rajout de nouvelle fonction

code/fonctions_activations_classiques/Creation_donnee.py

@@ -90,4 +90,26 @@ def creation_x_sin2(tmin,tmax,n,w,a=1,b=1,c=0):
     Lx=np.array(Lx)
     return(t,Lx)
 
+def creation_x(tmin,tmax,n):
+    Lx=[]
+    t= np.linspace(tmin,tmax,n)
+    for i in t:
+        Lx.append(i)
+    return(t,np.array(Lx))
+    
 
+def creation_arctan(tmin,tmax,n):
+    Lx=[]
+    t= np.linspace(tmin,tmax,n)
+    for i in t:
+        Lx.append(np.arctan(i))
+    return(t,np.array(Lx))
+
+
+def creation_x2(tmin,tmax,n):
+    Lx=[]
+    t= np.linspace(tmin,tmax,n)
+    for i in t:
+        Lx.append(i**2)
+    return(t,np.array(Lx))
+    

code/fonctions_activations_classiques/fonction_activation.py

@@ -8,7 +8,7 @@ import tensorflow as tf
 
 
 
-def snake(x, alpha=1.0):
+def snake(x, alpha=10):
     return (x + tf.sin(x)**2/alpha)
 
 

code/fonctions_activations_classiques/sin.py

@@ -33,11 +33,8 @@ model_sin=tf.keras.models.Sequential()
 
 model_sin.add(tf.keras.Input(shape=(1,)))
 
-model_sin.add(tf.keras.layers.Dense(4, activation=sin))
-model_sin.add(tf.keras.layers.Dense(4, activation=sin))
-model_sin.add(tf.keras.layers.Dense(4, activation=sin))
-model_sin.add(tf.keras.layers.Dense(4, activation=sin))
-model_sin.add(tf.keras.layers.Dense(4, activation=sin))
+model_sin.add(tf.keras.layers.Dense(512, activation=sin))
+
 
 
 model_sin.add(tf.keras.layers.Dense(1))
@@ -69,9 +66,3 @@ plt.legend()
 plt.show()
 
 
-"""
-Created on Wed Nov 24 16:53:37 2021
-
-@author: virgi
-"""
-

code/fonctions_activations_classiques/snake_vs_ReLU.py

@@ -11,16 +11,16 @@ from fonction_activation import *
 
 from Creation_donnee import *
 import numpy as np
-
+w=10
 n=20
 #création de la base de donnéé
-X,Y=creation_sin(-15,-8,n,1,)
-X2,Y2=creation_sin(10,18,n,1,)
+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_sin(-20,20,n,1)
+Xv,Yv=creation_sin(-2,2,n,w)
 
 
 model_ReLU=tf.keras.models.Sequential()
@@ -28,11 +28,8 @@ model_ReLU=tf.keras.models.Sequential()
 
 model_ReLU.add(tf.keras.Input(shape=(1,)))
 
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
+model_ReLU.add(tf.keras.layers.Dense(512, activation='relu'))
+
 
 
 model_ReLU.add(tf.keras.layers.Dense(1))
@@ -46,7 +43,7 @@ model_ReLU.summary()
 
 
 
-model_ReLU.fit(X, Y, batch_size=1, epochs=10, shuffle='True',validation_data=(Xv, Yv))
+model_ReLU.fit(X, Y, batch_size=16, epochs=10, shuffle='True',validation_data=(Xv, Yv))
 
 
 
@@ -54,11 +51,7 @@ model_snake=tf.keras.models.Sequential()
 
 model_snake.add(tf.keras.Input(shape=(1,)))
 
-model_snake.add(tf.keras.layers.Dense(64, activation=snake))
-model_snake.add(tf.keras.layers.Dense(64, activation=snake))
-model_snake.add(tf.keras.layers.Dense(64, activation=snake))
-model_snake.add(tf.keras.layers.Dense(64, activation=snake))
-model_snake.add(tf.keras.layers.Dense(64, activation=snake))
+model_snake.add(tf.keras.layers.Dense(512, activation=snake))
 
 
 model_snake.add(tf.keras.layers.Dense(1))
@@ -70,7 +63,7 @@ model_snake.compile(opti, loss='mse', metrics=['accuracy'])
 
 model_snake.summary()
 
-model_snake.fit(X, Y, batch_size=1, epochs=10, shuffle='True',validation_data=(Xv, Yv))
+model_snake.fit(X, Y, batch_size=16, epochs=100, shuffle='True',validation_data=(Xv, Yv))
 
 
 

code/fonctions_activations_classiques/swish.py

@@ -31,11 +31,8 @@ model_swish=tf.keras.models.Sequential()
 
 model_swish.add(tf.keras.Input(shape=(1,)))
 
-model_swish.add(tf.keras.layers.Dense(64, activation='swish'))
-model_swish.add(tf.keras.layers.Dense(64, activation='swish'))
-model_swish.add(tf.keras.layers.Dense(64, activation='swish'))
-model_swish.add(tf.keras.layers.Dense(64, activation='swish'))
-model_swish.add(tf.keras.layers.Dense(64, activation='swish'))
+model_swish.add(tf.keras.layers.Dense(512, activation='swish'))
+
 
 
 model_swish.add(tf.keras.layers.Dense(1))

code/fonctions_activations_classiques/tanh_vs_ReLU.py

@@ -30,11 +30,8 @@ model_ReLU=tf.keras.models.Sequential()
 
 model_ReLU.add(tf.keras.Input(shape=(1,)))
 
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
-model_ReLU.add(tf.keras.layers.Dense(64, activation='relu'))
+model_ReLU.add(tf.keras.layers.Dense(512, activation='relu'))
+
 
 
 model_ReLU.add(tf.keras.layers.Dense(1))
@@ -56,11 +53,8 @@ model_tanh=tf.keras.models.Sequential()
 
 model_tanh.add(tf.keras.Input(shape=(1,)))
 
-model_tanh.add(tf.keras.layers.Dense(64, activation='tanh'))
-model_tanh.add(tf.keras.layers.Dense(64, activation='tanh'))
-model_tanh.add(tf.keras.layers.Dense(64, activation='tanh'))
-model_tanh.add(tf.keras.layers.Dense(64, activation='tanh'))
-model_tanh.add(tf.keras.layers.Dense(64, activation='tanh'))
+model_tanh.add(tf.keras.layers.Dense(512, activation='tanh'))
+
 
 
 model_tanh.add(tf.keras.layers.Dense(1))

code/fonctions_activations_classiques/x_sin.py

@@ -40,11 +40,8 @@ model_xsin=tf.keras.models.Sequential()
 
 model_xsin.add(tf.keras.Input(shape=(1,)))
 
-model_xsin.add(tf.keras.layers.Dense(64, activation=x_sin))
-model_xsin.add(tf.keras.layers.Dense(64, activation=x_sin))
-model_xsin.add(tf.keras.layers.Dense(64, activation=x_sin))
-model_xsin.add(tf.keras.layers.Dense(64, activation=x_sin))
-model_xsin.add(tf.keras.layers.Dense(64, activation=x_sin))
+model_xsin.add(tf.keras.layers.Dense(512, activation=x_sin))
+
 
 
 model_xsin.add(tf.keras.layers.Dense(1))