1.原理图:
2.代码:
import numpy as np
import tensorflow as tf
import matplotlib. pyplot as plt
import tensorflow. examples. tutorials. mnist. input_data as input_data
mnist = input_data. read_data_sets( 'data/' , one_hot= True )
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10
x = tf. placeholder( "float" , [ None , n_input] )
y = tf. placeholder( "float" , [ None , n_classes] )
stddev = 0.1
weights = {
'w1' : tf. Variable( tf. random_normal( [ n_input, n_hidden_1] , stddev= stddev) ) ,
'w2' : tf. Variable( tf. random_normal( [ n_hidden_1, n_hidden_2] , stddev= stddev) ) ,
'out' : tf. Variable( tf. random_normal( [ n_hidden_2, n_classes] , stddev= stddev) )
}
biases = {
'b1' : tf. Variable( tf. random_normal( [ n_hidden_1] ) ) ,
'b2' : tf. Variable( tf. random_normal( [ n_hidden_2] ) ) ,
'out' : tf. Variable( tf. random_normal( [ n_classes] ) )
}
print ( "NETWORK READY" )
def multilayer_perceptron ( _X, _weights, _biases) :
layer_1 = tf. nn. sigmoid( tf. add( tf. matmul( _X, _weights[ 'w1' ] ) , _biases[ 'b1' ] ) )
layer_2 = tf. nn. sigmoid( tf. add( tf. matmul( layer_1, _weights[ 'w2' ] ) , _biases[ 'b2' ] ) )
return ( tf. matmul( layer_2, _weights[ 'out' ] ) + _biases[ 'out' ] )
pred = multilayer_perceptron( x, weights, biases)
cost = tf. reduce_mean( tf. nn. softmax_cross_entropy_with_logits( labels= y, logits= pred) )
optm = tf. train. GradientDescentOptimizer( learning_rate= 0.001 ) . minimize( cost)
corr = tf. equal( tf. argmax( pred, 1 ) , tf. argmax( y, 1 ) )
accr = tf. reduce_mean( tf. cast( corr, "float" ) )
init = tf. global_variables_initializer( )
print ( "FUNCTIONS READY" )
training_epochs = 20
batch_size = 100
display_step = 4
sess = tf. Session( )
sess. run( init)
for epoch in range ( training_epochs) :
avg_cost = 0 .
total_batch = int ( mnist. train. num_examples/ batch_size)
for i in range ( total_batch) :
batch_xs, batch_ys = mnist. train. next_batch( batch_size)
feeds = { x: batch_xs, y: batch_ys}
sess. run( optm, feed_dict= feeds)
avg_cost += sess. run( cost, feed_dict= feeds)
avg_cost = avg_cost / total_batch
if ( epoch+ 1 ) % display_step == 0 :
print ( "Epoch: %03d/%03d cost: %.9f" % ( epoch, training_epochs, avg_cost) )
feeds = { x: batch_xs, y: batch_ys}
train_acc = sess. run( accr, feed_dict= feeds)
print ( "TRAIN ACCURACY: %.3f" % ( train_acc) )
feeds = { x: mnist. test. images, y: mnist. test. labels}
test_acc = sess. run( accr, feed_dict= feeds)
print ( "TEST ACCURACY: %.3f" % ( test_acc) )
print ( "OPTIMIZATION FINISHED" )
3.测试:
FUNCTIONS READY
2019-05-13 20:54:41.871000: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Epoch: 003/020 cost: 2.280481198
TRAIN ACCURACY: 0.140
TEST ACCURACY: 0.197
Epoch: 007/020 cost: 2.252024189
TRAIN ACCURACY: 0.270
TEST ACCURACY: 0.288
Epoch: 011/020 cost: 2.221016071
TRAIN ACCURACY: 0.340
TEST ACCURACY: 0.373
Epoch: 015/020 cost: 2.185427118
TRAIN ACCURACY: 0.480
TEST ACCURACY: 0.443
Epoch: 019/020 cost: 2.143298683
TRAIN ACCURACY: 0.360
TEST ACCURACY: 0.482
OPTIMIZATION FINISHED