experiment_for_msmits.py

gistfile1.txt

# -- imports --
import numpy as np
import tensorflow as tf
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)

# np.set_printoptions(precision=2) reduces np precision output to 2 digit
np.set_printoptions(precision=2, suppress=True)

# -- constant data --
x = [[0., 0.], [1., 1.], [1., 0.], [0., 1.], [-1., -1.], [-1., 0.], [0., -1.]]
y_ = [[0.],    [0.],     [1.],     [1.],     [0.],       [1.],      [1.]]

# -- induction --
# 1x2 input -> 2x5 hidden sigmoid -> 5x1 sigmoid output
SIZE = 5
# Layer 0 = the x2 inputs
x0 = tf.constant(x, dtype=tf.float32)
y0 = tf.constant(y_, dtype=tf.float32)

# Layer 1 = the 2x5 hidden sigmoid
m1 = tf.Variable(tf.random_uniform([2, SIZE], minval=-0.5, maxval=0.5, dtype=tf.float32))
b1 = tf.Variable(tf.random_uniform([SIZE], minval=-0.5, maxval=0.5, dtype=tf.float32))
h1 = tf.sigmoid(tf.matmul(x0, m1) + b1)

# Layer 2 = the 5x1 sigmoid output
m2 = tf.Variable(tf.random_uniform([SIZE, 1], minval=-0.5, maxval=0.5, dtype=tf.float32))
b2 = tf.Variable(tf.random_uniform([1], minval=-0.5, maxval=0.5, dtype=tf.float32))
y_out = tf.sigmoid(tf.matmul(h1, m2) + b2)


# -- loss --

# loss : sum of the squares of y0 - y_out
loss = tf.reduce_sum(tf.square(y0 - y_out))

# training step : gradient descent (1.0) to minimize loss
train = tf.train.GradientDescentOptimizer(1.0).minimize(loss)


# -- training --
# run 2500 times using all the X and Y
# print out the loss and any other interesting info
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print("\nloss")
    for step in range(2500):
        sess.run(train)
        if (step + 1) % 100 == 0:
            print(sess.run(loss))

    results = sess.run([m1, b1, m2, b2, y_out, loss])
    labels = "m1,b1,m2,b2,y_out,loss".split(",")
    for label, result in zip(*(labels, results)):
        print("")
        print(label)
        print(result)

print("")