simple_binary_classifier

simple_classifier.py

import numpy as np
import tensorflow as tf

# Create graph
sess = tf.Session()

# Create data
x_vals = np.concatenate((np.random.normal(-1, 1, 50), np.random.normal(1, 1, 50)))
y_vals = np.concatenate((np.repeat(0, 50), np.repeat(1, 50)))
x_data = tf.placeholder(shape=[1], dtype=tf.float32)
y_target = tf.placeholder(shape=[1], dtype=tf.int32)

# Create variable (one model parameter = A)
A = tf.Variable(tf.random_normal(shape=[1]))

# Add operation to graph
# Want to create a pair = [1,0] if <A or [0,1] if >=A
my_output = tf.concat(0,[tf.to_float(tf.less(x_data, A)), tf.to_float(tf.greater_equal(x_data, A))])
my_output_expanded = tf.expand_dims(my_output, 0)

# Add classification loss (cross entropy)
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(my_output_expanded, y_target)

# Initialize variables
init = tf.initialize_all_variables()
sess.run(init)

# Create Optimizer
my_opt = tf.train.GradientDescentOptimizer(0.1)
train_step = my_opt.minimize(xentropy)

# Run loop
for i in range(901):
    rand_index = np.random.choice(100)
    rand_x = [x_vals[rand_index]]
    rand_y = [y_vals[rand_index]]
    sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})
    if i%100==0:
        print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)))
        print('Loss = ' + str(sess.run(xentropy, feed_dict={x_data: rand_x, y_target: rand_y})))