tensorflow 学习2--- mnist测试

版权声明：本文为博主原创文章，未经博主允许不得转载。

目录(?)[+]

简介

• mnist相当于ML和DL的hello world程序，通过对手写数字的图片进行训练，并对测试图片进行测试，验证其有效性

数据集的准备

• 有时候直接在代码中下载可能需要一些时间，或者提示IO error。因此在实际的使用过程中，会先下载好离线的数据
• 下载地址相关链接 
  
  • http://www.tensorfly.cn/tfdoc/tutorials/mnist_download.html
  • https://github.com/HIPS/hypergrad/tree/master/data/mnist

基本的ML方法

参考链接

• https://www.tensorflow.org/versions/r0.10/tutorials/mnist/beginners/
• 通过下载https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/mnist/mnist_softmax.py中的mnist_softmax.py，在本地，激活tensorflow环境之后，直接运行即可。
• 注意：上面的代码中，需要指定刚才下载的数据集所在的目录，需要自己修改一下，也可以通过参数传递进去，如python mnist_softmax.py --data_dir=~/MNIST_data表示在home下面的MNIST_data文件夹下

DL方法

• 数据集和刚才的相同，下载cnn_mnist.py，运行即可
• 在上面的代码中，可能需要下载数据集，因此需要首先指定已经下载好的数据集路径，在tensorflow-master/tensorflow/examples/tutorials/mnist文件夹下的fully_connected_feed.py中，可以通过修改input_data_dir来确定数据集路径，如果搜索到其中含有需要的数据集，则不会下载，而直接训练和测试了。

按照ML重新写的一个mnist

• 参考链接：http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html

• 具体代码

  from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport argparseimport sysfrom tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfFLAGS = Nonedef main(_):  # Import data    mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)    # Create the model    x = tf.placeholder(tf.float32, [None, 784])    W = tf.Variable(tf.zeros([784, 10]))    b = tf.Variable(tf.zeros([10]))    y = tf.matmul(x, W) + b    # Define loss and optimizer    y_ = tf.placeholder(tf.float32, [None, 10])    # DL defs    W_conv1 = weight_variable([5, 5, 1, 32])    b_conv1 = bias_variable([32])    x_image = tf.reshape(x, [-1,28,28,1])    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)    h_pool1 = max_pool_2x2(h_conv1)    W_conv2 = weight_variable([5, 5, 32, 64])    b_conv2 = bias_variable([64])    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)    h_pool2 = max_pool_2x2(h_conv2)    W_fc1 = weight_variable([7 * 7 * 64, 1024])    b_fc1 = bias_variable([1024])    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)    keep_prob = tf.placeholder("float")    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)    W_fc2 = weight_variable([1024, 10])    b_fc2 = bias_variable([10])    y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)    cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)    correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))    sess = tf.InteractiveSession()    tf.global_variables_initializer().run()    #sess.run(tf.initialize_all_variables())    for i in range(20000):        batch = mnist.train.next_batch(50)        if i%100 == 0:            train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})            print("step %d, training accuracy %g"%(i, train_accuracy))        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})    print("test accuracy %g" % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))# end## about DL def weight_variable(shape):    initial = tf.truncated_normal(shape, stddev=0.1)    return tf.Variable(initial)def bias_variable(shape):    initial = tf.constant(0.1, shape=shape)    return tf.Variable(initial)def conv2d(x, W):    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2x2(x):    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],                        strides=[1, 2, 2, 1], padding='SAME')#region DL endif __name__ == '__main__':  parser = argparse.ArgumentParser()  parser.add_argument('--data_dir', type=str, default='MNIST_data',                      help='Directory for storing input data')  FLAGS, unparsed = parser.parse_known_args()  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

结果图

多层感知器训练mnist

• 之前的直接利用softmax方法对数据集mnist进行处理，得到的准确率在91%左右，如果在输入层和输出层之前添加一个隐藏层，相当于多层感知器（MLP，multi-layer percepton），准确率会达到97%以上，虽然准确率无法与cnn相比，但是耗时也很少

代码

from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfmnist = input_data.read_data_sets( 'MNIST_data', one_hot = True )sess = tf.InteractiveSession()in_units = 784h1_units = 300W1 = tf.Variable( tf.truncated_normal( [ in_units, h1_units ], stddev = 0.1 ) )b1 = tf.Variable( tf.zeros( [h1_units] ) )W2 = tf.Variable( tf.zeros( [h1_units, 10] ) )b2 = tf.Variable( tf.zeros( [10] ) )x = tf.placeholder( tf.float32, [None, in_units] )keep_prob = tf.placeholder( tf.float32 )hidden1 = tf.nn.relu( tf.matmul( x, W1 ) + b1 )hidden1_drop = tf.nn.dropout( hidden1, keep_prob )y = tf.nn.softmax( tf.matmul(hidden1_drop, W2)  + b2 )y_ = tf.placeholder( tf.float32, [ None, 10 ] )cross_entropy = tf.reduce_mean( -tf.reduce_sum( y_*tf.log(y),reduction_indices=[1] ) )train_step = tf.train.AdagradOptimizer(0.3).minimize( cross_entropy )tf.global_variables_initializer().run()for i in range( 3000 ):    print( 'now train epoch : %04d' % (i+1) )    batch_xs, batch_ys = mnist.train.next_batch( 100 )    train_step.run( {x:batch_xs, y_:batch_ys, keep_prob:0.75 } )correct_predication = tf.equal( tf.argmax(y,1), tf.argmax(y_,1) )accuracy = tf.reduce_mean( tf.cast( correct_predication, tf.float32 ) )print( accuracy.eval( { x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0 } ) )

结果图

总结

• 利用基于softmax的ML方法得到的准确率大概在91%左右，但是耗时较少，用基于cnn的DL方法，准确率为99%以上，但是耗时较长