4.py

import gzip
import tensorflow as tf
import struct
import numpy as np
import random

def one_hot_encode(i):
	ret = [0] * 10
	ret[i] = 1
	return ret

def load_idx1_file(filename):
	with gzip.GzipFile(filename) as f:
		magic_number, num_items = struct.unpack('>LL', f.read(8))
		assert magic_number == 0x0801

		print('Loading %s (%d)'%(filename, num_items))
		return [one_hot_encode(i) for i in f.read(num_items)]

def load_idx3_file(filename):
	with gzip.GzipFile(filename) as f:
		magic_number, num_images, num_rows, num_cols = struct.unpack('>LLLL', f.read(4 * 4))
		assert magic_number == 0x0803

		print('Loading %s (%d, %dx%d)'%(filename, num_images, num_rows, num_cols))

		imgs = [(np.frombuffer(f.read(num_rows * num_cols), dtype=np.byte)&0xff)/255. for _ in range(num_images)]
		return imgs

training_set_labels = load_idx1_file('mnist_data/train-labels-idx1-ubyte.gz')
training_set_images = load_idx3_file('mnist_data/train-images-idx3-ubyte.gz')
training_set = list(zip(training_set_images, training_set_labels))
test_set_labels = load_idx1_file('mnist_data/t10k-labels-idx1-ubyte.gz')
test_set_images = load_idx3_file('mnist_data/t10k-images-idx3-ubyte.gz')
test_set = list(zip(test_set_images, test_set_labels))

# model
placeholder_x = tf.placeholder('float', shape=[None, 28 * 28]) # images
placeholder_y = tf.placeholder('float', shape=[None, 10]) # labels

W = tf.Variable(tf.random_normal(shape=[28 * 28, 10], stddev=.1))
b = tf.Variable(tf.zeros([10]))

pred = tf.nn.softmax(tf.matmul(placeholder_x, W) + b)
loss = -tf.reduce_sum(placeholder_y * tf.log(pred)) # cross entropy

train_step = tf.train.GradientDescentOptimizer(.01).minimize(loss)

accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(placeholder_y, 1), tf.argmax(pred, 1)), tf.float32))

sess = tf.Session()
sess.run(tf.initialize_all_variables())

for i in range(10000):
	x, y = zip(*random.sample(training_set, 100)) # sample 100 training data
	_, tmp_loss, tmp_accuracy = sess.run([train_step, loss, accuracy], feed_dict={placeholder_x: x, placeholder_y: y})

	if i % 100 == 0:
		print('training avg_loss: {}, avg_accuracy: {}'.format(tmp_loss/100., tmp_accuracy))

		x, y = zip(*test_set)
		tmp_loss, tmp_accuracy = sess.run([loss, accuracy], feed_dict={placeholder_x: x, placeholder_y: y})

		print('test avg_loss: {}, avg_accuracy: {}'.format(tmp_loss/len(test_set), tmp_accuracy))