9k0,32516
|
24
|
+
pyerualjetwork/cuda/visualizations.py,sha256=9l5BhXqXoeopdhLvVGvjH1TKYZb9JdKOsSE2IYD02zs,28569
|
25
|
+
pyerualjetwork-5.30.dist-info/METADATA,sha256=Q3E3pQhsRrDKTJU35peIjK7gia91s4uN-K0LPwHdKoM,8133
|
26
|
+
pyerualjetwork-5.30.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
|
27
|
+
pyerualjetwork-5.30.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
|
28
|
+
pyerualjetwork-5.30.dist-info/RECORD,,
|
@@ -1,26 +0,0 @@
|
|
1
|
-
pyerualjetwork/__init__.py,sha256=OMPuF8AehsQx7gfqt_S76mnrYyodeCBdRAar-AJRUxk,2733
|
2
|
-
pyerualjetwork/activation_functions_cpu.py,sha256=axsVRSjw0GuRB709aBwyaNDgAi2vJBIqmJjTmcsCBBY,5743
|
3
|
-
pyerualjetwork/activation_functions_cuda.py,sha256=mNlecgmVX9G0_2yQ2_c6XQoMfvcdWIt9b1RUTdoLNBg,5809
|
4
|
-
pyerualjetwork/data_operations_cpu.py,sha256=HemqiYfSdlQKTTYNzpCh_9lTtS3AimMI4DvqJBAGjGw,16186
|
5
|
-
pyerualjetwork/data_operations_cuda.py,sha256=5zgyJGPjQuHyx6IHNkRwMguYhm-GcI6Hal49WNvw-bM,18536
|
6
|
-
pyerualjetwork/ene_cpu.py,sha256=35xz-KSmCigCg4lU7TD20EZbfuAN5PS21NcSywMTKhs,44350
|
7
|
-
pyerualjetwork/ene_cuda.py,sha256=9RyXC4JkRfDfhQUDkphFaKD89MiTp3QIia1brZTjsNA,44860
|
8
|
-
pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
|
9
|
-
pyerualjetwork/help.py,sha256=FcX8mxo1_mvoqONVXY0Kn7S09CDkhi0jwNmn8g9mYZc,804
|
10
|
-
pyerualjetwork/issue_solver.py,sha256=iY6hSsBxYI5l82RwnXQp2DrRUJyksk_7U9GUSnt2YfU,3117
|
11
|
-
pyerualjetwork/loss_functions_cpu.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
|
12
|
-
pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
|
13
|
-
pyerualjetwork/memory_operations.py,sha256=g24d-cDuUFc0fOEtk3AJe-z_EBctYV5S4cY1rQ6VGiE,14279
|
14
|
-
pyerualjetwork/metrics_cpu.py,sha256=vbfMwS0ay2heMSa0GNo-ydLjQ8cfexbLwaREp4FKAtY,6081
|
15
|
-
pyerualjetwork/metrics_cuda.py,sha256=PWyJyexeqlPKb09LAcF55JvhZVeXLCu3P_siYq5m2gg,5065
|
16
|
-
pyerualjetwork/model_operations_cpu.py,sha256=Y0uPkLVbdodP7lC-fOPdja3RWi2J9z2rwWIS2pxzotU,20523
|
17
|
-
pyerualjetwork/model_operations_cuda.py,sha256=B6vNYmqvrEJ3ZMGE1RWeJYn3V-JCsXhCHvS-aX4bWuU,21254
|
18
|
-
pyerualjetwork/neu_cpu.py,sha256=Mi-KcFVeoemK9I32H5Ov2oDPSwZG98dpQM3xaMuDsKE,31436
|
19
|
-
pyerualjetwork/neu_cuda.py,sha256=WBNZwwTEF7r6xIGti-8SFmTTTod_z7uP7NDgRhHgdHg,32573
|
20
|
-
pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
|
21
|
-
pyerualjetwork/visualizations_cpu.py,sha256=StyD1Hl1Gt55EMqR6tO3yVJZdPyGkOgCnQ75Zn8K6J8,28252
|
22
|
-
pyerualjetwork/visualizations_cuda.py,sha256=7lYrkOdrjwQGB3T4k_vI8UDxsm_TRjzaSSg9GhlNczs,28667
|
23
|
-
pyerualjetwork-5.27.dist-info/METADATA,sha256=eNL98od3NdBtaPKp2mQm1zir5FMfZJEtJE14kCVMbfM,8133
|
24
|
-
pyerualjetwork-5.27.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
|
25
|
-
pyerualjetwork-5.27.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
|
26
|
-
pyerualjetwork-5.27.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|