参考:
《TensorFlow技术解析与实战》
########################################################################################
训练过程的可视化TensorBoard
# -*- coding:utf-8 -*-
# ==============================================================================
# 20171114
# HelloZEX
# 训练可视化
# 注意一下,我是在SparkMNIST文件夹内打开Terminal的所以
# zhengxinxin@ubuntu:~/Desktop/PyCharm/Spark/SparkMNIST$
# 在后面键入tensorboard --logdir=logs/mnist_with_summaries
# Starting TensorBoard 47 at http://0.0.0.0:6006
# 然后在浏览器中打开网址 http://0.0.0.0:6006 或者 http://localhost:6006/ 即可
# ==============================================================================
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():
# Import data
mnist = input_data.read_data_sets("MNIST_Labels_Images", one_hot=True, fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# Create a multilayer model.
# Input placeholders
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_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.summary.image('input', image_shaped_input, 10)
# We can't initialize these variables to 0 - the network will get stuck.
def weight_variable(shape):
"""Create a weight variable with appropriate initialization."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""Create a bias variable with appropriate initialization."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def variable_summaries(var):
#对一个张量添加多个描述
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)#均值
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev)#标准差
tf.summary.scalar('max', tf.reduce_max(var))#最大
tf.summary.scalar('min', tf.reduce_min(var))#最小
tf.summary.histogram('histogram', var)#绘制张量经过激活函数前后的变化
def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
# 为确保计算图中各个层的分组,给每一层添加一个name_scope
with tf.name_scope(layer_name):
# This Variable will hold the state of the weights for the layer
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights)
with tf.name_scope('biases'):
biases = bias_variable([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)
# Do not apply softmax activation yet, see below.
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)
with tf.name_scope('cross_entropy'):
# So here we use tf.nn.softmax_cross_entropy_with_logits on the
# raw outputs of the nn_layer above, and then average across
# the batch.
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)
# Merge all the summaries and write them out to /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
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()
# Train the model, and also write summaries.
# Every 10th step, measure test-set accuracy, and write test summaries
# All other steps, run train_step on training data, & add training summaries
def feed_dict(train):
"""Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
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}
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summaries and test-set accuracy
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: # Record train set summaries, and train
if i % 100 == 99: # Record execution stats
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)
print('Adding run metadata for', i)
else: # Record a summary
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(_):
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_Labels_Images',
help='Directory for storing input data')
parser.add_argument('--log_dir', type=str, default='logs/mnist_with_summaries',
help='Summaries log directory')
#/home/zhengxinxin/Desktop/PyCharm/Spark/SparkMNIST/logs/mnist_with_summaries
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
########################################################################################
训练的图结构:
HISTOGRAMS:
等等等。。。