卷积神经网络 数字识别

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import numpy as np
data_dir='MNIST_data/'
mnist=input_data.read_data_sets(data_dir,one_hot=True)
log_dir="E:\coding\log/"
max_steps=10000
learning_rate=0.001
dropout_rate=0.9

sess=tf.InteractiveSession()
with tf.name_scope('input'):
    x=tf.placeholder(dtype=tf.float32,shape=[None,784],name="name_x")
    y=tf.placeholder(dtype=tf.float32,shape=[None,10],name="name_y")
with tf.name_scope("input_reshape"):
    x_reshape=tf.reshape(x,shape=[-1,28,28,1])
    tf.summary.image(name="input",tensor=x_reshape,max_outputs=10)

def weight_init(shape):
    weight=tf.Variable(tf.truncated_normal(shape=shape,stddev=0.1))
    return weight
def bias_init(shape):
    bias=tf.Variable(tf.constant(0.1,shape=shape))
    return bias
def variable_sum(var):
    with tf.name_scope("summaries"):
        mean=tf.reduce_mean(var)
        tf.summary.scalar('mean',mean)
        with tf.name_scope('stddev'):
            stddev=tf.sqrt(tf.reduce_mean(tf.square(var-mean)))
        tf.summary.scalar('stddev',stddev)
        tf.summary.scalar('min',tf.reduce_min(var))
        tf.summary.scalar('max',tf.reduce_max(var))
        tf.summary.histogram('histogram',var)
def nn_layers(layer_name,input_tensor,input_dim,output_dim,act=tf.nn.relu):
    with tf.name_scope(layer_name):
        with tf.name_scope("weights"):
            weights=weight_init((input_dim,output_dim))
            variable_sum(weights)
        with tf.name_scope("bias"):
            bias=bias_init([output_dim])
            variable_sum(bias)
        with tf.name_scope("wx_plus_b"):
            wx_plus_b=tf.matmul(input_tensor,weights)+bias
            tf.summary.histogram('pre_activation',wx_plus_b)
        acted=act(wx_plus_b,name="activation")
        tf.summary.histogram('activation',acted)
        return acted
hidden1=nn_layers("hidden1",x,784,500)
with tf.name_scope("dropout"):
    keep_prob=tf.placeholder(name="keep_prob",dtype=tf.float32)
    tf.summary.scalar("keep_prob",keep_prob)
    dropped=tf.nn.dropout(hidden1,keep_prob=keep_prob)
y_=nn_layers("layer2",dropped,500,10,act=tf.identity)
with tf.name_scope('cross_entory'):
    diff=tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=y_)
    with tf.name_scope("total"):
        cross_entory=tf.reduce_mean(diff)
tf.summary.scalar(tensor=cross_entory,name="cross_entory")
with tf.name_scope("train"):
    train_step=tf.train.AdamOptimizer(learning_rate).minimize(cross_entory)
    with tf.name_scope("train_step"):
        correct_prediction=tf.equal(tf.arg_max(y,1),tf.argmax(y_,1))
    with tf.name_scope('accuary'):
        accuary=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
tf.summary.scalar("accuary",accuary)
merged=tf.summary.merge_all()
train_writer=tf.summary.FileWriter(log_dir+'/train',sess.graph)
test_writer=tf.summary.FileWriter(log_dir+'/test',sess.graph)
tf.global_variables_initializer().run()
def feed_dict(train):
    if train:
        xs,ys=mnist.train.next_batch(100)
        k=dropout_rate
    else:
        xs,ys=mnist.test.images,mnist.test.labels
        k=1.0
    return {x:xs,y:ys,keep_prob:k}
saver=tf.train.Saver()
for i in range(max_steps):
    if i%10==0:
        summary,acc=sess.run([merged,accuary],feed_dict=feed_dict(False))
        test_writer.add_summary(summary,i)
        print("accuary at step %s:%s"%(i,acc))
    else:
        if i%100==99:
            run_options=tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
            run_metadata=tf.RunMetadata()
            summary,_=sess.run([merged,train_step],feed_dict=feed_dict(True),options=run_options,run_metadata=run_metadata)
            train_writer.add_run_metadata(run_metadata,'step%03d'%i)
            train_writer.add_summary(summary,i)
            saver.save(sess,log_dir+'/model.ckpt',i)
            print('Adding run metadata for',i)
        else:
            summary,_=sess.run([merged,train_step],feed_dict=feed_dict(True))
            train_writer.add_summary(summary,i)
train_writer.close()
test_writer.close()

实验结果：

心得: 复习了tensorboard的使用 接下来总结一下tensorboard的使用 对代码的理解可参考http://blog.csdn.net/sinat_33761963/article/details/62433234