GCP with Tensorboard for Softmax Visualization

by allenlu2007

Excellent Reference:


前文 (Tensorflow ABC) 提到 TensorFlow 的兩個好處是: (1) 提供 visualization tool (Tensor Board) 對於 debug 和理解 neural network behavior 非常重要。(2) 提供 google cloud platform (GCP) with built-in tensorflow software and tools, 可以做 large scale training and testing.  同樣非常重要。

本文主要討論 tensorboard 的使用方法,特別是在 GCP 上使用。

先說結論:在 caffe 的年代,TensorBoard 可能是唯一的 machine learning/deep learning visualization 工具。但目前有很多的 visualization tools.  例如 matlab, jupyter notebook+python plotting tools (matplotlib, pandas, etc.), 還有特別針對 deep learning visualization tool, 例如 deep dream.


Step 1: 在 GCP cloud shell 上用 python 執行 tensorflow.  同樣用 softmax classifer 作為例子。

tb.py (tensorboard example) code 如 hyperlink 或附件。


$ python tb.py



Step 2: 在 GCP cloud shell 執行 tensorboard.  注意要改 port from 6006 -> 8080. 

$ tensorboard –logdir=/tmp/tensorflow_logs –port=8080

Launch Preview on port 8080!!






Graph and Loss visualization using Tensorboard.
This example is using the MNIST database of handwritten digits

Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/

from __future__ import print_function

import tensorflow as tf

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 25
batch_size = 100
display_step = 1
logs_path = '/tmp/tensorflow_logs/example'

# tf Graph Input
# mnist data image of shape 28*28=784
x = tf.placeholder(tf.float32, [None, 784], name='InputData')
# 0-9 digits recognition => 10 classes
y = tf.placeholder(tf.float32, [None, 10], name='LabelData')

# Set model weights
W = tf.Variable(tf.zeros([784, 10]), name='Weights')
b = tf.Variable(tf.zeros([10]), name='Bias')

# Construct model and encapsulating all ops into scopes, making
# Tensorboard's Graph visualization more convenient
with tf.name_scope('Model'):
    # Model
    pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax
with tf.name_scope('Loss'):
    # Minimize error using cross entropy
    cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))
with tf.name_scope('SGD'):
    # Gradient Descent
    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
with tf.name_scope('Accuracy'):
    # Accuracy
    acc = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    acc = tf.reduce_mean(tf.cast(acc, tf.float32))

# Initializing the variables
init = tf.global_variables_initializer()

# Create a summary to monitor cost tensor
tf.summary.scalar("loss", cost)
# Create a summary to monitor accuracy tensor
tf.summary.scalar("accuracy", acc)
# Merge all summaries into a single op
merged_summary_op = tf.summary.merge_all()

# Launch the graph
with tf.Session() as sess:

    # op to write logs to Tensorboard
    summary_writer = tf.summary.FileWriter(logs_path, graph=tf.get_default_graph())

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop), cost op (to get loss value)
            # and summary nodes
            _, c, summary = sess.run([optimizer, cost, merged_summary_op],
                                     feed_dict={x: batch_xs, y: batch_ys})
            # Write logs at every iteration
            summary_writer.add_summary(summary, epoch * total_batch + i)
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # Test model
    # Calculate accuracy
    print("Accuracy:", acc.eval({x: mnist.test.images, y: mnist.test.labels}))

    print("Run the command line:\n" \
          "--> tensorboard --logdir=/tmp/tensorflow_logs " \
          "\nThen open into your web browser")