tensorflow_mnist

import  tensorflow as tf
import numpy as np

from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("mnist",one_hot=True)

x=tf.placeholder(tf.float32,shape=[None,784],name="x")
y=tf.placeholder(tf.float32,shape=[None,10],name="y")

x_t=tf.placeholder(tf.float32,shape=[None,784],name="x_t")
y_t=tf.placeholder(tf.float32,shape=[None,10],name="y_t")

W=tf.Variable(tf.zeros([784,10]))
B=tf.Variable(tf.zeros([10]))

t=tf.matmul(x,W)+B
y1=tf.nn.softmax(t)
entroy=tf.nn.softmax_cross_entropy_with_logits(logits=y1,labels=y)
loss=tf.reduce_mean(entroy)

t_t=tf.matmul(x_t,W)+B
y1_t=tf.nn.softmax(t_t)
correct_pred = tf.equal(tf.argmax(y1_t, 1), tf.argmax(y_t, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

optimizer=tf.train.GradientDescentOptimizer(learning_rate=0.01)
train_step=optimizer.minimize((loss))

init=tf.global_variables_initializer()



batch_size=100
epochs=int(mnist.train.num_examples/batch_size)




with tf.Session() as sess:
    sess.run(init)
    """
    x_data = {'images': mnist.train.images}['images']
    y_data = mnist.train.labels
    """
    x_data_test = {'images': mnist.test.images}['images']
    y_data_test = mnist.test.labels

    for nStep in range(10000):
        for n in range(epochs):
            batch_x,batch_y=mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_x,y:batch_y})
            lost=sess.run(loss,feed_dict={x:batch_x,y:batch_y})
            acc=sess.run(accuracy,feed_dict={x_t:batch_x,y_t:batch_y})
        test = sess.run(accuracy, feed_dict={x_t: x_data_test[:256], y_t: y_data_test[:256]})
        print(nStep,lost,acc,test)