pyerualjetwork 2.6.3__py3-none-any.whl → 2.6.4__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.
plan/plan.py CHANGED
@@ -272,8 +272,7 @@ def fit(
272
272
  elif calculating_est > 3600:
273
273
  print('Total training time(h): ', calculating_est/3600)
274
274
 
275
- layers.append('cat')
276
- trained_W.append(np.eye(len(class_count)))
275
+
277
276
 
278
277
 
279
278
  return trained_W
@@ -507,7 +506,7 @@ def evaluate(
507
506
  tuple: A tuple containing the predicted labels and the accuracy of the model.
508
507
  """
509
508
 
510
- layers = ['fex', 'cat']
509
+ layers = ['fex']
511
510
 
512
511
  try:
513
512
  Wc = [0] * len(W) # Wc = Weight copy
@@ -533,8 +532,7 @@ def evaluate(
533
532
 
534
533
  if Layer == 'fex':
535
534
  neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
536
- elif Layer == 'cat':
537
- neural_layer = np.dot(W[index], neural_layer)
535
+
538
536
 
539
537
  for i, w in enumerate(Wc):
540
538
  W[i] = np.copy(w)
@@ -656,8 +654,6 @@ def multiple_evaluate(
656
654
 
657
655
  if Layer == 'fex':
658
656
  neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
659
- elif Layer == 'cat':
660
- neural_layer = np.dot(W[index], neural_layer)
661
657
 
662
658
  output_layer += neural_layer
663
659
 
@@ -765,7 +761,7 @@ def save_model(model_name,
765
761
  # Operations to be performed by the function will be written here
766
762
  pass
767
763
 
768
- layers = ['fex', 'cat']
764
+ layers = ['fex']
769
765
 
770
766
  if weights_type != 'txt' and weights_type != 'npy' and weights_type != 'mat':
771
767
  print(Fore.RED + "ERROR110: Save Weight type (File Extension) Type must be 'txt' or 'npy' or 'mat' from: save_model" +
@@ -976,7 +972,7 @@ def predict_model_ssd(Input, model_name, model_path):
976
972
  non_scaled = True
977
973
 
978
974
 
979
- layers = ['fex', 'cat']
975
+ layers = ['fex']
980
976
 
981
977
  Wc = [0] * len(W)
982
978
  for i, w in enumerate(W):
@@ -1022,7 +1018,7 @@ def predict_model_ram(Input, scaler_params, W, activation_potentiation=None):
1022
1018
 
1023
1019
  Input = standard_scaler(None, Input, scaler_params)
1024
1020
 
1025
- layers = ['fex', 'cat']
1021
+ layers = ['fex']
1026
1022
 
1027
1023
  Wc = [0] * len(W)
1028
1024
  for i, w in enumerate(W):
@@ -1,7 +1,7 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: pyerualjetwork
3
- Version: 2.6.3
4
- Summary: New optional parameters added for fit function, x_val, y_val show_count, val_count, val. For more information please read user document
3
+ Version: 2.6.4
4
+ Summary: Code improvements
5
5
  Author: Hasan Can Beydili
6
6
  Author-email: tchasancan@gmail.com
7
7
  Keywords: model evaluation,classifcation,pruning learning artficial neural networks
@@ -0,0 +1,6 @@
1
+ plan/__init__.py,sha256=gmaz8lnQfl18MbOQwabBUPmShajK5S99jfyY-hQe8tc,502
2
+ plan/plan.py,sha256=XcEAeyweDvP4WRRNdL_hOue_fOeqf1_rXsJ75q4sEdk,55940
3
+ pyerualjetwork-2.6.4.dist-info/METADATA,sha256=9_sisdjKeZGNIwLdOa_OFXmcPXrEga9FgRUyIfO-e-w,239
4
+ pyerualjetwork-2.6.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
5
+ pyerualjetwork-2.6.4.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
6
+ pyerualjetwork-2.6.4.dist-info/RECORD,,
@@ -1,6 +0,0 @@
1
- plan/__init__.py,sha256=gmaz8lnQfl18MbOQwabBUPmShajK5S99jfyY-hQe8tc,502
2
- plan/plan.py,sha256=fUVW_bUadJjTPoXN3YQwU_1b-FSr64fCH3_WUAoDcn8,56253
3
- pyerualjetwork-2.6.3.dist-info/METADATA,sha256=uc5OY2rYco6MWnILvfmZ4rR9-9xheUTsR7MMOlg1J9Q,357
4
- pyerualjetwork-2.6.3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
5
- pyerualjetwork-2.6.3.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
6
- pyerualjetwork-2.6.3.dist-info/RECORD,,