In [ ]:

    




    

In [ ]:

    




    

In [1]:

    

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.examples.tutorials.mnist import input_data


    

In [ ]:

    




    

In [2]:

    

mnist = input_data.read_data_sets("/tmp/tensorflow/mnist/input_data", one_hot=True)


x = tf.placeholder(tf.float32, [None, 784])

w = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, w) + b)

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = - tf.reduce_mean(tf.reduce_sum(y_ * tf.log(y)))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.global_variables_initializer()


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


for _ in range(1000):
	batch_xs, batch_ys = mnist.train.next_batch(100)
	sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
	#print(sess.run(cross_entropy, feed_dict={x: batch_xs, y_: batch_ys}))

print("W:",  sess.run(w))
print("b:", sess.run(b))

# array of true/false, that stores whether it predicts correct(=true) or not(false)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_, 1))

# first case into 0/1, then calculate the accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

sess.close()


    

    




Extracting /tmp/tensorflow/mnist/input_data/train-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/train-labels-idx1-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-labels-idx1-ubyte.gz
W: [[ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 ..., 
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]]
b: [-0.56963778  0.41223094  0.19959284 -0.28630033 -0.02008468  2.00138426
 -0.18814687  0.89906693 -2.063977   -0.38412941]
0.9033

In [ ]:

    




    

In [ ]:

    




    

In [4]:

    

# Import data
mnist = input_data.read_data_sets("/tmp/mnist/", one_hot=True)

# Create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b

# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])

# The raw formulation of cross-entropy,
#
#   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
#                                 reduction_indices=[1]))
#
# can be numerically unstable.
#
# So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
# outputs of 'y', and then average across the batch.
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)

sess = tf.Session()
init_op = tf.global_variables_initializer()

sess.run(init_op)

# Train
for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

print("W:",  sess.run(W))
print("b:", sess.run(b))    
    

    
# Test trained model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y_: mnist.test.labels}))


## resize the W to one-hot vector, check its parameters, do it after finished
## prediction, still we can do it, as it doesn't change W
print("W(-> one-hot vector):", sess.run(tf.reduce_sum(tf.reshape(W, [-1]))))


    

    




Extracting /tmp/mnist/train-images-idx3-ubyte.gz
Extracting /tmp/mnist/train-labels-idx1-ubyte.gz
Extracting /tmp/mnist/t10k-images-idx3-ubyte.gz
Extracting /tmp/mnist/t10k-labels-idx1-ubyte.gz
W: [[ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 ..., 
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]
 [ 0.  0.  0. ...,  0.  0.  0.]]
b: [-0.38706648  0.34549493  0.1118118  -0.25729853  0.00582388  1.30816662
 -0.10529024  0.62364125 -1.43931139 -0.20597126]
0.9159
W(-> one-hot vector): 2.65837e-05

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: