【TensorFlow】TensorBoard的使用（一）
概述
TensorBoard是一个可视化工具，它可以用来展示网络图、张量的指标变化、张量的分布情况等。特别是在训练网络的时候，我们可以设置不同的参数（比如：权重W、偏置B、卷积层数、全连接层数等），使用TensorBoader可以很直观的帮我们进行参数的选择。
本系列文章一共四篇，由浅入深，以常见的Mnist数据集为实验对象，从实现最简单TensorBoard开始，逐步增加参数、复杂度，最后实现使用TensorBoard工具可视化调参的功能。
TensorBoard的使用一共可分成四步：
- 设置保存路径：tenboard_dir = './tensorboard/test1/'
- 指定一个文件用来保存TensorFlow的图：writer = tf.summary.FileWriter(tenboard_dir + hparam)
- 把图add进去：writer.add_graph(sess.graph)
- 进入test1文件夹的上一层文件夹，在DOS窗口运行命令：tensorboard --logdir=./test1
示例
演示以上四步的一个实现过程，代码如下：
mnist_board_1.py：
import os
import tensorflow as tf
LOGDIR = './mnist'
mnist = tf.contrib.learn.datasets.mnist.read_data_sets(train_dir=LOGDIR + 'data', one_hot=True)
def conv_layer(input, size_in, size_out):
w = tf.Variable(tf.truncated_normal([5, 5, size_in, size_out], stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[size_out]))
conv = tf.nn.conv2d(input, w, strides=[1, 1, 1, 1], padding='SAME')
act = tf.nn.relu(conv + b)
return tf.nn.max_pool(act, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def fc_layer(input, size_in, size_out):
w = tf.Variable(tf.truncated_normal([size_in, size_out], stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[size_out]))
act = tf.nn.relu(tf.matmul(input, w) + b)
return act
def mnist_model(learning_rate, use_two_conv, use_two_fc, hparam):
tf.reset_default_graph()
sess = tf.Session()
# setup placeholders, and reshape the data
x = tf.placeholder(tf.float32, shape=[None, 784])
x_image = tf.reshape(x, [-1, 28, 28, 1])
y = tf.placeholder(tf.float32, shape=[None, 10])
if use_two_conv:
conv1 = conv_layer(x_image, 1, 32)
conv_out = conv_layer(conv1, 32, 64)
else:
conv1 = conv_layer(x_image, 1, 64)
conv_out = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
flattened = tf.reshape(conv_out, [-1, 7 * 7 * 64])
if use_two_fc:
fc1 = fc_layer(flattened, 7 * 7 * 64, 1024)
embedding_input = fc1
embedding_size = 1024
logits = fc_layer(fc1, 1024, 10)
else:
embedding_input = flattened
embedding_size = 7 * 7 * 64
logits = fc_layer(flattened, 7 * 7 * 64, 10)
xent = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
train_step = tf.train.AdamOptimizer(learning_rate).minimize(xent)
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
emdedding = tf.Variable(tf.zeros([1024, embedding_size]))
assignment = emdedding.assign(embedding_input)
sess.run(tf.global_variables_initializer())
# 保存路径
tenboard_dir = './tensorboard/test1/'
# 指定一个文件用来保存图
writer = tf.summary.FileWriter(tenboard_dir + hparam)
# 把图add进去
writer.add_graph(sess.graph)
for i in range(2001):
batch = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch[0], y: batch[1]})
def make_hparam_string(learning_rate, use_two_fc, use_two_conv):
conv_param = 'conv=2' if use_two_conv else 'conv=1'
fc_param = 'fc=2' if use_two_fc else 'fc=1'
return 'lr_%.0E,%s,%s' % (learning_rate, conv_param, fc_param)
def main():
# You can try adding some more learning rates
for learning_rate in [1E-4]:
# Include 'False' as a value to try different model architectures.
for use_two_fc in [True]:
for use_two_conv in [True]:
# Construct a hyperparameter string for each one(example: 'lr_1E-3,fc=2,conv=2')
hparam = make_hparam_string(learning_rate, use_two_fc, use_two_conv)
print('Starting run for %s' % hparam)
# Actually run with the new settings
mnist_model(learning_rate, use_two_fc, use_two_conv, hparam)
if __name__ == '__main__':
main()
以上程序对Mnist数据集进行两次卷积、两次全连接操作。运行后，生成如下文件：
展示
打开Windows的DOS命令行，进入test1的上一层目录，注意此处的目录一定不能进错。执行：tensorboard --logdir=./test1
在浏览器输入网址：http://localhost:6006，或者输入上图提示的网址，即可查看生成图。
由上图可以看到，生成的图较大、较乱，并且变量都是以Variable_XXX命名， 阅读起来让人不知所云。
下篇文章讲述如何针对上述情况进行优化——定义操作名字、作用域。