pyerualjetwork 5.32__py3-none-any.whl → 5.33__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -42,7 +42,7 @@ PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
 - Contact: tchasancan@gmail.com
 """
 
-__version__ = "5.32"
+__version__ = "5.33"
 __update__ = """* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES
 * PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main
 * PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf

pyerualjetwork/cpu/ene.py

@@ -138,7 +138,7 @@ def evolver(weights,
             weight_mutate_threshold=16,
             weight_mutate_prob=1,
             is_mlp=False,
-            save_best_genome=False,
+            save_best_genome=True,
             dtype=np.float32):
    """
    Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
@@ -157,7 +157,7 @@ def evolver(weights,
       what_gen (int): The current generation number, used for informational purposes or logging.
       
       fitness (numpy.ndarray): A 1D array containing the fitness values of each genome. 
-         The array is used to rank the genomes based on their performance. PLANEAT maximizes or minimizes this fitness based on the `target_fitness` parameter.
+         The array is used to rank the genomes based on their performance. ENE maximizes or minimizes this fitness based on the `target_fitness` parameter.
       
       weight_evolve (bool, optional): Are weights to be evolves or just activation combinations Default: True. Note: Regardless of whether this parameter is True or False, you must give the evolver function a list of weights equal to the number of activation potentiations. You can create completely random weights if you want. If this parameter is False, the weights entering the evolver function and the resulting weights will be exactly the same.
       
@@ -227,7 +227,7 @@ def evolver(weights,
 
       is_mlp (bool, optional): Evolve PLAN model or MLP model ? Default: False (PLAN)
       
-      save_best_genome (bool, optional): Save the best genome of the previous generation to the next generation. Default: False
+      save_best_genome (bool, optional): Save the best genome of the previous generation to the next generation. (index of best individual: 0) Default: True
 
       dtype (numpy.dtype, optional): Data type for the arrays. Default: np.float32. 
          Example: np.float64 or np.float16 [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not recommended!].
@@ -314,7 +314,7 @@ def evolver(weights,
    else:
       raise ValueError("genome population size must be even number. for example: not 99, make 100 or 98.")
 
-   if weight_evolve is False: origin_weights = np.copy(weights)
+   if weight_evolve is False: origin_weights = copy.deepcopy(weights)
 
    if is_mlp:
       activation_mutate_add_prob = 0
@@ -336,11 +336,11 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = np.copy(good_weights[-1]) if is_mlp is False else copy.deepcopy(good_weights[-1])
+   best_weight = copy.deepcopy(good_weights[-1])
 
    good_activations = list(activations[slice_center:])
    bad_activations = list(activations[:slice_center])
-   best_activations = good_activations[-1].copy() if isinstance(good_activations[-1], list) else good_activations[-1]
+   best_activations = copy.deepcopy(good_activations[-1]) if isinstance(good_activations[-1], list) else good_activations[-1]
 
    
 ### ENE IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
@@ -353,23 +353,23 @@ def evolver(weights,
    best_fitness = normalized_fitness[-1]
    epsilon = np.finfo(float).eps
    
-   child_W = np.copy(bad_weights)
-   child_act = bad_activations.copy()
+   child_W = copy.deepcopy(bad_weights)
+   child_act = copy.deepcopy(bad_activations)
 
-   mutated_W = np.copy(bad_weights)
-   mutated_act = bad_activations.copy()
+   mutated_W = copy.deepcopy(bad_weights)
+   mutated_act = copy.deepcopy(bad_activations)
 
 
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
-         first_parent_W = np.copy(best_weight)
-         first_parent_act = best_activations
+         first_parent_W = copy.deepcopy(best_weight)
+         first_parent_act = copy.deepcopy(best_activations)
          first_parent_fitness = best_fitness
 
       elif policy == 'explorer':
-         first_parent_W = good_weights[i]
-         first_parent_act = good_activations[i]
+         first_parent_W = copy.deepcopy(good_weights[i])
+         first_parent_act = copy.deepcopy(good_activations[i])
          first_parent_fitness = normalized_fitness[len(good_weights) + i]
 
       else: raise ValueError("policy parameter must be: 'aggressive' or 'explorer'")
@@ -475,8 +475,8 @@ def evolver(weights,
    activations = child_act + mutated_act
 
    if save_best_genome:
-      weights[0] = best_weight
-      activations[0] = best_activations
+      weights[0] = copy.deepcopy(best_weight)
+      activations[0] = copy.deepcopy(best_activations)
    
    ### INFO PRINTING CONSOLE
    
@@ -501,7 +501,7 @@ def evolver(weights,
       print("  ACTIVATION SELECTION ADD PROB: ", str(activation_selection_add_prob))
       print("  ACTIVATION SELECTION CHANGE PROB: ", str(activation_selection_change_prob))
       print("  FITNESS BIAS: ", str(fitness_bias))
-      print("  SAVE BEST GENOME: ", str(save_best_genome) + '\n')
+      print("  SAVE BEST GENOME: ", str(save_best_genome) + " (index of best individual: 0)" + '\n')
 
 
       print("*** Performance ***")
@@ -664,18 +664,18 @@ def cross_over(first_parent_W,
    decision = dominant_parent_selection(bad_genomes_selection_prob)
 
    if decision == 'first_parent':
-      dominant_parent_W = np.copy(first_parent_W)
+      dominant_parent_W = copy.deepcopy(first_parent_W)
       dominant_parent_act = first_parent_act
 
-      undominant_parent_W = np.copy(second_parent_W)
+      undominant_parent_W = copy.deepcopy(second_parent_W)
       undominant_parent_act = second_parent_act
       succes = second_parent_fitness + epsilon
 
    elif decision == 'second_parent':
-      dominant_parent_W = np.copy(second_parent_W)
+      dominant_parent_W = copy.deepcopy(second_parent_W)
       dominant_parent_act = second_parent_act
 
-      undominant_parent_W = np.copy(first_parent_W)
+      undominant_parent_W = copy.deepcopy(first_parent_W)
       undominant_parent_act = first_parent_act
       succes = first_parent_fitness + epsilon
 
@@ -713,7 +713,7 @@ def cross_over(first_parent_W,
    if isinstance(dominant_parent_act, str): dominant_parent_act = [dominant_parent_act]
    if isinstance(undominant_parent_act, str): undominant_parent_act = [undominant_parent_act]
 
-   child_act = list(np.copy(dominant_parent_act))
+   child_act = list(copy.deepcopy(dominant_parent_act))
 
    activation_selection_add_prob = 1 - activation_selection_add_prob # if prob 0.8 (%80) then 1 - 0.8. Because 0-1 random number probably greater than 0.2
    potential_activation_selection_add = random.uniform(0, 1)

pyerualjetwork/cpu/nn.py

@@ -295,15 +295,14 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
                 
                 weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), neurons=neurons_copy, activation_functions=activation_functions, population_size=pop_size, dtype=dtype)
  
-                # 0 indexed individual will keep PLAN's learned informations and in later generations it will share other individuals.
-                for l in range(1, len(weight_pop[0])):
-                    original_shape = weight_pop[0][l].shape
+                # 0 indexed individual will keep PLAN's learned informations and in later generations it will share with other individuals.
+                for layer in range(1, len(mlp_W)):
+                    row_shape, col_shape = mlp_W[layer].shape
 
-                    identity_matrix = np.eye(original_shape[0], original_shape[1], dtype=weight_pop[0][l].dtype)
-                    weight_pop[0][l] = identity_matrix
-                    
-                for l in range(len(weight_pop)):
-                    weight_pop[l][0] = np.copy(best_weight)
+                    identity_matrix = np.eye(row_shape, col_shape)
+                    mlp_W[layer] = identity_matrix
+
+                mlp_W[0] = plan_W
 
                 best_weight = np.array(weight_pop[0], dtype=object)
                 final_activations = act_pop[0]

pyerualjetwork/cuda/ene.py

@@ -138,7 +138,7 @@ def evolver(weights,
             weight_mutate_threshold=16,
             weight_mutate_prob=1,
             is_mlp=False,
-            save_best_genome=False,
+            save_best_genome=True,
             dtype=cp.float32):
    """
    Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
@@ -157,7 +157,7 @@ def evolver(weights,
       what_gen (int): The current generation number, used for informational purposes or logging.
       
       fitness (cupy.ndarray): A 1D array containing the fitness values of each genome. 
-         The array is used to rank the genomes based on their performance. PLANEAT maximizes or minimizes this fitness based on the `target_fitness` parameter.
+         The array is used to rank the genomes based on their performance. ENE maximizes or minimizes this fitness based on the `target_fitness` parameter.
       
       weight_evolve (bool, optional): Are weights to be evolves or just activation combinations Default: True. Note: Regardless of whether this parameter is True or False, you must give the evolver function a list of weights equal to the number of activation potentiations. You can create completely random weights if you want. If this parameter is False, the weights entering the evolver function and the resulting weights will be exactly the same.
 
@@ -227,7 +227,7 @@ def evolver(weights,
 
       is_mlp (bool, optional): Evolve PLAN model or MLP model ? Default: False (PLAN)
 
-      save_best_genome (bool, optional): Save the best genome of the previous generation to the next generation. Default: False
+      save_best_genome (bool, optional): Save the best genome of the previous generation to the next generation. (index of best individual: 0) Default: True
 
       dtype (cupy.dtype): Data type for the arrays. Default: cp.float32. 
          Example: cp.float64 or cp.float16 [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not recommended!].
@@ -313,7 +313,7 @@ def evolver(weights,
    else:
       raise ValueError("genome population size must be even number. for example: not 99, make 100 or 98.")
 
-   if weight_evolve is False: origin_weights = cp.copy(weights) if is_mlp else copy.deepcopy(weights)
+   if weight_evolve is False: origin_weights = copy.deepcopy(weights)
 
    if is_mlp:
       activation_mutate_add_prob = 0
@@ -345,14 +345,14 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = cp.copy(good_weights[-1])
+   best_weight = copy.deepcopy(good_weights[-1])
 
    good_activations = list(activations[slice_center:])
    bad_activations = list(activations[:slice_center])
-   best_activations = good_activations[-1].copy() if isinstance(good_activations[-1], list) else good_activations[-1]
+   best_activations = copy.deepcopy(good_activations[-1]) if isinstance(good_activations[-1], list) else good_activations[-1]
 
 
-### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
+### ENE IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
    
    bar_format = loading_bars()[0]
    
@@ -362,23 +362,23 @@ def evolver(weights,
    best_fitness = normalized_fitness[-1]
    epsilon = cp.finfo(float).eps
 
-   child_W = cp.copy(bad_weights)
-   child_act = bad_activations.copy()
+   child_W = copy.deepcopy(bad_weights)
+   child_act = copy.deepcopy(bad_activations)
 
-   mutated_W = cp.copy(bad_weights)
-   mutated_act = bad_activations.copy()
+   mutated_W = copy.deepcopy(bad_weights)
+   mutated_act = copy.deepcopy(bad_activations)
 
 
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
-         first_parent_W = best_weight
-         first_parent_act = best_activations
+         first_parent_W = copy.deepcopy(best_weight)
+         first_parent_act = copy.deepcopy(best_activations)
          first_parent_fitness = best_fitness
 
       elif policy == 'explorer':
-         first_parent_W = good_weights[i]
-         first_parent_act = good_activations[i]
+         first_parent_W = copy.deepcopy(good_weights[i])
+         first_parent_act = copy.deepcopy(good_activations[i])
          first_parent_fitness = normalized_fitness[len(good_weights) + i]
 
       else: raise ValueError("policy parameter must be: 'aggressive' or 'explorer'")
@@ -493,8 +493,8 @@ def evolver(weights,
    activations = child_act + mutated_act
 
    if save_best_genome:
-      weights[0] = best_weight
-      activations[0] = best_activations
+      weights[0] = copy.deepcopy(best_weight)
+      activations[0] = copy.deepcopy(best_activations)
 
    ### INFO PRINTING CONSOLE
    
@@ -519,7 +519,7 @@ def evolver(weights,
       print("  ACTIVATION SELECTION ADD PROB: ", str(activation_selection_add_prob))
       print("  ACTIVATION SELECTION CHANGE PROB: ", str(activation_selection_change_prob))
       print("  FITNESS BIAS: ", str(fitness_bias))
-      print("  SAVE BEST GENOME: ", str(save_best_genome) + '\n')
+      print("  SAVE BEST GENOME: ", str(save_best_genome) + " (index of best individual: 0)" + '\n')
 
       print("*** Performance ***")
       print("  MAX FITNESS: ", str(cp.round(max(fitness), 2)))
@@ -682,18 +682,18 @@ def cross_over(first_parent_W,
    decision = dominant_parent_selection(bad_genomes_selection_prob)
 
    if decision == 'first_parent':
-      dominant_parent_W = cp.copy(first_parent_W)
+      dominant_parent_W = copy.deepcopy(first_parent_W)
       dominant_parent_act = first_parent_act
 
-      undominant_parent_W = cp.copy(second_parent_W)
+      undominant_parent_W = copy.deepcopy(second_parent_W)
       undominant_parent_act = second_parent_act
       succes = second_parent_fitness + epsilon
 
    elif decision == 'second_parent':
-      dominant_parent_W = cp.copy(second_parent_W)
+      dominant_parent_W = copy.deepcopy(second_parent_W)
       dominant_parent_act = second_parent_act
 
-      undominant_parent_W = cp.copy(first_parent_W)
+      undominant_parent_W = copy.deepcopy(first_parent_W)
       undominant_parent_act = first_parent_act
       succes = first_parent_fitness + epsilon
 

{pyerualjetwork-5.32.dist-info → pyerualjetwork-5.33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.32
+Version: 5.33
 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.
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-5.32.dist-info → pyerualjetwork-5.33.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=X-alwoq6f9sVQjlVKzJMev51yAFgX4qoqSKrMGEd2b8,2704
+pyerualjetwork/__init__.py,sha256=a5zhtKQrVwHbhqgnBuAbKkLi4hC27iGD1Cf1jegr_eU,2704
 pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
 pyerualjetwork/help.py,sha256=Nyi0gHAN9ZnO4wgQLeENt0n7tSCZ3hJmjaJ853eGjCE,831
 pyerualjetwork/issue_solver.py,sha256=3pZTGotS29sy3pIuGQoJFUePibtSzS-tNoU80T_Usgk,3131
@@ -7,22 +7,22 @@ pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
 pyerualjetwork/cpu/__init__.py,sha256=0yAYner_-v7SmT3P7JV2itU8xJUQdQpb40dhAMQiZkc,829
 pyerualjetwork/cpu/activation_functions.py,sha256=zZSoOQ452Ykp_RsHVxklxesJmmFgufyIB4F3WQjudEQ,6689
 pyerualjetwork/cpu/data_ops.py,sha256=5biKr7pqLbJOayHYgGdQV1K5GqKbcOvrbbuAyByuDC8,16154
-pyerualjetwork/cpu/ene.py,sha256=ZLCaCxkpAmFLdxDS2OH-S8fT4jKq4HNVCHgpIufb8lg,44322
+pyerualjetwork/cpu/ene.py,sha256=1k2_qQydHyrp-3RlvsUu7cFdPa0pN3OcXI6jwIHiWg0,44484
 pyerualjetwork/cpu/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
 pyerualjetwork/cpu/metrics.py,sha256=WhZ8iEqWehaygPRADUlhA5j_Qv3UwqV_eMxpyRVkeVs,6070
 pyerualjetwork/cpu/model_ops.py,sha256=sWsP_7Gfa8_DJ2X7AUrOkeXnz2Eej6573grQQ3CooXM,20295
-pyerualjetwork/cpu/nn.py,sha256=B8V32y0j4a85JBz11Ke_hE8hUp8kv0gQ6LDtaCiASzk,32010
+pyerualjetwork/cpu/nn.py,sha256=TYLXmVLbbfFCDFA_cH9TSMxgjauDi6d7xfrPzOx6Xwg,31867
 pyerualjetwork/cpu/visualizations.py,sha256=rOQsc-W8b71z7ovXSoF49lx4fmpvlaHLsyj9ejWnhnI,28164
 pyerualjetwork/cuda/__init__.py,sha256=NbqvAS4jlMdoFdXa5_hi5ukXQ5zAZR_5BQ4QAqtiKug,879
 pyerualjetwork/cuda/activation_functions.py,sha256=FmoSAxDr9SGO4nkE6ZflXK4pmvZ0sL3Epe1Lz-3GOVI,6766
 pyerualjetwork/cuda/data_ops.py,sha256=SiNodFNmWyTPY_KnKuAi9biPRdpTAYY3XM01bRSUPCs,18510
-pyerualjetwork/cuda/ene.py,sha256=aSCPr9VFdgK2cxxfwuP7z0jbJL9gkKNM0rgu8ihLarQ,44830
+pyerualjetwork/cuda/ene.py,sha256=veJRW1KoBFoDEhDJWYr-Y35kQC-Qh6UwURtXeM16S0M,45009
 pyerualjetwork/cuda/loss_functions.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
 pyerualjetwork/cuda/metrics.py,sha256=PjDBoRvr6va8vRvDIJJGBO4-I4uumrk3NCM1Vz4NJTo,5054
 pyerualjetwork/cuda/model_ops.py,sha256=iQPuxmthKxP2GTFLHJppxoU64C6mEpkDW-DsfwFGiuY,21020
 pyerualjetwork/cuda/nn.py,sha256=7rbaIEcmssaFgcionWVRmKijlgFyftVjf-MMNaLO_28,33140
 pyerualjetwork/cuda/visualizations.py,sha256=9l5BhXqXoeopdhLvVGvjH1TKYZb9JdKOsSE2IYD02zs,28569
-pyerualjetwork-5.32.dist-info/METADATA,sha256=1wsSwMOifBtpBpAZE3UnFKdK8P4Bq3DUX8N_sdi-Pe4,8020
-pyerualjetwork-5.32.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-5.32.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-5.32.dist-info/RECORD,,
+pyerualjetwork-5.33.dist-info/METADATA,sha256=QHnz5cJtj77mPGeUo5ZQcvD1BpFJj5kZPkiCGdZxXv0,8020
+pyerualjetwork-5.33.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-5.33.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-5.33.dist-info/RECORD,,