pyerualjetwork 5.26__py3-none-any.whl → 5.27__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 (9) hide show
  1. pyerualjetwork/__init__.py +1 -1
  2. pyerualjetwork/ene_cpu.py +0 -14
  3. pyerualjetwork/ene_cuda.py +0 -14
  4. pyerualjetwork/neu_cpu.py +1 -1
  5. pyerualjetwork/neu_cuda.py +1 -1
  6. {pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/METADATA +1 -1
  7. {pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/RECORD +9 -9
  8. {pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/WHEEL +0 -0
  9. {pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/top_level.txt +0 -0
pyerualjetwork/__init__.py CHANGED
@@ -42,7 +42,7 @@ PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
42
42
  - Contact: tchasancan@gmail.com
43
43
  """
44
44
 
45
- __version__ = "5.26"
45
+ __version__ = "5.27"
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
pyerualjetwork/ene_cpu.py CHANGED
@@ -97,13 +97,6 @@ def define_genomes(input_shape, output_shape, population_size, neurons=[], activ
97
97
  if l != hidden:
98
98
  population_activations[i][l] = activation_functions[l]
99
99
 
100
- # ACTIVATIONS APPLYING IN WEIGHTS SPECIFIC OUTPUT CONNECTIONS (MORE PLAN LIKE FEATURES(FOR NON-LINEARITY)):
101
-
102
- for j in range(population_weights[i][l].shape[0]):
103
-
104
- population_weights[i][l][j,:] = apply_activation(population_weights[i][l][j,:], population_activations[i])
105
- population_weights[i][l][j,:] = normalization(population_weights[i][l][j,:], dtype=dtype)
106
-
107
100
  return population_weights, population_activations
108
101
 
109
102
  else:
@@ -118,13 +111,6 @@ def define_genomes(input_shape, output_shape, population_size, neurons=[], activ
118
111
  population_weights[i] = np.random.uniform(-1, 1, (output_shape, input_shape)).astype(dtype)
119
112
  population_activations[i] = activations[int(random.uniform(0, len(activations)-1))]
120
113
 
121
- # ACTIVATIONS APPLYING IN WEIGHTS SPECIFIC OUTPUT CONNECTIONS (MORE PLAN LIKE FEATURES(FOR NON-LINEARITY)):
122
-
123
- for j in range(population_weights[i].shape[0]):
124
-
125
- population_weights[i][j,:] = apply_activation(population_weights[i][j,:], population_activations[i])
126
- population_weights[i][j,:] = normalization(population_weights[i][j,:], dtype=dtype)
127
-
128
114
  return np.array(population_weights, dtype=dtype), population_activations
129
115
 
130
116
 
pyerualjetwork/ene_cuda.py CHANGED
@@ -98,13 +98,6 @@ def define_genomes(input_shape, output_shape, population_size, neurons=[], activ
98
98
  if l != hidden:
99
99
  population_activations[i][l] = activation_functions[l]
100
100
 
101
- # ACTIVATIONS APPLYING IN WEIGHTS SPECIFIC OUTPUT CONNECTIONS (MORE PLAN LIKE FEATURES(FOR NON-LINEARITY)):
102
-
103
- for j in range(population_weights[i][l].shape[0]):
104
-
105
- population_weights[i][l][j,:] = apply_activation(population_weights[i][l][j,:], population_activations[i])
106
- population_weights[i][l][j,:] = normalization(population_weights[i][l][j,:], dtype=dtype)
107
-
108
101
  return population_weights, population_activations
109
102
 
110
103
  else:
@@ -119,13 +112,6 @@ def define_genomes(input_shape, output_shape, population_size, neurons=[], activ
119
112
  population_weights[i] = cp.random.uniform(-1, 1, (output_shape, input_shape)).astype(dtype, copy=False)
120
113
  population_activations[i] = activations[int(random.uniform(0, len(activations)-1))]
121
114
 
122
- # ACTIVATIONS APPLYING IN WEIGHTS SPECIFIC OUTPUT CONNECTIONS (MORE PLAN LIKE FEATURES(FOR NON-LINEARITY)):
123
-
124
- for j in range(population_weights[i].shape[0]):
125
-
126
- population_weights[i][j,:] = apply_activation(population_weights[i][j,:], population_activations[i])
127
- population_weights[i][j,:] = normalization(population_weights[i][j,:], dtype=dtype)
128
-
129
115
  return cp.array(population_weights, dtype=dtype), population_activations
130
116
 
131
117
  def evolver(weights,
pyerualjetwork/neu_cpu.py CHANGED
@@ -250,7 +250,7 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
250
250
  loss_list = []
251
251
  target_pop = []
252
252
 
253
- progress = initialize_loading_bar(total=activations_len, desc="", ncols=77, bar_format=bar_format_learner)
253
+ progress = initialize_loading_bar(total=pop_size, desc="", ncols=77, bar_format=bar_format_learner)
254
254
 
255
255
  if fit_start is False:
256
256
  weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), neurons=neurons, activation_functions=activations, population_size=pop_size, dtype=dtype)
pyerualjetwork/neu_cuda.py CHANGED
@@ -259,7 +259,7 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
259
259
  loss_list = []
260
260
  target_pop = []
261
261
 
262
- progress = initialize_loading_bar(total=activations_len, desc="", ncols=79, bar_format=bar_format_learner)
262
+ progress = initialize_loading_bar(total=pop_size, desc="", ncols=79, bar_format=bar_format_learner)
263
263
 
264
264
  if fit_start is False:
265
265
  weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), neurons=neurons, activation_functions=activations, population_size=pop_size, dtype=dtype)
{pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: pyerualjetwork
3
- Version: 5.26
3
+ Version: 5.27
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
{pyerualjetwork-5.26.dist-info → pyerualjetwork-5.27.dist-info}/RECORD RENAMED
@@ -1,10 +1,10 @@
1
- pyerualjetwork/__init__.py,sha256=DqL4tpLYw-zpIc6Sf-mc2wq1H2R5R3P0jf0J37h0-YE,2733
1
+ pyerualjetwork/__init__.py,sha256=OMPuF8AehsQx7gfqt_S76mnrYyodeCBdRAar-AJRUxk,2733
2
2
  pyerualjetwork/activation_functions_cpu.py,sha256=axsVRSjw0GuRB709aBwyaNDgAi2vJBIqmJjTmcsCBBY,5743
3
3
  pyerualjetwork/activation_functions_cuda.py,sha256=mNlecgmVX9G0_2yQ2_c6XQoMfvcdWIt9b1RUTdoLNBg,5809
4
4
  pyerualjetwork/data_operations_cpu.py,sha256=HemqiYfSdlQKTTYNzpCh_9lTtS3AimMI4DvqJBAGjGw,16186
5
5
  pyerualjetwork/data_operations_cuda.py,sha256=5zgyJGPjQuHyx6IHNkRwMguYhm-GcI6Hal49WNvw-bM,18536
6
- pyerualjetwork/ene_cpu.py,sha256=vM-eGAqkiw4U68VmNDMpC5UAmewc8S876VPoyUDcSl4,45163
7
- pyerualjetwork/ene_cuda.py,sha256=dWavZydKL9b5BAGL430SuWs1TenMelbFtltoEAXKkJY,45673
6
+ pyerualjetwork/ene_cpu.py,sha256=35xz-KSmCigCg4lU7TD20EZbfuAN5PS21NcSywMTKhs,44350
7
+ pyerualjetwork/ene_cuda.py,sha256=9RyXC4JkRfDfhQUDkphFaKD89MiTp3QIia1brZTjsNA,44860
8
8
  pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
9
9
  pyerualjetwork/help.py,sha256=FcX8mxo1_mvoqONVXY0Kn7S09CDkhi0jwNmn8g9mYZc,804
10
10
  pyerualjetwork/issue_solver.py,sha256=iY6hSsBxYI5l82RwnXQp2DrRUJyksk_7U9GUSnt2YfU,3117
@@ -15,12 +15,12 @@ pyerualjetwork/metrics_cpu.py,sha256=vbfMwS0ay2heMSa0GNo-ydLjQ8cfexbLwaREp4FKAtY
15
15
  pyerualjetwork/metrics_cuda.py,sha256=PWyJyexeqlPKb09LAcF55JvhZVeXLCu3P_siYq5m2gg,5065
16
16
  pyerualjetwork/model_operations_cpu.py,sha256=Y0uPkLVbdodP7lC-fOPdja3RWi2J9z2rwWIS2pxzotU,20523
17
17
  pyerualjetwork/model_operations_cuda.py,sha256=B6vNYmqvrEJ3ZMGE1RWeJYn3V-JCsXhCHvS-aX4bWuU,21254
18
- pyerualjetwork/neu_cpu.py,sha256=3s1YYjT0evctWi8TSzivfCgsNstQTIIfupKsbfw3NOo,31443
19
- pyerualjetwork/neu_cuda.py,sha256=fT8vx-dqG9HZt0iSQUH3ZzRxBPfkEtvISvBy4Y8vR_M,32580
18
+ pyerualjetwork/neu_cpu.py,sha256=Mi-KcFVeoemK9I32H5Ov2oDPSwZG98dpQM3xaMuDsKE,31436
19
+ pyerualjetwork/neu_cuda.py,sha256=WBNZwwTEF7r6xIGti-8SFmTTTod_z7uP7NDgRhHgdHg,32573
20
20
  pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
21
21
  pyerualjetwork/visualizations_cpu.py,sha256=StyD1Hl1Gt55EMqR6tO3yVJZdPyGkOgCnQ75Zn8K6J8,28252
22
22
  pyerualjetwork/visualizations_cuda.py,sha256=7lYrkOdrjwQGB3T4k_vI8UDxsm_TRjzaSSg9GhlNczs,28667
23
- pyerualjetwork-5.26.dist-info/METADATA,sha256=y3NZzX7Xbl0HpsLdgGp6cGtuRe_YB1GRBD6E68nqCCo,8133
24
- pyerualjetwork-5.26.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
25
- pyerualjetwork-5.26.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
26
- pyerualjetwork-5.26.dist-info/RECORD,,
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,,