前言
本文基于TensorFlow官网How-Tos的Visualizing Learning和Graph Visualization写成。
TensorBoard是TensorFlow自带的一个可视化工具。本文在学习笔记（4）的基础上修改少量代码，以探索TensorBoard的使用方法。
代码
import gzip
import struct
import numpy
as np
from sklearn.linear_model
import LogisticRegression
from sklearn
import preprocessing
from sklearn.metrics
import accuracy_score
import tensorflow
as tf
def read_image(file_name):
with gzip.open(file_name,
'rb')
as f:
buf = f.read()
index =
0
magic, images, rows, columns = struct.unpack_from(
'>IIII' , buf , index)
index += struct.calcsize(
'>IIII')
image_size =
'>' + str(images*rows*columns) +
'B'
ims = struct.unpack_from(image_size, buf, index)
im_array = np.array(ims).reshape(images, rows, columns)
return im_array
def read_label(file_name):
with gzip.open(file_name,
'rb')
as f:
buf = f.read()
index =
0
magic, labels = struct.unpack_from(
'>II', buf, index)
index += struct.calcsize(
'>II')
label_size =
'>' + str(labels) +
'B'
labels = struct.unpack_from(label_size, buf, index)
label_array = np.array(labels)
return label_array
print "Start processing MNIST handwritten digits data..."
train_x_data = read_image(
"MNIST_data/train-images-idx3-ubyte.gz")
train_x_data = train_x_data.reshape(train_x_data.shape[
0], -
1).astype(np.float32)
train_y_data = read_label(
"MNIST_data/train-labels-idx1-ubyte.gz")
test_x_data = read_image(
"MNIST_data/t10k-images-idx3-ubyte.gz")
test_x_data = test_x_data.reshape(test_x_data.shape[
0], -
1).astype(np.float32)
test_y_data = read_label(
"MNIST_data/t10k-labels-idx1-ubyte.gz")
train_x_minmax = train_x_data /
255.0
test_x_minmax = test_x_data /
255.0
eval_sklearn =
False
if eval_sklearn:
print "Start evaluating softmax regression model by sklearn..."
reg = LogisticRegression(solver=
"lbfgs", multi_class=
"multinomial")
reg.fit(train_x_minmax, train_y_data)
np.savetxt(
'coef_softmax_sklearn.txt', reg.coef_, fmt=
'%.6f')
test_y_predict = reg.predict(test_x_minmax)
print "Accuracy of test set: %f" % accuracy_score(test_y_data, test_y_predict)
eval_tensorflow =
True
batch_gradient =
False
def variable_summaries(var):
with tf.name_scope(
'summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar(
'mean', mean)
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))
tf.summary.histogram(
'histogram', var)
if eval_tensorflow:
print "Start evaluating softmax regression model by tensorflow..."
lb = preprocessing.LabelBinarizer()
lb.fit(train_y_data)
train_y_data_trans = lb.transform(train_y_data)
test_y_data_trans = lb.transform(test_y_data)
x = tf.placeholder(tf.float32, [
None,
784])
with tf.name_scope(
'weights'):
W = tf.Variable(tf.zeros([
784,
10]))
variable_summaries(W)
with tf.name_scope(
'biases'):
b = tf.Variable(tf.zeros([
10]))
variable_summaries(b)
with tf.name_scope(
'Wx_plus_b'):
V = tf.matmul(x, W) + b
tf.summary.histogram(
'pre_activations', V)
with tf.name_scope(
'softmax'):
y = tf.nn.softmax(V)
tf.summary.histogram(
'activations', y)
y_ = tf.placeholder(tf.float32, [
None,
10])
with tf.name_scope(
'cross_entropy'):
loss = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[
1]))
tf.summary.scalar(
'cross_entropy', loss)
with tf.name_scope(
'train'):
optimizer = tf.train.GradientDescentOptimizer(
0.5)
train = optimizer.minimize(loss)
with tf.name_scope(
'evaluate'):
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)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(
'log/train', sess.graph)
test_writer = tf.summary.FileWriter(
'log/test')
if batch_gradient:
for step
in range(
300):
sess.run(train, feed_dict={x: train_x_minmax, y_: train_y_data_trans})
if step %
10 ==
0:
print "Batch Gradient Descent processing step %d" % step
print "Finally we got the estimated results, take such a long time..."
else:
for step
in range(
1000):
if step %
10 ==
0:
summary, acc = sess.run([merged, accuracy], feed_dict={x: test_x_minmax, y_: test_y_data_trans})
test_writer.add_summary(summary, step)
print "Stochastic Gradient Descent processing step %d accuracy=%.2f" % (step, acc)
else:
sample_index = np.random.choice(train_x_minmax.shape[
0],
100)
batch_xs = train_x_minmax[sample_index, :]
batch_ys = train_y_data_trans[sample_index, :]
summary, _ = sess.run([merged, train], feed_dict={x: batch_xs, y_: batch_ys})
train_writer.add_summary(summary, step)
np.savetxt(
'coef_softmax_tf.txt', np.transpose(sess.run(W)), fmt=
'%.6f')
print "Accuracy of test set: %f" % sess.run(accuracy, feed_dict={x: test_x_minmax, y_: test_y_data_trans})
思考
主要修改点有：
Summary：所有需要在TensorBoard上展示的统计结果。
tf.name_scope()：为Graph中的Tensor添加层级，TensorBoard会按照代码指定的层级进行展示，初始状态下只绘制最高层级的效果，点击后可展开层级看到下一层的细节。
tf.summary.scalar()：添加标量统计结果。
tf.summary.histogram()：添加任意shape的Tensor，统计这个Tensor的取值分布。
tf.summary.merge_all()：添加一个操作，代表执行所有summary操作，这样可以避免人工执行每一个summary op。
tf.summary.FileWrite：用于将Summary写入磁盘，需要制定存储路径logdir，如果传递了Graph对象，则在Graph Visualization会显示Tensor Shape Information。执行summary op后，将返回结果传递给add_summary()方法即可。
效果
Visualizing Learning
Scalar
Histogram
首先是Distribution，显示取值范围：
更细节的取值概率信息在Historgram里，如下：
Graph Visualization
双击train后，可查看下一层级的详细信息：
