pyerualjetwork 4.5__py3-none-any.whl → 4.5.1__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.
Files changed (18) hide show
  1. pyerualjetwork/__init__.py +1 -1
  2. pyerualjetwork/data_operations.py +45 -40
  3. pyerualjetwork/data_operations_cuda.py +42 -45
  4. pyerualjetwork/fitness_functions.py +3 -8
  5. pyerualjetwork/memory_operations.py +9 -23
  6. pyerualjetwork/model_operations.py +43 -55
  7. pyerualjetwork/model_operations_cuda.py +43 -53
  8. pyerualjetwork/plan.py +50 -72
  9. pyerualjetwork/plan_cuda.py +57 -85
  10. pyerualjetwork/planeat.py +1 -1
  11. pyerualjetwork/planeat_cuda.py +2 -2
  12. pyerualjetwork/visualizations.py +17 -17
  13. pyerualjetwork/visualizations_cuda.py +17 -17
  14. {pyerualjetwork-4.5.dist-info → pyerualjetwork-4.5.1.dist-info}/METADATA +1 -1
  15. pyerualjetwork-4.5.1.dist-info/RECORD +25 -0
  16. pyerualjetwork-4.5.dist-info/RECORD +0 -25
  17. {pyerualjetwork-4.5.dist-info → pyerualjetwork-4.5.1.dist-info}/WHEEL +0 -0
  18. {pyerualjetwork-4.5.dist-info → pyerualjetwork-4.5.1.dist-info}/top_level.txt +0 -0
pyerualjetwork/planeat_cuda.py CHANGED
@@ -37,7 +37,7 @@ def define_genomes(input_shape, output_shape, population_size, dtype=cp.float32)
37
37
 
38
38
  population_size (int): The number of genomes (individuals) in the population.
39
39
 
40
- dtype (cupy.dtype): Data type for the arrays. np.float32 by default. Example: cp.float64 or cp.float16. [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not reccomended!] (optional)
40
+ dtype (cupy.dtype): Data type for the arrays. np.float32 by default. Example: cp.float64 or cp.float16.
41
41
 
42
42
  Returns:
43
43
  tuple: A tuple containing:
@@ -97,7 +97,7 @@ def evolver(weights,
97
97
  weight_mutate_prob=1,
98
98
  dtype=cp.float32):
99
99
  """
100
- Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
100
+ Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
101
101
  The function modifies the population's weights and activation functions based on a specified policy, mutation probabilities, and strategy.
102
102
 
103
103
  'selection' args effects cross-over.
pyerualjetwork/visualizations.py CHANGED
@@ -9,27 +9,27 @@ def draw_neural_web(W, ax, G, return_objs=False):
9
9
  """
10
10
  Visualizes a neural web by drawing the neural network structure.
11
11
 
12
- Parameters:
13
- W : numpy.ndarray
14
- A 2D array representing the connection weights of the neural network.
15
- ax : matplotlib.axes.Axes
16
- The matplotlib axes where the graph will be drawn.
17
- G : networkx.Graph
18
- The NetworkX graph representing the neural network structure.
19
- return_objs : bool, optional
20
- If True, returns the drawn objects (nodes and edges). Default is False.
12
+ Args:
13
+ W : numpy.ndarray
14
+ A 2D array representing the connection weights of the neural network.
15
+ ax : matplotlib.axes.Axes
16
+ The matplotlib axes where the graph will be drawn.
17
+ G : networkx.Graph
18
+ The NetworkX graph representing the neural network structure.
19
+ return_objs : bool, optional
20
+ If True, returns the drawn objects (nodes and edges). Default is False.
21
21
 
22
22
  Returns:
23
- art1 : matplotlib.collections.PathCollection or None
24
- Returns the node collection if return_objs is True; otherwise, returns None.
25
- art2 : matplotlib.collections.LineCollection or None
26
- Returns the edge collection if return_objs is True; otherwise, returns None.
27
- art3 : matplotlib.collections.TextCollection or None
28
- Returns the label collection if return_objs is True; otherwise, returns None.
23
+ art1 : matplotlib.collections.PathCollection or None
24
+ Returns the node collection if return_objs is True; otherwise, returns None.
25
+ art2 : matplotlib.collections.LineCollection or None
26
+ Returns the edge collection if return_objs is True; otherwise, returns None.
27
+ art3 : matplotlib.collections.TextCollection or None
28
+ Returns the label collection if return_objs is True; otherwise, returns None.
29
29
 
30
30
  Example:
31
- art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
32
- plt.show()
31
+ art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
32
+ plt.show()
33
33
  """
34
34
 
35
35
  for i in range(W.shape[0]):
pyerualjetwork/visualizations_cuda.py CHANGED
@@ -9,27 +9,27 @@ def draw_neural_web(W, ax, G, return_objs=False):
9
9
  """
10
10
  Visualizes a neural web by drawing the neural network structure.
11
11
 
12
- Parameters:
13
- W : numpy.ndarray
14
- A 2D array representing the connection weights of the neural network.
15
- ax : matplotlib.axes.Axes
16
- The matplotlib axes where the graph will be drawn.
17
- G : networkx.Graph
18
- The NetworkX graph representing the neural network structure.
19
- return_objs : bool, optional
20
- If True, returns the drawn objects (nodes and edges). Default is False.
12
+ Args:
13
+ W : numpy.ndarray
14
+ A 2D array representing the connection weights of the neural network.
15
+ ax : matplotlib.axes.Axes
16
+ The matplotlib axes where the graph will be drawn.
17
+ G : networkx.Graph
18
+ The NetworkX graph representing the neural network structure.
19
+ return_objs : bool, optional
20
+ If True, returns the drawn objects (nodes and edges). Default is False.
21
21
 
22
22
  Returns:
23
- art1 : matplotlib.collections.PathCollection or None
24
- Returns the node collection if return_objs is True; otherwise, returns None.
25
- art2 : matplotlib.collections.LineCollection or None
26
- Returns the edge collection if return_objs is True; otherwise, returns None.
27
- art3 : matplotlib.collections.TextCollection or None
28
- Returns the label collection if return_objs is True; otherwise, returns None.
23
+ art1 : matplotlib.collections.PathCollection or None
24
+ Returns the node collection if return_objs is True; otherwise, returns None.
25
+ art2 : matplotlib.collections.LineCollection or None
26
+ Returns the edge collection if return_objs is True; otherwise, returns None.
27
+ art3 : matplotlib.collections.TextCollection or None
28
+ Returns the label collection if return_objs is True; otherwise, returns None.
29
29
 
30
30
  Example:
31
- art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
32
- plt.show()
31
+ art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
32
+ plt.show()
33
33
  """
34
34
  W = W.get()
35
35
  for i in range(W.shape[0]):
{pyerualjetwork-4.5.dist-info → pyerualjetwork-4.5.1.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: pyerualjetwork
3
- Version: 4.5
3
+ Version: 4.5.1
4
4
  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
5
5
  Author: Hasan Can Beydili
6
6
  Author-email: tchasancan@gmail.com
pyerualjetwork-4.5.1.dist-info/RECORD ADDED
@@ -0,0 +1,25 @@
1
+ pyerualjetwork/__init__.py,sha256=Oe1PUj-kEsIW73oaiAxac3x_QQxSAFhOpUacNgzc6gs,1279
2
+ pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
3
+ pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
4
+ pyerualjetwork/data_operations.py,sha256=SOPcuCUedAVKLZ10q4uX8XVgtFAgQ2gz6efVHR6ctw0,15166
5
+ pyerualjetwork/data_operations_cuda.py,sha256=X0rUCxehqyVknjBToJ0zXCTGQwlAA7GEVAcqQ-YJYfQ,17267
6
+ pyerualjetwork/fitness_functions.py,sha256=urRdeMvUhNgWxD4ZGHCRdQlIf9cTWYMvF3_aVBojRqY,1235
7
+ pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
8
+ pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
9
+ pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
10
+ pyerualjetwork/memory_operations.py,sha256=0yCOHcgiNyF4ccMcRlL1Q9F_byG4nzjhmkbpXE_yU6E,13401
11
+ pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
12
+ pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
13
+ pyerualjetwork/model_operations.py,sha256=BLRL_5s_KSs8iCiLsEwWvhRcGiWCP_TD9lsjYWM7Zek,12746
14
+ pyerualjetwork/model_operations_cuda.py,sha256=b3Bkobbrhq28AmYZ0vGxf2Hf8V2LPvoiM0xaPAApqec,13254
15
+ pyerualjetwork/plan.py,sha256=UyIvPmvHCHwczlc9KHolE4y6CPEeBfhnRN5yznSbnoM,23028
16
+ pyerualjetwork/plan_cuda.py,sha256=iteqgv7x9Z2Pj4vGOZs6HXS3r0bNaF_smr7ZXaOdRnw,23990
17
+ pyerualjetwork/planeat.py,sha256=_dnGRVBzdRUgvVCnHZ721tdXYV9PSvCz-aUnj--5VpU,38697
18
+ pyerualjetwork/planeat_cuda.py,sha256=CXBF4vsTZ-fE-3W8Zc6Zxe_oKuyJS02FaHsOzSwzLV8,38731
19
+ pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
20
+ pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
21
+ pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
22
+ pyerualjetwork-4.5.1.dist-info/METADATA,sha256=xjGpEBnY_JunoNvXCbD1oJfdYL7Wvzj0Nt7oWj61gZg,7505
23
+ pyerualjetwork-4.5.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
24
+ pyerualjetwork-4.5.1.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
25
+ pyerualjetwork-4.5.1.dist-info/RECORD,,
pyerualjetwork-4.5.dist-info/RECORD DELETED
@@ -1,25 +0,0 @@
1
- pyerualjetwork/__init__.py,sha256=xOgL47nXk4gItE1UKQ_uEBevdRI2RUjN5RVuB-BRlHM,1277
2
- pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
3
- pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
4
- pyerualjetwork/data_operations.py,sha256=c2FWIdHJQw_h6QP_ir0yx22zP7a9CtRp249V8Ro9V-0,15357
5
- pyerualjetwork/data_operations_cuda.py,sha256=IqS0JoXGM0XiYfoFSAj9li1WWiBroNXIcN52JWhlNFk,18224
6
- pyerualjetwork/fitness_functions.py,sha256=GisM8mDJAivw8YailXXDAw2M-lW1MHwRnIlWUVe-UEg,1261
7
- pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
8
- pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
9
- pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
10
- pyerualjetwork/memory_operations.py,sha256=I7QiZ--xSyRkFF0wcckPwZV7K9emEvyx5aJ3DiRHZFI,13468
11
- pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
12
- pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
13
- pyerualjetwork/model_operations.py,sha256=MCSCNYiiICRVZITobtS3ZIWmH5Q9gjyELuH32sAdgg4,12649
14
- pyerualjetwork/model_operations_cuda.py,sha256=NT01BK5nrDYE7H1x3KnSI8gmx0QTGGB0mP_LqEb1uuU,13157
15
- pyerualjetwork/plan.py,sha256=XEptIEWfWbqXEy92Eil5q_uujEiIBWnjejAGD7Lh0-w,22975
16
- pyerualjetwork/plan_cuda.py,sha256=rFHZa8jsgfol0uUo1rfCKAGtb-B4ivfzqqlnynsfMzQ,23966
17
- pyerualjetwork/planeat.py,sha256=DVJGptIPYKyz4ePwqRnbbwgHwQzbxMoBci0Te8kfCzk,38802
18
- pyerualjetwork/planeat_cuda.py,sha256=-GxZY8aMPayuYhwhcsRVn4LWq604o36VxkEtdoBum98,38835
19
- pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
20
- pyerualjetwork/visualizations.py,sha256=1QSisYAaGnO5kug6qo1qOssTkQM-MgR7L8h4c3sczzU,28294
21
- pyerualjetwork/visualizations_cuda.py,sha256=PYRqj4QYUbuYMYcNwO8yaTPB-jK7E6kZHhTrAi0lwPU,28749
22
- pyerualjetwork-4.5.dist-info/METADATA,sha256=njuvH-FdU7-KudHvxUEJvBeyOvDWzyWi52ZIpRjR9K4,7503
23
- pyerualjetwork-4.5.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
24
- pyerualjetwork-4.5.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
25
- pyerualjetwork-4.5.dist-info/RECORD,,