Tensorflow MNIST入门

机器学习

代码

训练模型并导出.pb文件：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#import data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)
def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# Define loss and optimizer
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
"""
Train the model and save the model to disk as a model2.ckpt file
file is stored in the same directory as this python script is started
Based on the documentatoin at
https://www.tensorflow.org/versions/master/how_tos/variables/index.html
"""
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
#with tf.Session() as sess:
    #sess.run(init_op)
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
save_path = saver.save(sess, "./model2.ckpt")
tf.train.write_graph(sess.graph_def, '', 'graph.pb')
print ("Model saved in file: ", save_path)
print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

识别图片：

import sys
import tensorflow as tf
from PIL import Image, ImageFilter
def predictint(imvalue):
    """
    This function returns the predicted integer.
    The imput is the pixel values from the imageprepare() function.
    """
    # Define the model (same as when creating the model file)
    x = tf.placeholder(tf.float32, [None, 784])
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    def weight_variable(shape):
      initial = tf.truncated_normal(shape, stddev=0.1)
      return tf.Variable(initial)
    def bias_variable(shape):
      initial = tf.constant(0.1, shape=shape)
      return tf.Variable(initial)
    def conv2d(x, W):
      return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
    def max_pool_2x2(x):
      return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')   
    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    x_image = tf.reshape(x, [-1,28,28,1])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)
    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])
    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
    init_op = tf.global_variables_initializer()
    saver = tf.train.Saver()
    """
    Load the model2.ckpt file
    file is stored in the same directory as this python script is started
    Use the model to predict the integer. Integer is returend as list.
    Based on the documentatoin at
    https://www.tensorflow.org/versions/master/how_tos/variables/index.html
    """
    with tf.Session() as sess:
        sess.run(init_op)
        saver.restore(sess, "model2.ckpt")
        #print ("Model restored.")
        prediction=tf.argmax(y_conv,1)
        return prediction.eval(feed_dict={x: [imvalue],keep_prob: 1.0}, session=sess)
def imageprepare(argv):
    """
    This function returns the pixel values.
    The imput is a png file location.
    """
    im = Image.open(argv).convert('L')
    width = float(im.size[0])
    height = float(im.size[1])
    newImage = Image.new('L', (28, 28), (255)) #creates white canvas of 28x28 pixels
    if width > height: #check which dimension is bigger
        #Width is bigger. Width becomes 20 pixels.
        nheight = int(round((20.0/width*height),0)) #resize height according to ratio width
        if (nheigth == 0): #rare case but minimum is 1 pixel
            nheigth = 1  
        # resize and sharpen
        img = im.resize((20,nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
        wtop = int(round(((28 - nheight)/2),0)) #caculate horizontal pozition
        newImage.paste(img, (4, wtop)) #paste resized image on white canvas
    else:
        #Height is bigger. Heigth becomes 20 pixels. 
        nwidth = int(round((20.0/height*width),0)) #resize width according to ratio height
        if (nwidth == 0): #rare case but minimum is 1 pixel
            nwidth = 1
         # resize and sharpen
        img = im.resize((nwidth,20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
        wleft = int(round(((28 - nwidth)/2),0)) #caculate vertical pozition
        newImage.paste(img, (wleft, 4)) #paste resized image on white canvas
    #newImage.save("sample.png")
    tv = list(newImage.getdata()) #get pixel values
    #normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
    tva = [ (255-x)*1.0/255.0 for x in tv] 
    return tva
    #print(tva)
def main(argv):
    """
    Main function.
    """
    imvalue = imageprepare(argv)
    predint = predictint(imvalue)
    print (predint[0]) #first value in list
if __name__ == "__main__":
    main(sys.argv[1])

参考

mnist 源码
mnist 源码解析
深度学习 - Tensorflow on iOS 入门 + MNIST
机器学习Tensorflow笔记1：Hello World到MNIST实验
机器学习Tensorflow笔记2：超详细剖析MNIST实验
MNIST机器学习入门
写给初学者的深度学习教程之 MNIST 数字识别
tensorflow-mnist-predict