tensorflow cifar10数据集的测试

说明

• 在之前的mnist数据集中，由于数据特征太少，十分简单，仅用简单的cnn就能实现99.2%的准确率，这里尝试测试更加复杂的cifar10数据集

准备

• 需要cifar10的数据集，可以在代码里实现下载，并指定文件夹

• 需要下载预处理cifar数据集的一些类，用以下代码即可得到

  git clone https://github.com/tensorflow/models.git
  cd models/tutorials/image/cifar10
  

  为使用其数据集预处理的类，需要进入该文件夹下，并新建python文件，代码具体如下

代码

import cifar10, cifar10_input
import tensorflow as tf
import numpy as np
import time

max_steps = 2000
batch_size = 128

#下载好的数据集所在的文件夹
data_dir = 'cifar10_data/cifar-10-batches-bin' 
# 如果没有下载，则需要将下面一句话取消注释并运行
#cifar10.maybe_download_and_extract()

def variable_with_weight_loss(shape, stddev, wl) :
    var = tf.Variable( tf.truncated_normal(shape, stddev=stddev) ) 
    if wl is not None:
        weight_loss = tf.multiply( tf.nn.l2_loss(var), wl, name='weight_loss' )
        tf.add_to_collection( 'losses', weight_loss )
    return var

images_train, labels_train = cifar10_input.distorted_inputs( data_dir=data_dir, batch_size=batch_size )
images_test, labels_test = cifar10_input.inputs( eval_data = True, data_dir=data_dir, batch_size=batch_size )

image_holder = tf.placeholder( tf.float32, [ batch_size, 24, 24, 3 ] )
label_holder = tf.placeholder( tf.int32, [batch_size] )

weight1 = variable_with_weight_loss( shape=[5,5,3,64], stddev=5e-2, wl=0.0 )
kernel1 = tf.nn.conv2d( image_holder, weight1, [1,1,1,1], padding='SAME' )
bias1 = tf.Variable( tf.constant( 0.0, shape=[64] ) )
conv1 = tf.nn.relu( tf.nn.bias_add( kernel1, bias1 ) )
pool1 = tf.nn.max_pool(conv1, ksize = [1,3,3,1], strides=[1,2,2,1], padding='SAME' )
norm1 = tf.nn.lrn( pool1, 4, bias=1.0, alpha=0.001/9.0, beta = 0.75 )

weight2 = variable_with_weight_loss( shape=[5,5,64,64], stddev=5e-2, wl=0.0 )
kernel2 = tf.nn.conv2d( norm1, weight2, [1,1,1,1], padding='SAME' )
bias2 = tf.Variable(tf.constant( 0.1, shape=[64] ) )
conv2 = tf.nn.relu( tf.nn.bias_add(kernel2, bias2) )
norm2 = tf.nn.lrn( conv2, 4, bias=1.0, alpha=0.001/9.0, beta = 0.75 )
pool2 = tf.nn.max_pool(norm2, ksize = [1,3,3,1], strides=[1,2,2,1], padding='SAME' )

reshape = tf.reshape( pool2, [batch_size, -1] )
dim = reshape.get_shape( )[1].value
weight3 = variable_with_weight_loss( shape=[dim,384], stddev=0.04, wl=0.004 )
bias3 = tf.Variable( tf.constant( 0.1, shape=[384] ) )
local3 = tf.nn.relu( tf.matmul( reshape, weight3 ) + bias3 )

weight4 = variable_with_weight_loss( shape=[384,192], stddev=0.04, wl=0.004 )
bias4 = tf.Variable( tf.constant( 0.1, shape=[192] ) )
local4 = tf.nn.relu( tf.matmul( local3, weight4 ) + bias4 )

weight5 = variable_with_weight_loss( shape=[192,10], stddev=1.0/192, wl=0.0 )
bias5 = tf.Variable( tf.constant( 0.0, shape=[10] ) )
logits = tf.add( tf.matmul( local4, weight5 ), bias5 )

def lossFcn( logits, labels ):
    labels = tf.cast( labels, tf.int64 )
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits( logits=logits, labels=labels, name='cross_entropy_per_example' )
    cross_entropy_mean = tf.reduce_mean( cross_entropy, name = 'cross_entropy' )
    tf.add_to_collection( 'losses', cross_entropy_mean )

    return tf.add_n( tf.get_collection( 'losses' ), name = 'total_loss' )

loss = lossFcn( logits, label_holder )
train_op = tf.train.AdamOptimizer( 1e-3 ).minimize( loss )

top_k_op = tf.nn.in_top_k( logits, label_holder, 1 )
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

tf.train.start_queue_runners()

for step in range( max_steps ):
    start_time = time.time()
    image_batch, label_batch = sess.run( [ images_train, labels_train ] )

    _, loss_value = sess.run( [train_op, loss ], feed_dict={ image_holder:image_batch, label_holder:label_batch } )
    duration = time.time() - start_time
    if step % 10 == 0:
        example_per_sec = batch_size / duration
        sec_per_batch = float( duration )

        print( ' step : %04d, loss = %.2f, %.1f example/sec; %.3f sec/batch ' %( step, loss_value, example_per_sec, sec_per_batch ) )

num_examples = 1e4
import math
num_iter = int( math.ceil( num_examples / batch_size ) )
true_count = 0
total_sample_count = num_iter * batch_size
step = 0
while step < num_iter:
    image_batch, label_batch = sess.run( [ images_test, labels_test ] )

    predictions = sess.run( [top_k_op], feed_dict = { image_holder:image_batch, label_holder:label_batch } )
    true_count += np.sum( predictions )
    step += 1

precision = 1.0 * true_count / total_sample_count 
print('precision :  %.5f' %( precision ) )

结果图

训练1000次获得了0.579的准确率，可以通过增加训练次数和改善网络结构来提升准确率