bla

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

"""
input>weight>hidden layer 1 (actv funct)>weight>hidden l2 (actv fucnt)>weights>output lacer

compare output to intended output>cost function(cross entropy)
optimization funvtion(omptimier)>minimize cost(AdamOptimizer...SGD,AdaGrad)

feed forward + backprob = epoch
"""


mnist= input_data.read_data_sets("/tmp/data", one_hot=True)
n_nodes_hl1=784
n_nodes_hl2=342
n_nodes_hl3=1

n_classes=10
batch_size=100

x=tf.placeholder('float',[None, 784])
y=tf.placeholder('float')

def neural_network_model(data):
	#(input_data*weights)+biases
	hidden_1_layer ={
	'weights':tf.Variable(tf.random_normal([784,n_nodes_hl1])),
	}

	hidden_2_layer ={
	'weights':tf.Variable(tf.random_normal([n_nodes_hl1,n_nodes_hl2])),
	}
	hidden_3_layer ={
	'weights':tf.Variable(tf.random_normal([n_nodes_hl2,n_nodes_hl3])),
	}

	output_layer ={
	'weights':tf.Variable(tf.random_normal([n_nodes_hl3,n_classes])),
	}



	l1=tf.matmul(data,hidden_1_layer['weights'])
	l1=tf.nn.relu(l1)

	l2=tf.matmul(l1,hidden_2_layer['weights'])
	l2=tf.nn.relu(l2)

	l3=tf.matmul(l2,hidden_3_layer['weights'])
	l3=tf.nn.relu(l3)

	output=tf.matmul(l3, output_layer['weights'])

	return output

def train_neural_network(x):
	prediction=neural_network_model(x)
	cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction,y))

	#defualt learning rate=0.001
	optimizer =tf.train.AdamOptimizer().minimize(cost)

	#cycles feed forward +backprob
	hm_epochs=1

	with tf.Session() as sess:
		sess.run(tf.initialize_all_variables())

		for epoch in range(hm_epochs):
			epoch_loss=0
			for _ in range(int(mnist.train.num_examples/batch_size)):
				epoch_x, epoch_y=mnist.train.next_batch(batch_size)
				_,c=sess.run([optimizer, cost], feed_dict={ x:epoch_x , y:epoch_y})
				epoch_loss+=c
			print('Epoch:',epoch," completed out of", hm_epochs, 'loss:', epoch_loss)


		correct=tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
		accuracy=tf.reduce_mean(tf.cast(correct,'float'))
		print('Accuracy:',accuracy.eval({x:mnist.test.images,y:mnist.test.labels}))

train_neural_network(x)

"""
onehot: 0=[1,0,0,0,0,0,0,0,0,0]
onehot: 1=[1,0,0,0,0,0,0,0,0,0]
onehot: 2=[0,0,1,0,0,0,0,0,0,0]
onehot: 3=[1,0,0,0,0,0,0,0,0,0]
onehot: 4=[0,1,0,0,0,0,0,0,0,0]

10 classes, 0-9
"""