Tensorflow MNIST手写数字识别

X: image of a handwritten digit

Y: the digit value recognize the digit in the image

MODEL:

logits = X*w + b

Y_predicted = softmax(logits)

loss = cross_entropy(Y, Y_predicted)

数据集下载地址： http://yann.lecun.com/exdb/mnist/

代码：

input.py

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os
import tempfile

import numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

mnist.py

import tensorflow as tf
import input_data

#define paramaters for the model
learning_rate = 0.01
batch_size = 128
n_epochs = 30

#step 1:read in data
#using TF Learn's built in function to load MNIST data to the folder data/mnist
mnist = input_data.read_data_sets('data/',one_hot = True)

#step 2: creat placeholder for features and labels
#each image in the MNIST data is of shape 28*28 = 784
#therefore,each image is represented with a 1x784 tensor
#there are 10 classes for each image,corresponding to digits 0-9
#each lable iss one hot vector
X = tf.placeholder(tf.float32, [batch_size, 784], name = 'X_placeholder')
Y = tf.placeholder(tf.float32, [batch_size, 10], name = 'Y_placeholder')

#step 3:creat weights and bias
#w is initialized to random variables with mean of 0, stddev of 0.01
#b is initialized to 0
#shape of w depends on the dimension of X and Y so that Y = tf.matul(X, w)
#shape of b depends on Y
w = tf.Variable(tf.random_normal(shape= [784,, 10],stddev = 0.01), name = 'wieghts')
b = tf.Variable(tf.zeros([1,10]), name="bias")

#step 4:build model
#the model that returns the logits
#this logits will be later passed through softmax layer
logits = tf.matmul(X,w)+b

#step 5:define loss function
#use cross entropy of softmax of logits as the loss function
entropy = tf.nn.softmax_cross_entropy_with_logits(logits,Y,name='loss')
loss = tf.reduce_mean(entropy)#computes the mean over all the examples in the batch

#step 6: define traning op
#using gradient descent with learning rate of 0.01 to minimize loss
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)


with tf.Session() as sess:
    #to visualize using TensorBoard
    writer = tf.summary.FileWriter('./my_graph/03/logistic_reg', sess.graph)
    start_time = time.time()
    sess.run(tf.global_variables_initializer())
    n_batches = int(mnist.train.num_examples/batch_size)
    for i in range(n_epochs):#train the model n_epochs times
        total_loss = 0
        for _ in range(n_batches):
            X_batch, Y_batch = mnist.train.next_batch(batch_size)
            _, loss_batch = sess.run([optimizer, loss], feed_dict={X:X_batch, Y:Y_batch})
            total_loss += loss_batch
        print 'Average loss epoch {0}; {1}'.format(i, total_loss/n_batches)
    print 'Total time: {0} seconds'.format(time.time() - start_time)
    print ('Optimization Finished!')

    #test the model
    n_batches = int(mnist.test.num_example/batch_size)
    total_correct_preds = 0
    for i in range(n_batches):
        x_batch, Y_batch = mnist.test.next_batch(batch_size)
        _,loss_batch, logits_batch = sess.run([optimizer, loss, logits], feed_dict={X: X_batch, Y:Y_batch})
        preds = tf.nn.softmax(logits_batch)
        correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(Y_batch, 1))
        accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32))
        total_correct_preds += sess.run(accuracy)
    print 'Accuracy {0}'.format(total_correct_preds/mnist.test.num_examples)

    writer.close()

结果：