23-06-30

seed 조정 추가

iris.py

@@ -2,16 +2,10 @@ import os
 
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
-import tensorflow as tf
-
-tf.random.set_seed(777)  # for reproducibility
-
-import numpy as np
-
-np.random.seed(777)
-
 import gc
 
+import numpy as np
+import tensorflow as tf
 from pso import Optimizer
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
@@ -52,7 +46,8 @@ pso_iris = Optimizer(
     c1=0.8, 
     w_min=0.7,
     w_max=1.0, 
-    negative_swarm=0.25
+    negative_swarm=0,
+    mutation_swarm=0,
     )
 
 best_score = pso_iris.fit(

mnist.py

@@ -3,17 +3,9 @@ import os
 
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
-import tensorflow as tf
-
-tf.random.set_seed(777)  # for reproducibility
-
-import numpy as np
-
-np.random.seed(777)
-
 import gc
-from datetime import date
 
+import tensorflow as tf
 from keras import backend as K
 from keras.datasets import mnist
 from keras.layers import Conv2D, Dense, Dropout, Flatten, MaxPooling2D
@@ -76,7 +68,7 @@ if __name__ == "__main__":
             w_min=0.6,
             w_max=0.9,
             negative_swarm=0.25,
-            momentun_swarm=0,
+            mutation_swarm=0,
             )
 
         best_score = pso_mnist.fit(

pso/optimizer.py

@@ -33,6 +33,8 @@ class Optimizer:
         w_max=1.5,
         negative_swarm: float = 0,
         mutation_swarm: float = 0,
+        np_seed: int = 777,
+        tf_seed: int = 777,
     ):
         """
         particle swarm optimization
@@ -48,6 +50,8 @@ class Optimizer:
             nefative_swarm (float): 최적해와 반대로 이동할 파티클 비율 - 0 ~ 1 사이의 값
             momentun_swarm (float): 관성을 추가로 사용할 파티클 비율 - 0 ~ 1 사이의 값
         """
+        np.random.seed(np_seed)
+        tf.random.set_seed(tf_seed)
         self.model = model  # 모델 구조
         self.loss = loss  # 손실함수
         self.n_particles = n_particles  # 파티클 개수
@@ -67,11 +71,14 @@ class Optimizer:
             m = keras.models.model_from_json(model.to_json())
             init_weights = m.get_weights()
             w_, sh_, len_ = self._encode(init_weights)
-            w_ = np.random.rand(len(w_)) * 5 - 2.5 
-            # w_ = np.random.uniform(-1.5, 1.5, len(w_))
+            w_ = np.random.uniform(-0.5, 0.5, len(w_))
             m.set_weights(self._decode(w_, sh_, len_))
             m.compile(loss=self.loss, optimizer="sgd", metrics=["accuracy"])
-            self.particles[i] = Particle(m, loss, negative=True if i < negative_swarm * self.n_particles else False, mutation=True if i > self.n_particles * (1 - self.mutation_swarm) else False)
+            self.particles[i] = Particle(
+                m, loss, 
+                negative=True if i < negative_swarm * self.n_particles else False, 
+                mutation=True if i > self.n_particles * (1 - self.mutation_swarm) else False
+                )
                 
         gc.collect()
         
@@ -427,7 +434,7 @@ class Optimizer:
             "empirical_balance": self.empirical_balance,
             "Dispersion": self.Dispersion,
             "negative_swarm": self.negative_swarm,
-            "momentun_swarm": self.momentun_swarm,
+            "mutation_swarm": self.mutation_swarm,
             "renewal": self.renewal,
         }
 

xor.py

@@ -1,19 +1,15 @@
 # %%
 import os
+
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
-import tensorflow as tf
-tf.random.set_seed(777)  # for reproducibility
-
 import numpy as np
-np.random.seed(777)
-
+import tensorflow as tf
 # from pso_tf import PSO
 from pso import Optimizer
-
 from tensorflow import keras
-from tensorflow.keras.models import Sequential
 from tensorflow.keras import layers
+from tensorflow.keras.models import Sequential
 
 print(tf.__version__)
 print(tf.config.list_physical_devices())
@@ -40,7 +36,7 @@ x_test, y_test = get_data()
 loss = ['mean_squared_error', 'mean_squared_logarithmic_error', 'binary_crossentropy', 'categorical_crossentropy', 'sparse_categorical_crossentropy', 'kullback_leibler_divergence', 'poisson', 'cosine_similarity', 'log_cosh', 'huber_loss', 'mean_absolute_error', 'mean_absolute_percentage_error']
 
 pso_xor = Optimizer(model,
-    loss=loss[0], n_particles=75, c0=0.35, c1=0.8, w_min=0.6, w_max=1.2, negative_swarm=0.25)
+    loss=loss[0], n_particles=75, c0=0.35, c1=0.8, w_min=0.6, w_max=1.2, negative_swarm=0.25, mutation_swarm=0.25)
 best_score = pso_xor.fit(
     x_test, y_test, epochs=200, save=True, save_path="./result/xor", renewal="acc", empirical_balance=False, Dispersion=False, check_point=25)