example for tensorflow

mnist_tb_example.py

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

def main(_):
  mnist = input_data.read_data_sets("./data", one_hot=True)
  x = tf.placeholder(tf.float32, [None, 784])
  W = tf.Variable(tf.truncated_normal(shape=[784, 10], stddev=0.1))
  b = tf.Variable(tf.constant(0.1, shape=[10]))
  y = tf.matmul(x, W) + b
  y_ = tf.placeholder(tf.float32, [None, 10])
  cross_entropy = tf.reduce_mean(
      tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
  train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

  # Attach summaries to loss & accuracy
  tf.summary.scalar('loss', cross_entropy)
  tf.summary.scalar('accuracy', accuracy)
  merged = tf.summary.merge_all()

  sess = tf.Session()
  sess.run(tf.global_variables_initializer())
  
  # create a writer to save logs
  writer = tf.summary.FileWriter('./tb_logs',sess.graph)
  for it in range(5000):
    batch_xs, batch_ys = mnist.train.next_batch(128)
    # run merged op in session
    _, loss, summary = sess.run([train_step, cross_entropy, merged], feed_dict={x: batch_xs, y_: batch_ys})
    print("iteration: {}, loss: {}".format(it, loss))
    writer.add_summary(summary, it)

  final_test = sess.run(accuracy, feed_dict={x: mnist.test.images,y_: mnist.test.labels})
  print("final test acc: %.2f"%final_test)

if __name__ == '__main__':
  tf.app.run(main=main)