In [19]:
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_dara/", one_hot = True)
Extracting MNIST_dara/train-images-idx3-ubyte.gz
Extracting MNIST_dara/train-labels-idx1-ubyte.gz
Extracting MNIST_dara/t10k-images-idx3-ubyte.gz
Extracting MNIST_dara/t10k-labels-idx1-ubyte.gz
In [20]:
import tensorflow as tf
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)
In [21]:
y_= tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.initialize_all_variables()
In [22]:
sess = tf.Session()
sess.run(init)
In [23]:
for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x:batch_xs, y_:batch_ys})
    
In [24]:
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}))
0.9197
In [63]:
import numpy as np
import pandas as pd
from pandas import DataFrame


submission = np.savetxt('submission_softmax.csv', 
           np.c_[range(1,len(mnist.test.labels)+1),mnist.test.labels], 
           delimiter=',', 
           header = 'ImageId,Label', 
           comments = '', 
           fmt='%d')
In [ ]:
print submission
In [ ]: