前言
这篇博文主要是依照官网,介绍各种类型的summary的使用,包括标量scalar类型的,图像类型的image,直方图累心的histogram.
代码
该代码主要是使用普通的神经网络对MNIST手写体数字进行分类识别.网络各层的神经元个数为:784-500-10.784代表输入神经元个数为784,隐层神经元个数为500,输出层为10,代表10个类别.
# coding=utf-8
""" tensorboard 的使用"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
FLAGS = None
def train():
# 读取MNIST数据
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True, fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# 给下面的 tensor 加上词头; 【注:】with 不能改变其下变量的作用域
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
with tf.name_scope('input_shape'):
image_shaped_input = tf.reshape(x, shape=[-1, 28, 28, 1])
# image类型的summary
tf.summary.image('input', image_shaped_input, 10)
# 网络参数初始化
def weight_variable(shape):
initial = tf.truncated_normal(shape=shape, stddev=0.1)
return tf.Variable(initial)
def bias_varibale(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# 要写到summary的信息
def variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
# 标量型summary
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('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
# 直方图型summary,可以用来查看tensor的值的分布
tf.summary.histogram('histogram', var)
def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
with tf.name_scope(layer_name):
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights)
with tf.name_scope('biases'):
biases = bias_varibale([output_dim])
variable_summaries(biases)
with tf.name_scope('Wx_plus_b'):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.summary.histogram('pre_activations', preactivate)
activations = act(preactivate, name='activation')
tf.summary.histogram('activations', activations)
return activations
hidden1 = nn_layer(x, 784, 500, 'layer1')
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.summary.scalar('dropout_keep_probability', keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)
with tf.name_scope('cross_entropy'):
diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
with tf.name_scope('total'):
cross_entropy = tf.reduce_mean(diff)
tf.summary.scalar('cross_entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
cross_entropy)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
# 合并所有类型的 summary
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
tf.global_variables_initializer().run()
# 获取sess.run中需要的feed_dict
def feed_dict(train):
if train or FLAGS.fake_data:
xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
k = FLAGS.dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0
return {x: xs, y_: ys, keep_prob: k}
# 网络的训练和summary的写入
for i in range(FLAGS.max_steps):
if i % 10 == 0:
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('Accuracy 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))
# train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, 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()
def main(_):
# tensorflow 中的文件操作操作类tf.gfile
if tf.gfile.Exists(FLAGS.log_dir):
tf.gfile.DeleteRecursively(FLAGS.log_dir)
tf.gfile.MakeDirs(FLAGS.log_dir)
train()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--fake_data', nargs='?', const=True, type=bool,
default=False,
help='If true, uses fake data for unit testing.')
parser.add_argument('--max_steps', type=int, default=1000,
help='Number of steps to run trainer.')
parser.add_argument('--learning_rate', type=float, default=0.001,
help='Initial learning rate')
parser.add_argument('--dropout', type=float, default=0.9,
help='Keep probability for training dropout.')
parser.add_argument('--data_dir', type=str, default='MNIST_data',
help='Directory for storing input data')
parser.add_argument('--log_dir', type=str, default='MNIST_Log',
help='Summaries log directory')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
代码中产生各种类型的summary的可视化结果如下:
标量类型:
图片类型:
图模型类型:
分布类型:
直方图类型:
注意事项
(1)对于tf.summary.image,其输入的图片必须是4-D的,[batch_size, height, width, channels].
参考网址
https://www.tensorflow.org/get_started/summaries_and_tensorboard —tensorflow官网教程