pyerualjetwork 5.47__py3-none-any.whl → 5.48__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 +1 -1
- pyerualjetwork/cpu/data_ops.py +5 -5
- pyerualjetwork/cuda/data_ops.py +7 -7
- pyerualjetwork/nn.py +2 -2
- {pyerualjetwork-5.47.dist-info → pyerualjetwork-5.48.dist-info}/METADATA +1 -1
- {pyerualjetwork-5.47.dist-info → pyerualjetwork-5.48.dist-info}/RECORD +8 -8
- {pyerualjetwork-5.47.dist-info → pyerualjetwork-5.48.dist-info}/WHEEL +0 -0
- {pyerualjetwork-5.47.dist-info → pyerualjetwork-5.48.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.
|
45
|
+
__version__ = "5.48"
|
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/cpu/data_ops.py
CHANGED
@@ -436,12 +436,12 @@ def find_closest_factors(a):
|
|
436
436
|
return i, j
|
437
437
|
|
438
438
|
|
439
|
-
def batcher(
|
439
|
+
def batcher(x, y, batch_size=1):
|
440
440
|
|
441
441
|
if batch_size == 1:
|
442
|
-
return
|
442
|
+
return x, y
|
443
443
|
|
444
|
-
y_labels = np.argmax(
|
444
|
+
y_labels = np.argmax(y, axis=1)
|
445
445
|
|
446
446
|
sampled_x, sampled_y = [], []
|
447
447
|
|
@@ -453,7 +453,7 @@ def batcher(x_test, y_test, batch_size=1):
|
|
453
453
|
|
454
454
|
sampled_indices = np.random.choice(class_indices, num_samples, replace=False)
|
455
455
|
|
456
|
-
sampled_x.append(
|
457
|
-
sampled_y.append(
|
456
|
+
sampled_x.append(x[sampled_indices])
|
457
|
+
sampled_y.append(y[sampled_indices])
|
458
458
|
|
459
459
|
return np.concatenate(sampled_x), np.concatenate(sampled_y)
|
pyerualjetwork/cuda/data_ops.py
CHANGED
@@ -484,20 +484,20 @@ def find_closest_factors(a):
|
|
484
484
|
j = a // i
|
485
485
|
return i, j
|
486
486
|
|
487
|
-
def batcher(
|
487
|
+
def batcher(x, y, batch_size=1):
|
488
488
|
|
489
489
|
if batch_size == 1:
|
490
|
-
return
|
490
|
+
return x, y
|
491
491
|
|
492
|
-
y_labels = cp.argmax(
|
492
|
+
y_labels = cp.argmax(y, axis=1)
|
493
493
|
|
494
494
|
unique_labels = cp.unique(y_labels)
|
495
495
|
total_samples = sum(
|
496
496
|
int(cp.sum(y_labels == class_label) * batch_size) for class_label in unique_labels
|
497
497
|
)
|
498
498
|
|
499
|
-
sampled_x = cp.empty((total_samples,
|
500
|
-
sampled_y = cp.empty((total_samples,
|
499
|
+
sampled_x = cp.empty((total_samples, x.shape[1]), dtype=x.dtype)
|
500
|
+
sampled_y = cp.empty((total_samples, y.shape[1]), dtype=y.dtype)
|
501
501
|
|
502
502
|
offset = 0
|
503
503
|
for class_label in unique_labels:
|
@@ -507,8 +507,8 @@ def batcher(x_test, y_test, batch_size=1):
|
|
507
507
|
|
508
508
|
sampled_indices = cp.random.choice(class_indices, num_samples, replace=False)
|
509
509
|
|
510
|
-
sampled_x[offset:offset + num_samples] =
|
511
|
-
sampled_y[offset:offset + num_samples] =
|
510
|
+
sampled_x[offset:offset + num_samples] = x[sampled_indices]
|
511
|
+
sampled_y[offset:offset + num_samples] = y[sampled_indices]
|
512
512
|
|
513
513
|
offset += num_samples
|
514
514
|
|
pyerualjetwork/nn.py
CHANGED
@@ -351,10 +351,10 @@ def learn(x_train, y_train, optimizer, template_model, gen, pop_size, fit_start=
|
|
351
351
|
progress.last_print_n = 0
|
352
352
|
progress.update(0)
|
353
353
|
|
354
|
-
x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
|
355
|
-
|
356
354
|
for j in range(pop_size):
|
357
355
|
|
356
|
+
x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
|
357
|
+
|
358
358
|
if fit_start is True and i == 0:
|
359
359
|
if start_this_act is not None and j == 0:
|
360
360
|
pass
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: pyerualjetwork
|
3
|
-
Version: 5.
|
3
|
+
Version: 5.48
|
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
|
@@ -1,27 +1,27 @@
|
|
1
|
-
pyerualjetwork/__init__.py,sha256=
|
1
|
+
pyerualjetwork/__init__.py,sha256=S6a9ziYG2ZtpvF9O67Tdy4W0uAQSi3wb1NDGmnrXFFc,3020
|
2
2
|
pyerualjetwork/ene.py,sha256=8g2XEPRm3NLqSaN7xihIj1xXdIjSrl8Q69zqWTIXPI4,42142
|
3
3
|
pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
|
4
4
|
pyerualjetwork/help.py,sha256=sn9jBzXkQsTZvdgsUXUpSs_BbYYIgY3whofg6dj8peI,848
|
5
5
|
pyerualjetwork/issue_solver.py,sha256=uay_9XK6xWnLmK2P_BeyDQlyNXzg_zYffnXYd228wZk,4102
|
6
6
|
pyerualjetwork/memory_ops.py,sha256=TUFh9SYWCKL6N-vNdWId_EwU313TuZomQCHOrltrD-4,14280
|
7
7
|
pyerualjetwork/model_ops.py,sha256=39eUKrj0VKYiEYWKcq1U8O0TV_QMrxkuy8IhCHQsEcw,25101
|
8
|
-
pyerualjetwork/nn.py,sha256=
|
8
|
+
pyerualjetwork/nn.py,sha256=t1Jf99F6PqfEfCH6erPcwN6q-tF3DPYgHUlQ7OMtnv8,36656
|
9
9
|
pyerualjetwork/old_cpu_model_ops.py,sha256=1KNgjUeYCO_TsA5RtbNiuIiBJzq8-rL2dE6jxKqCBU0,21481
|
10
10
|
pyerualjetwork/old_cuda_model_ops.py,sha256=KAscAd8e_I8Vqdd9BJaHd6-IG6fhxFglAFxys0sqmEo,23079
|
11
11
|
pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
|
12
12
|
pyerualjetwork/cpu/__init__.py,sha256=9apRbPqvGKLJwyI3Md6R5a478YbZ7kIq0dRRa_lqgrY,789
|
13
13
|
pyerualjetwork/cpu/activation_functions.py,sha256=zZSoOQ452Ykp_RsHVxklxesJmmFgufyIB4F3WQjudEQ,6689
|
14
|
-
pyerualjetwork/cpu/data_ops.py,sha256=
|
14
|
+
pyerualjetwork/cpu/data_ops.py,sha256=9fCUrBmAc2WJQ3WkWEkDNSJyPdkkKsYX4rwSEy2TSvc,16108
|
15
15
|
pyerualjetwork/cpu/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
|
16
16
|
pyerualjetwork/cpu/metrics.py,sha256=NF8FARAqtuGlf4omVkQT4pOQZy7uePqzuHZGX9Y_Pn4,6076
|
17
17
|
pyerualjetwork/cpu/visualizations.py,sha256=RcEZXX-U3BStOna1-C_a7z2VpXHuLAigeg1pD4u8I9I,26923
|
18
18
|
pyerualjetwork/cuda/__init__.py,sha256=Kja6OmNaJ0giOhRNYw9hgGkh5N4F1EUS2v94E_rmp2k,839
|
19
19
|
pyerualjetwork/cuda/activation_functions.py,sha256=Gj-qalU0GoAWoZzbFFHsD-R0c0KzHwOK1wwUQneBE44,6872
|
20
|
-
pyerualjetwork/cuda/data_ops.py,sha256=
|
20
|
+
pyerualjetwork/cuda/data_ops.py,sha256=BEXh4M7BWXaTpYlVS9D2i3CGgOmL5131vy7FZyuTQBA,18453
|
21
21
|
pyerualjetwork/cuda/loss_functions.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
|
22
22
|
pyerualjetwork/cuda/metrics.py,sha256=PjDBoRvr6va8vRvDIJJGBO4-I4uumrk3NCM1Vz4NJTo,5054
|
23
23
|
pyerualjetwork/cuda/visualizations.py,sha256=2mHE7iqqsN3K6xtCnemS4o_YWGS0bIV2IxF4cG6Ur9k,20090
|
24
|
-
pyerualjetwork-5.
|
25
|
-
pyerualjetwork-5.
|
26
|
-
pyerualjetwork-5.
|
27
|
-
pyerualjetwork-5.
|
24
|
+
pyerualjetwork-5.48.dist-info/METADATA,sha256=QB4KoTEWk9oYD5Ypj--mwmszeP1Xm6yk8S1fuldxJec,7988
|
25
|
+
pyerualjetwork-5.48.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
|
26
|
+
pyerualjetwork-5.48.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
|
27
|
+
pyerualjetwork-5.48.dist-info/RECORD,,
|
File without changes
|
File without changes
|