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 : d, 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