```python
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

```


```python
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
```


```python
with tf.name_scope("input_X"):
	x = tf.placeholder(tf.float32, [None, 784])
```


```python
with tf.name_scope("Weight_and_bias"):
	W = tf.Variable(tf.zeros([784, 10]))
	b = tf.Variable(tf.zeros([10]))
```


```python
w_h = tf.summary.histogram("weight",W)
b_h = tf.summary.histogram("bias",b)
```


```python
with tf.name_scope("Prediction_y"):
	y = tf.nn.softmax(tf.matmul(x, W) + b)
```


```python
with tf.name_scope("Actual_y"):
	y_ = tf.placeholder(tf.float32, [None, 10])
```


```python
with tf.name_scope("Cross_Entropy"):
	cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
	tf.summary.scalar("cost_function",cross_entropy)
```


```python
with tf.name_scope("GradientDescentOptimizer"):
	train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
```


```python
with tf.name_scope("accuracy"):
        correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar("accuracy",accuracy)
```


```python
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.2
sess = tf.Session(config=config)
```


```python
init = tf.global_variables_initializer()
sess.run(init)
```


```python
merged_summary_op = tf.summary.merge_all()
writer = tf.summary.FileWriter("output", sess.graph)
```


```python
for i in range(1000):
	batch_xs, batch_ys = mnist.train.next_batch(100)
	result = sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
	summary_val = sess.run(merged_summary_op, feed_dict={x: batch_xs, y_: batch_ys})
	writer.add_summary(summary_val)

```


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


```python
writer.close()
```


```python

```