Beginning TensorFlow at 2nd day

I started to learn Machine Learning and TensorFlow at 2nd day.
This article shows TensorFlow tutorial codes and some description for ML term.

🐯 Basic Usage

To use TensorFlow you need to understand how TensorFlow

• Represents computations as graphs
• Executes graphs in the context of Sessions
• Represents data as tensors
• Maintains state with Variables

🚕 Terms

• ops (short for operations) : Nodes in the graph
• Tensors : Data structure as an n-dimensional array or list having Rank, Shape and Type
• Tensor : A typed multi-dimensional array
• Construction phase : Assembling a graph to represent and train a neural network
• Execution phase : Using a session to execute repeatedly a set of training ops in the graph

🎃 Building the graph

import tensorflow as tf

# Create a Constant op that produces a 1x2 matrix.  The op is
# added as a node to the default graph.
#
# The value returned by the constructor represents the output
# of the Constant op.
matrix1 = tf.constant([[3., 3.]])

# Create another Constant that produces a 2x1 matrix.
matrix2 = tf.constant([[2.],[2.]])

# Create a Matmul op that takes 'matrix1' and 'matrix2' as inputs.
# The returned value, 'product', represents the result of the matrix
# multiplication.
product = tf.matmul(matrix1, matrix2)

The default graph now has three nodes: two constant() ops and one matmul() op.

😸 Launching the graph in a session

# Launch the default graph.
sess = tf.Session()

# To run the matmul op we call the session 'run()' method, passing 'product'
# which represents the output of the matmul op.  This indicates to the call
# that we want to get the output of the matmul op back.
#
# All inputs needed by the op are run automatically by the session.  They
# typically are run in parallel.
#
# The call 'run(product)' thus causes the execution of three ops in the
# graph: the two constants and matmul.
#
# The output of the op is returned in 'result' as a numpy `ndarray` object.
result = sess.run(product)
print(result)
# ==> [[ 12.]]

# Close the Session when we're done.
sess.close()

😀 Interactive Usage

# Enter an interactive TensorFlow Session.
import tensorflow as tf
sess = tf.InteractiveSession()

x = tf.Variable([1.0, 2.0])
a = tf.constant([3.0, 3.0])

# Initialize 'x' using the run() method of its initializer op.
x.initializer.run()

# Add an op to subtract 'a' from 'x'.  Run it and print the result
sub = tf.sub(x, a)
print(sub.eval())
# ==> [-2. -1.]

# Close the Session when we're done.
sess.close()

🍄 Variables

Variables maintain state across executions of the graph

import tensorflow as tf

# Create a Variable, that will be initialized to the scalar value 0.
state = tf.Variable(0, name="counter")

# Create an Op to add one to `state`.

one = tf.constant(1)
new_value = tf.add(state, one)
update = tf.assign(state, new_value)

# Variables must be initialized by running an `init` Op after having
# launched the graph.  We first have to add the `init` Op to the graph.
init_op = tf.initialize_all_variables()

# Launch the graph and run the ops.
with tf.Session() as sess:
  # Run the 'init' op
  sess.run(init_op)
  # Print the initial value of 'state'
  print(sess.run(state))
  # Run the op that updates 'state' and print 'state'.
  for _ in range(3):
    sess.run(update)
    print(sess.run(state))

# output:

# 0
# 1
# 2
# 3

🐞 Fetches

import tensorflow as tf

input1 = tf.constant([3.0])
input2 = tf.constant([2.0])
input3 = tf.constant([5.0])
intermed = tf.add(input2, input3)
mul = tf.mul(input1, intermed)

with tf.Session() as sess:
  result = sess.run([mul, intermed])
  print(result)

# output:
# [array([ 21.], dtype=float32), array([ 7.], dtype=float32)]

🍣 Feeds

import tensorflow as tf

input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.mul(input1, input2)

with tf.Session() as sess:
  print(sess.run([output], feed_dict={input1:[7.], input2:[2.]}))

# output:
# [array([ 14.], dtype=float32)]

🐹 Tensor Ranks, Shapes, and Types

Rank

Examples of Rank are as follows:

• Rank 0 : Scalar (magnitude only) : s = 483
• Rank 1 : Vector (magnitude and direction) : v = [1.1, 2.2, 3.3]
• Rank 2 : Matrix (table of numbers) : m = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
• Rank 3 : 3-Tensor (cube of numbers) : t = [[[2], [4], [6]], [[8], [10], [12]], [[14], [16], [18]]]
• Rank n : n-Tensor (you get the idea) : ….

Shape

The following list shows how these relate to one another:

• Rank 0 : Shape [] : Dimension number 0-D : A 0-D tensor. A scalar
• Rank 1 : Shape [D0] : Dimension number 1-D : A 1-D tensor with shape [5]
• Rank 2 : Shape [D0,D1] : Dimension number 2-D : A 2-D tensor with shape [3,4]
• Rank 3 : Shape [D0,D1,D2] : Dimension number 3-D : A 3-D tensor with shape [1,4,3]
• Rank n : Shape [D0,D1,…,D(n-1)] : Dimension number n-D : A tensor with shape [D0,D1,D(n-1)]

Shapes can be represented via Python lists/tuples of inits.

Data types

There are folloing data types to tensor:

• DT_FLOAT / tf.float32 / 32 bits floating point.
• DT_DOUBLE / tf.float64 / 64 bits floating point.
• DT_INT8 / tf.int8 / 8 bits signed integer.
• DT_INT16 / tf.int16 / 16 bits signed integer.
• DT_INT32 / tf.int32 / 32 bits signed integer.
• DT_INT64 / tf.int64 / 64 bits signed integer.
• DT_UINT8 / tf.uint8 / 8 bits unsigned integer.
• DT_STRING / tf.string / Variable length byte arrays. Each element of a Tensor is a byte array.
• DT_BOOL / tf.bool / Boolean.
• DT_COMPLEX64 / tf.complex64 / Complex number made of two 32 bits floating points: real and imaginary parts.
• DT_COMPLEX128 / tf.complex128 / Complex number made of two 64 bits floating points: real and imaginary parts.
• DT_QINT8 / tf.qint8 / 8 bits signed integer used in quantized Ops.
• DT_QINT32 / tf.qint32 / 32 bits signed integer used in quantized Ops.
• DT_QUINT8 / tf.quint8 / 8 bits unsigned integer used in quantized Ops.

🏈 Introduction to Machine Learning Theory

Type

Supervised machine learning

The program is “trained” on a pre-defined set of “training examples”,
which then caficiltates its ability to reach an accurate conclusion when given new data.

Unsupervised machine learning

The program is vien a bunch of data and must find patterns and relationships therein.

😼 Liner Regression

# A linear regression learning algorithm example using TensorFlow library.

import tensorflow as tf
import numpy
import matplotlib.pyplot as plt
rng = numpy.random

# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50

# Training Data
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
                         7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
                         2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape[0]

# tf Graph Input
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# Construct a linear model
pred = tf.add(tf.mul(X, W), b)

# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)

# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.initialize_all_variables()

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

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        #Display logs per epoch step
        if (epoch+1) % display_step == 0:
            c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
                "W=", sess.run(W), "b=", sess.run(b))

    print("Optimization Finished!")
    training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
    print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

    #Graphic display
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()

👽 tf.contrib.learn Quickstart

import tensorflow as tf
import numpy as np

# Data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TEST = "iris_test.csv"

# Load datasets.
training_set = tf.contrib.learn.datasets.base.load_csv(filename=IRIS_TRAINING, target_dtype=np.int)
test_set = tf.contrib.learn.datasets.base.load_csv(filename=IRIS_TEST, target_dtype=np.int)

# set variable
x_train, y_train = training_set.data, training_set.target
x_test, y_test = test_set.data, test_set.target

# Build 3 layer DNN with 10, 20, 10 units respectively.
classifier = tf.contrib.learn.DNNClassifier(hidden_units=[10, 40, 10], n_classes=3)

# Fit model.
classifier.fit(x=x_train, y=y_train, steps=200)

# Evaluate accuracy.
accuracy_score = classifier.evaluate(x=x_test, y=y_test)["accuracy"]
print('Accuracy: {0:f}'.format(accuracy_score))

# Classify two new flower samples.
new_samples = np.array(
    [[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=float)
y = classifier.predict(new_samples)
print ('Predictions: {}'.format(str(y)))

😎 Special Thanks

• A Neural Network Playground
• Gradient descent - Wikipedia

---

🐠 Sample Code

morizyun/tensorflow_tutorial

🖥 Recommended VPS Service

VULTR provides high performance cloud compute environment for you. Vultr has 15 data-centers strategically placed around the globe, you can use a VPS with 512 MB memory for just $ 2.5 / month ($ 0.004 / hour). In addition, Vultr is up to 4 times faster than the competition, so please check it => Check Benchmark Results!!