Pas encore de compte ?
Activations de couches
relu function
Testé sous Anaconda et Python 3.7
def ReLu(val): return max(0.0,val) val = 1.0 print(ReLu(val)) val1 = -1.0 print(ReLu(val1))
1.0
0.0
sigmoid function
Testé sous Anaconda et Python 3.7
import numpy as np def sigmoid(x): return 1.0 / (1.0 + np.exp(-x)) print(sigmoid(0.5))
0.6224593312018546
softmax function
Testé sous Anaconda et Python 3.7
import numpy as np def softmax(vec): exponential = np.exp(vec) probabilities = exponential / np.sum(exponential) return probabilities vector = np.array([1.0, 3.0, 2.0]) probabilities = softmax(vector) print("Probability Distribution is:") print(probabilities)
Probability Distribution is :
[0.09003057 0.66524096 0.24472847]
softplus function
Testé sous Anaconda et Python 3.7
# Importing the Tensorflow library import tensorflow as tf # Importing the NumPy library import numpy as np # Importing the matplotlib.pyplot function import matplotlib.pyplot as plt # A vector of size 15 with values from -5 to 5 a = np.linspace(-5, 5, 15) # Applying the softplus function and # storing the result in 'b' b = tf.nn.softplus(a, name ='softplus') # Initiating a Tensorflow session with tf.Session() as sess: print('Input:', a) print('Output:', sess.run(b)) plt.plot(a, sess.run(b), color = 'red', marker = "o") plt.title("tensorflow.nn.softplus") plt.xlabel("X") plt.ylabel("Y") plt.show()
Input: [-5. -4.28571429 -3.57142857 -2.85714286 -2.14285714 -1.42857143
-0.71428571 0. 0.71428571 1.42857143 2.14285714 2.85714286
3.57142857 4.28571429 5. ]
Output: [0.00671535 0.01366993 0.02772767 0.05584391 0.11093221 0.21482992
0.39846846 0.69314718 1.11275418 1.64340135 2.25378936 2.91298677
3.59915624 4.29938421 5.00671535]
softsign function
Testé sous Anaconda et Python 3.7
import numpy as np import matplotlib.pyplot as plt def SoftSign(x): s = x/(1+abs(x)) plt.plot(x,s) plt.xlabel('valus of x') plt.ylabel('SoftSign Values') plt.title('SoftSign Function') plt.legend(["Softsign"]) plt.show() return s x = np.array(np.arange(-10,11,1)) s = print(SoftSign(x))
[-0.90909091 -0.9 -0.88888889 -0.875 -0.85714286 -0.83333333
-0.8 -0.75 -0.66666667 -0.5 0. 0.5
0.66666667 0.75 0.8 0.83333333 0.85714286 0.875
0.88888889 0.9 0.90909091]
tanh function
f(x) = tanh(x)
Testé sous Anaconda et Python 3.7
import numpy as np import matplotlib.pyplot as plt in_array = np.linspace(-np.pi, np.pi, 12) out_array = np.tanh(in_array) print("in_array : ", in_array) print("\nout_array : ", out_array) # red for numpy.tanh() plt.plot(in_array, out_array, color = 'red', marker = "o") plt.title("numpy.tanh()") plt.xlabel("X") plt.ylabel("Y") plt.show()
in_array : [-3.14159265 -2.57039399 -1.99919533 -1.42799666 -0.856798 -0.28559933
0.28559933 0.856798 1.42799666 1.99919533 2.57039399 3.14159265]
out_array : [-0.99627208 -0.98836197 -0.96397069 -0.89125532 -0.69460424 -0.27807943
0.27807943 0.69460424 0.89125532 0.96397069 0.98836197 0.99627208]
selu function
elu function
exponential function
f(x) = exp(x)
Couche de densification
DenseBlock
DenseNet
FC-DenseNet - GitHub
Couche convolutive transposée
Couche de mutualisation
Couche d'augmentation d'image
Couche d'attention
Couche d'aplatissement
Couche de concaténation
Bienvenu, je m’appelle Eric Soupet et je suis l'administrateur du site elodees.com. elodees.com est un état de l'art de l'Intelligence Artificielle et se veut collaboratif, vous pouvez dès à présent proposer du contenu tels que des articles, des événements, des tutoriels, ... alors n'hésitez pas !
Crédit des images de la plate-forme : Pixabay - Pixabay License | Pexels - Pexels License