A demo for MNIST LeNet model for TensorFlow, including exporting model and visualization.

mnist-convnet-lenet-visualize.py

import os
import tensorflow as tf

LOGDIR = 'visualize/'

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("F:\\Datasets\\AorB\\mnist\\", one_hot=True)

def conv_layer(input, size_in, size_out, name="conv"):
  with tf.name_scope(name):
    w = tf.Variable(tf.truncated_normal([5, 5, size_in, size_out], stddev=0.1), name="W")
    b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
    conv = tf.nn.conv2d(input, w, strides=[1, 1, 1, 1], padding="VALID")
    act = tf.nn.relu(conv + b)
    tf.summary.histogram("weights", w)
    tf.summary.histogram("biases", b)
    tf.summary.histogram("activations", act)
    return tf.nn.max_pool(act, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")


def fc_layer(input, size_in, size_out, name="fc"):
  with tf.name_scope(name):
    w = tf.Variable(tf.truncated_normal([size_in, size_out], stddev=0.1), name="W")
    b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
    act = tf.nn.relu(tf.matmul(input, w) + b)
    tf.summary.histogram("weights", w)
    tf.summary.histogram("biases", b)
    tf.summary.histogram("activations", act)
    return act

def fc_output_layer(input, size_in, size_out, name="fco"):
  with tf.name_scope(name):
    w = tf.Variable(tf.truncated_normal([size_in, size_out], stddev=0.1), name="W")
    b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
    act = tf.nn.softmax(tf.matmul(input, w) + b)
    tf.summary.histogram("weights", w)
    tf.summary.histogram("biases", b)
    tf.summary.histogram("activations", act)
    return act

def main():
  tf.reset_default_graph()
  sess = tf.Session()

  # Setup placeholders, and reshape the data
  x = tf.placeholder(tf.float32, shape=[None, 784], name="x")
  x_image = tf.reshape(x, [-1, 28, 28, 1])
  tf.summary.image('input', x_image, 3)
  y = tf.placeholder(tf.float32, shape=[None, 10], name="labels")

  conv_1 = conv_layer(x_image, 1, 6, "conv1")
  conv_2 = conv_layer(conv_1, 6, 12, "conv2")

  flattened = tf.reshape(conv_2, [-1, 4 * 4 * 12])

  fc1 = fc_layer(flattened, 4 * 4 * 12, 1024, "fc1")
  embedding_input = fc1
  embedding_size = 1024
  logits = fc_output_layer(fc1, 1024, 10, "fc2")

  with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.square(logits - y), name="loss")
    tf.summary.scalar("loss", loss)

  with tf.name_scope("train"):
    train_step = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

  with tf.name_scope("accuracy"):
    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    tf.summary.scalar("accuracy", accuracy)

  summ = tf.summary.merge_all()

  embedding = tf.Variable(tf.zeros([1024, embedding_size]), name="test_embedding")
  assignment = embedding.assign(embedding_input)
  saver = tf.train.Saver()

  sess.run(tf.global_variables_initializer())
  writer = tf.summary.FileWriter(LOGDIR + "mnist-convnet")
  writer.add_graph(sess.graph)

  config = tf.contrib.tensorboard.plugins.projector.ProjectorConfig()
  embedding_config = config.embeddings.add()
  embedding_config.tensor_name = embedding.name
  embedding_config.sprite.image_path = LOGDIR + 'sprite_1024.png'
  embedding_config.metadata_path = LOGDIR + 'labels_1024.tsv'
  # Specify the width and height of a single thumbnail.
  embedding_config.sprite.single_image_dim.extend([28, 28])
  tf.contrib.tensorboard.plugins.projector.visualize_embeddings(writer, config)

  for i in range(2001):
    batch = mnist.train.next_batch(100)
    if i % 5 == 0:
      [train_accuracy, s] = sess.run([accuracy, summ], feed_dict={x: batch[0], y: batch[1]})
      writer.add_summary(s, i)
      if i % 200 == 0:
        print("Step %d, train accuracy %g"%(i, train_accuracy))
    if i % 500 == 0:
      sess.run(assignment, feed_dict={x: mnist.test.images[:1024], y: mnist.test.labels[:1024]})
      saver.save(sess, os.path.join(LOGDIR, "model.ckpt"), i)
    sess.run(train_step, feed_dict={x: batch[0], y: batch[1]})

if __name__ == '__main__':
  main()