This problem occurs on the basis of pycharm.
I don’t know how to solve the problem with this laptop.
I used colab just in case. It works just right, but I want to use this laptop. Please tell me how to solve the problem.
I’m sorry that I’m not good at English.
from tensorflow.math import exp, maximum
tensorflow-cpu2.7.0 (pip)
code
import tensorflow as tf
from tensorflow.math import exp, maximum
from tensorflow.keras.layers import Activation
x = tf.random.normal(shape=(1, 5))
sigmoid = Activation(‘sigmoid’)
tanh = Activation(‘tanh’)
relu = Activation(‘relu’)
y_sigmoid_tf = sigmoid(x)
y_tanh_tf = tanh(x)
y_relu_tf = relu(x)
y_sigmoid_man = 1 / (1 + exp(-x))
y_tanh_man = (exp(x) - exp(-x)) / (exp(x) + exp(-x))
y_relu_man = maximum(x, 0)
print(“x: {}\n{}”.format(x.shape, x.numpy()))
print(“sigmoid(Tensorflow): {}\n{}”.format(y_sigmoid_tf.shape, y_sigmoid_tf.numpy()))
print(“sigmoid(manual): {}\n{}”.format(y_sigmoid_man.shape, y_sigmoid_man.numpy()))
print(“Tanh(Tensorflow): {}\n{}”.format(y_tanh_tf.shape, y_tanh_tf.numpy()))
print(“Tanh(manual): {}\n{}\n”.format(y_tanh_man.shape, y_tanh_man.numpy()))
print(“ReLU(Tensorflow): {}\n{}”.format(y_relu_tf.shape, y_relu_tf.numpy()))
print(“ReLU(manual): {}\n{}\n”.format(y_relu_man.shape, y_relu_man.numpy()))
Result
x: (1, 5)
[[-1.1591758 2.2604184 -0.5664556 -2.350039 -0.1003536]]
sigmoid(Tensorflow): (1, 5)
[[0.2388171 0.9055454 0.3620551 0.08706263 0.47493264]]
sigmoid(manual): (1, 5)
[[0.2388171 0.9055454 0.3620551 0.08706267 0.47493264]]
Tanh(Tensorflow): (1, 5)
[[-0.82077116 0.9784743 -0.5127515 -0.98197484 -0.10001805]]
Tanh(manual): (1, 5)
[[-0.82077116 0.9784743 -0.5127515 -0.9819748 -0.10001804]]
ReLU(Tensorflow): (1, 5)
[[0. 2.2604184 0. 0. 0. ]]
ReLU(manual): (1, 5)
[[0. 2.2604184 0. 0. 0. ]]