finalisation du fonctionnement

code/fonctions_activations_classiques/sin.py

@@ -17,9 +17,9 @@ from Creation_donnee import *
 import numpy as np
 
 w=10
-n=20
+n=2000
 #création de la base de donnéé
-X,Y=creation_sin(-1.5,-1,n,w)
+X,Y=creation_sin(-2.5,-1,n,w)
 X2,Y2=creation_sin(1,1.5,n,w)
 X=np.concatenate([X,X2])
 Y=np.concatenate([Y,Y2])
@@ -34,13 +34,13 @@ model_sin=tf.keras.models.Sequential()
 
 model_sin.add(tf.keras.Input(shape=(1,)))
 
-# model_sin.add(tf.keras.layers.Dense(64, activation=sin))
-# model_sin.add(tf.keras.layers.Dense(64, activation=sin))
-# model_sin.add(tf.keras.layers.Dense(64, activation=sin))
-# model_sin.add(tf.keras.layers.Dense(64, activation=sin))
-# model_sin.add(tf.keras.layers.Dense(512, activation=sin))
-# model_sin.add(tf.keras.layers.Dense(64, activation=sin))
-model_sin.add(tf.keras.layers.Dense(8, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+model_sin.add(tf.keras.layers.Dense(64, activation=sin))
+# model_sin.add(tf.keras.layers.Dense(8, activation=sin))
 model_sin.add(tf.keras.layers.Dense(1))
 
 opti=tf.keras.optimizers.Adam()
@@ -50,7 +50,7 @@ model_sin.compile(opti, loss='mse', metrics=['accuracy'])
 
 model_sin.summary()
 
-model_sin.fit(X, Y, batch_size=16, epochs=1000, shuffle='True',validation_data=(Xv, Yv))
+model_sin.fit(X, Y, batch_size=16, epochs=150, shuffle='True',validation_data=(Xv, Yv))
 
 
 

code/fonctions_activations_classiques/snake.py

@@ -19,7 +19,7 @@ import numpy as np
 w=10
 n=20000
 #création de la base de donnéé
-X,Y=creation_sin(-1.5,-1,n,w)
+X,Y=creation_sin(-2.5,-1,n,w)
 X2,Y2=creation_sin(1,1.5,n,w)
 X=np.concatenate([X,X2])
 Y=np.concatenate([Y,Y2])
@@ -50,7 +50,7 @@ model_sin.compile(opti, loss='mse', metrics=['accuracy'])
 
 model_sin.summary()
 
-model_sin.fit(X, Y, batch_size=16, epochs=10, shuffle='True',validation_data=(Xv, Yv))
+model_sin.fit(X, Y, batch_size=16, epochs=100, shuffle='True',validation_data=(Xv, Yv))
 
 
 
@@ -64,8 +64,8 @@ Y_predis_validation_sin=model_sin.predict(Xv)
 plt.figure()
 plt.plot(X,Y,'x',label='donnée')
 plt.plot(Xv,Yv,label="validation")
-plt.plot(X,Y_predis_sin,'o',label='prediction sur les données avec sin ')
-plt.plot(Xv,Y_predis_validation_sin,label='prediction sur la validation avec sin')
+plt.plot(X,Y_predis_sin,'o',label='prediction sur les données avec snake')
+plt.plot(Xv,Y_predis_validation_sin,label='prediction sur la validation avec snake')
 plt.legend()
 plt.show()
 

code/fonctions_activations_classiques/swish.py

@@ -15,15 +15,15 @@ from Creation_donnee import *
 import numpy as np
 
 w=10
-n=20
+n=2000
 #création de la base de donnéé
-X,Y=creation_x2(-1.5,-1,n)
-X2,Y2=creation_x2(1,1.5,n)
+X,Y=creation_sin(-1.5,-1,n,w)
+X2,Y2=creation_sin(1,1.5,n,w)
 X=np.concatenate([X,X2])
 Y=np.concatenate([Y,Y2])
 
 n=10000
-Xv,Yv=creation_x2(-3,3,n)
+Xv,Yv=creation_sin(-3,3,n,w)
 
 
 
@@ -45,7 +45,7 @@ model_swish.compile(opti, loss='mse', metrics=['accuracy'])
 
 model_swish.summary()
 
-model_swish.fit(X, Y, batch_size=1, epochs=16, shuffle='True',validation_data=(Xv, Yv))
+model_swish.fit(X, Y, batch_size=16, epochs=50, shuffle='True',validation_data=(Xv, Yv))
 
 
 

code/fonctions_activations_classiques/tanh_vs_ReLU.py

@@ -14,15 +14,15 @@ from fonction_activation import *
 from Creation_donnee import *
 import numpy as np
 w=10
-n=20
+n=2000
 #création de la base de donnéé
-X,Y=creation_x2(-1.5,-1,n)
-X2,Y2=creation_x2(1,1.5,n)
+X,Y=creation_sin(-1.5,-1,n,w)
+X2,Y2=creation_sin(1,1.5,n,w)
 X=np.concatenate([X,X2])
 Y=np.concatenate([Y,Y2])
 
 n=10000
-Xv,Yv=creation_x2(-3,3,n)
+Xv,Yv=creation_sin(-3,3,n,w)