[PYTHON] [Introduction to TensorBoard: image] TensorFlow Visualize image processing to deepen understanding
Accelerate your understanding of TensorFlow with TensorBoard
I wanted to check the process of convolution processing and pooling processing of TensorFlow, so I output it to TensorBoard. It is a memo of the image confirmation method at that time. As a premise, please refer to [[Introduction to TensorBoard] Visualize TensorFlow processing to deepen understanding] for basic usage. Environment: python3.5 tensorflow1.21
Reference link
-Installing TensorFlow on Windows was easy even for Python beginners -[Explanation for beginners] TensorFlow basic syntax and concept -[Explanation for beginners] TensorFlow tutorial MNIST (for beginners) -[Introduction to TensorBoard] Visualize TensorFlow processing to deepen understanding -[Introduction to TensorBoard: Projector] Make TensorFlow processing look cool -[Visualize TensorFlow Tutorial MNIST (for beginners) with TensorBoard] (http://qiita.com/FukuharaYohei/items/2834cc054a8b8884e150) -[Explanation for beginners] TensorFlow Tutorial Deep MNIST -TensorFlow API memo -Yuki Kashiwagi's facial features to understand TensorFlow [Part 1]
Simple logic of TensorBoard (Image)
View handwritten numeric characters (MNIST)
Let's write a code that just looks at the handwritten numeric characters (MNIST).
import tensorflow as tf
sess = tf.InteractiveSession()
#Read MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#TensorBoard information output directory
log_dir = '/tmp/tensorflow/test/tensorboard_image01'
#Delete the specified directory if it exists and recreate it
if tf.gfile.Exists(log_dir):
tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)
#Placeholder to put image data
x = tf.placeholder(tf.float32, shape=[None, 784])
#Convert images to 28x28 and output 10 to Tensorboard
_ = tf.summary.image('image', tf.reshape(x, [-1, 28, 28, 1]), 10)
merged = tf.summary.merge_all()
#Get minst image
batch = mnist.train.next_batch(10)
#Run
summary = sess.run(merged, feed_dict={x: batch[0]})
#Writer processing
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
summary_writer.add_summary(summary)
summary_writer.close()
Then launch Tensorboard. Since my environment is built with Anaconda, I first start Terminal from Anaconda Navigator.
Then, start Tensorbaord from Terminal by specifying the directory (the directory is stored in the variable log_dir in the Python program).
tensorboard --logdir=/tmp/tensorflow/mnist/logs/simple01
After booting, open http: // localhost: 6006 / in your browser and you will see the TensorBoard screen.
I get angry with "No scalar data was found", but this time there is no problem because scalar is not output and only Graph output is used. You can see the images by selecting "Images" from the menu on the screen.
View the image of the local file
Description
Reads and outputs a local file. For the local file reading method, I referred to the article "Preparation for reading the original data set".
import tensorflow as tf
sess = tf.InteractiveSession()
#TensorBoard information output directory
log_dir = '/tmp/tensorflow/test/tensorboard_image02'
#Delete the specified directory if it exists and recreate it
if tf.gfile.Exists(log_dir):
tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)
#File location("C:\\"Because the part is escaped"\"Note that there are two)
jpg = tf.read_file('C:\\Users\yohei.fukuhara\Pictures\Saved Pictures\Sample Pictures\Koala.jpg')
#JPEG file decoding(tf.image.decode_png and versatile tf.image.decode_There is also an image)
img_raw = tf.image.decode_jpeg(jpg, channels=3)
#Get image size(Can also be confirmed from the image file properties)
img_shape = tf.shape(img_raw)
#Output image to Tensorboard
_ = tf.summary.image('local', tf.reshape(img_raw, [-1, img_shape[0], img_shape[1], img_shape[2]]), 1)
merged = tf.summary.merge_all()
#Run
summary = sess.run(merged)
#Writer processing
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
summary_writer.add_summary(summary)
summary_writer.close()
The result will come out.
Tutorial for Experts Deep MNIST for Experts
It's finally the main subject. We will take a look at the process of convolution and pooling in the tutorial for experts. The code is below.
import tensorflow as tf
sess = tf.InteractiveSession()
#Read MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#TensorBoard information output directory
log_dir = '/tmp/tensorflow/mnist/logs/mnist_expert_images'
#Delete the specified directory if it exists and recreate it
if tf.gfile.Exists(log_dir):
tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)
# Input placeholders &Image conversion
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, shape=[None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, shape=[None, 10], name='y-input')
#Convert image to 28x28
x_image = tf.reshape(x, [-1, 28, 28, 1])
tf.summary.image('preprocess', x_image, 10)
#Function that processes variables and outputs TensorBoard
def variable_summaries(var):
#Variable Summary
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var) #Scalar output(average)
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) #Scalar output(standard deviation)
tf.summary.scalar('max', tf.reduce_max(var)) #Scalar output(Maximum value)
tf.summary.scalar('min', tf.reduce_min(var)) #Scalar output(minimum value)
tf.summary.histogram('histogram', var) #Histogram output
#Weighted value
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1) #Standard deviation 0.Normal distribution random number of 1
return tf.Variable(initial)
#Bias value
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape) #Initial value 0.1 constant
return tf.Variable(initial)
#Convolution process
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
# Max Pooling
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
#1st layer
with tf.name_scope('1st_layer'):
#1st convolution layer
with tf.name_scope('conv1_layer'):
with tf.name_scope('weight'):
W_conv1 = weight_variable([5, 5, 1, 32])
variable_summaries(W_conv1)
#Tensor[5,5,1,32]From[32,5,5,1]Permutation conversion and image output
tf.summary.image('filter', tf.transpose(W_conv1,perm=[3,0,1,2]), 10)
with tf.name_scope('bias'):
b_conv1 = bias_variable([32])
variable_summaries(b_conv1)
with tf.name_scope('activations'):
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
tf.summary.histogram('activations', h_conv1)
#Tensor[-1,28,28,32]From[-1,32,28,28]And permutation,[-1]When[-32]Merge and output image
tf.summary.image('convolved', tf.reshape(tf.transpose(h_conv1,perm=[0,3,1,2]),[-1,28,28,1]), 10)
#1st pooling layer
with tf.name_scope('pool1_layer'):
h_pool1 = max_pool_2x2(h_conv1)
#Tensor[-1,14,14,32]From[-1,32,14,14]And permutation,[-1]When[32]Merge and output image
tf.summary.image('pooled', tf.reshape(tf.transpose(h_pool1,perm=[0,3,1,2]),[-1,14,14,1]), 10)
#2nd layer
with tf.name_scope('2nd_layer'):
#2nd convolution layer
with tf.name_scope('conv2_layer'):
with tf.name_scope('weight'):
W_conv2 = weight_variable([5, 5, 32, 64])
variable_summaries(W_conv2)
#Tensor[5,5,32,64]From[32*64,5,5,1]Permutation conversion and image output
tf.summary.image('filter', tf.reshape(tf.transpose(W_conv2,perm=[2,3,0,1]),[-1,5,5,1]), 20)
with tf.name_scope('bias'):
b_conv2 = bias_variable([64])
variable_summaries(b_conv2)
with tf.name_scope('activations'):
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
tf.summary.histogram('activations', h_conv2)
#Tensor[-1,14,14,64]From[-1,64,14,14]And permutation,[-1]When[64]Merge and output image
tf.summary.image('convolved', tf.reshape(tf.transpose(h_conv2,perm=[0,3,1,2]),[-1,14,14,1]), 10)
#2nd pooling layer
with tf.name_scope('pool2_layer'):
h_pool2 = max_pool_2x2(h_conv2)
#Tensor[-1,7,7,64]From[-1,64,7,7]And permutation,[-1]When[64]Merge and output image
tf.summary.image('pooled', tf.reshape(tf.transpose(h_pool2,perm=[0,3,1,2]),[-1,7,7,1]), 10)
#Tightly coupled layer
with tf.name_scope('fc1_layer'):
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
with tf.name_scope('weight'):
W_fc1 = weight_variable([7 * 7 * 64, 1024])
variable_summaries(W_fc1)
with tf.name_scope('bias'):
b_fc1 = bias_variable([1024])
variable_summaries(b_fc1)
with tf.name_scope('activations'):
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
tf.summary.histogram('activations', h_fc1)
#Drop out
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.summary.scalar('dropout_keep_probability', keep_prob)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#Read layer
with tf.name_scope('fc2_layer'):
with tf.name_scope('weight'):
W_fc2 = weight_variable([1024, 10])
variable_summaries(W_fc2)
with tf.name_scope('bias'):
b_fc2 = bias_variable([10])
variable_summaries(b_fc2)
with tf.name_scope('preactivations'):
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
tf.summary.histogram('preactivations', y_conv)
#Cross entropy(Cross entropy)Calculation
with tf.name_scope('cross_entropy'):
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
tf.summary.scalar("cross_entropy", cross_entropy)
#Training
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#Correct answer rate calculation
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
#Output all Summary
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph) #Training data
test_writer = tf.summary.FileWriter(log_dir + '/test') #test data
#Initialization
tf.global_variables_initializer().run()
#Repeat training / test
for i in range(3000):
batch = mnist.train.next_batch(50)
#Training trace details every 100 times
if i % 100 == 0:
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, train_accuracy, _ = sess.run([merged, accuracy , train_step],
feed_dict={x: batch[0], y_:batch[1], keep_prob: 1.0},
options=run_options,
run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
print('step %d, training accuracy %g' % (i, train_accuracy))
#Test every 100 times
elif i % 100 == 99:
summary_test, train_accuracy = sess.run([merged, accuracy], feed_dict={x: mnist.test.images, y_:mnist.test.labels, keep_prob: 1.0})
test_writer.add_summary(summary_test, i)
#Training result writing
summary, _ = sess.run([merged, train_step], feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
train_writer.add_summary(summary, i)
#Final test result output
print('test accuracy %g' % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
#Writer closed
train_writer.close()
test_writer.close()
result It is grouped by name (input, 1st_layer, 2nd_layer). See also the article "[Explanation for Beginners] TensorFlow Tutorial Deep MNIST".
It is good to be able to output images according to the training steps.
Recommended Posts