Linear Regression
Gradient Descent Solution
(Iterative Solution)
Linear Regression: Gradient
Descent Solution
Linear Regression: Gradient
Descent Solution
TensorFlow
from Google
Deep Learning
Most Common Frameworks
50,000+ binary installs in 72 hours, 500,000+ since November, 2015
Deep Learning
Most Common Frameworks
Deep Learning
Most Common Frameworks
Mobile App using TensorFlow
(Signs Translation)
Mobile App using TensorFlow
(Language Translation)
Google Cloud
Data Center as a Computer
Google Cloud
Data Center as a Computer
Google Cloud
Data Center as a Computer
TensorFlow architecture
TensorFlow basic concepts
A TensorFlow computation is described by a directed
graph , which is composed of a set of nodes
● Library user construct a computational graph using one
of the supported frontend languages (C++ or Python)
● In a TensorFlow graph, each node has zero or more
inputs and zero or more outputs, and represents the
instantiation of an operation
● Values that flow along normal edges in the graph
(from outputs to inputs) are tensors - arbitrary
dimensionality arrays where the underlying element type is
specified or inferred at graph-construction time
● Special edges, called control dependencies , can also
exist in the graph
●
Tensorflow Operation types
Hello World
Tensorflow
import tensorflow as tf
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
input3 = tf.constant(5.0)
add_res = tf.add(input2, input3)
mul = tf.mul(input1, add_res)
with tf.Session() as sess:
result = sess.run(mul,feed_dict={input1:[3.0],input2:[2.0]})
print(result)
Linear Regression
Using
TensorFlow
1-D Data Example
Data Preparation
import numpy as np
num_of_points = 100 #Generate 100 Data Points
points = []
for i in range(num_of_points):
x1= np.random.normal(0.0, 0.55)
y1= x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.01)
points.append([x1, y1])
x_data = [v[0] for v in points]
y_data = [v[1] for v in points]
Draw Data
import matplotlib.pyplot as plt
plt.plot(x_data, y_data, 'ro', label='Original data')
plt.legend()
plt.show()
Original Data
Variables and Nodes
Preparation
import tensorflow as tf
#initialize weights "W and bias "b"
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = W * x_data + b
#Define Loss function as Mean of Squared Error
loss = tf.reduce_mean(tf.square(y - y_data))
#Create Optimizer class to minimize Losses
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
#initialize TensorFlow Variables (always)
init = tf.global_variables_initializer()
Execute TensorFlow Graph
#Start TensorFlow Session and carryout Variable initialization
sess = tf.Session()
sess.run(init)
#Carryout 16 Iterations
for step in range(16):
sess.run(train)
#Draw Original Data
plt.plot(x_data, y_data, 'ro')
#Draw Predicted data (using calculated weight and bias after training
plt.plot(x_data, sess.run(W) * x_data + sess.run(b))
plt.xlabel('x')
plt.xlim(-2, 2)
plt.ylim(0.1, 0.6)
plt.ylabel('y')
plt.legend()
plt.show()
# print updated weights, bias, and Loss value after current training iteration
print(step, sess.run(W), sess.run(b),sess.run(loss))
Iteration 1
Iteration 2
Iteration 3
Iteration 4
Iteration 5
Iteration 6
Iteration 7
Iteration 8
Iteration 9
Iteration 10
Iteration 11
Iteration 12
Iteration 13
Iteration 14
Iteration 15
Iteration 16
Updated Weights and
Calculated Loss
2-D Data Example
Data Preparation
import numpy as np
#Prepare Random Data set (Linear + Random Noise)
num_of_points = 100 #1000
points = []
for i in range(num_of_points):
x1= np.random.normal(0.0, 0.55)
x2= np.random.normal(0.0, 0.55)
y1= x1 * 0.1 + x2 * 0.2 + 0.3 + np.random.normal(0.0, 0.01)
points.append([x1,x2, y1])
x1_data = [v[0] for v in points]
x2_data = [v[1] for v in points]
y_data = [v[2] for v in points]
Draw Data
#Draw Data Set as 3-D
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
from matplotlib.ticker import LinearLocator, FormatStrFormatter
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(x1_data, x2_data, y_data, c='r', marker="o")
plt.legend()
plt.show()
Draw Data
Variables and Nodes
Preparation
import tensorflow as tf
#initialize weights "W and bias "b"
W1 = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
W2 = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = W1 * x1_data + W2 * x2_data + b
#Define Loss function as Mean of Squared Error
loss = tf.reduce_mean(tf.square(y - y_data))
#Create Optimizer to minimize Losses
optimizer = tf.train.GradientDescentOptimizer(0.9)
train = optimizer.minimize(loss)
#initialize TensorFlow Variables (always)
init = tf.global_variables_initializer()
Execute TensorFlow Graph
#Start TensorFlow Session and carryout Variable initialization
sess = tf.Session()
sess.run(init)
#Carryout 24 Iterations
#
#
#
# { Continue in Next Slide }
Execute TensorFlow Graph
#Carryout 24 Iterations
for step in range(24):
sess.run(train)
#Draw Original Data
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(x1_data, x2_data, y_data, c='r', marker="o")
#Draw Mesh Grid (XX,YY) --> claculated regression surface
XX = np.arange(-1, 1, 0.1)
YY = np.arange(-1, 1, 0.1)
XY, YY = np.meshgrid(XX, YY)
ZZ=sess.run(W1) * XX + sess.run(W2) * YY + sess.run(b)
ax.plot_surface(XX, YY, ZZ, cmap=cm.coolwarm,linewidth=0, antialiased=False)
#Draw Calculated Points corresponding to Original Data Points
ax.scatter(x1_data, x2_data, sess.run(W1) * x1_data + sess.run(W2) * x2_data
+ sess.run(b), c='b', marker="^")
plt.legend()
plt.show()
# print updated weights, bias, and Loss value after current training iteration
print(step+1, sess.run(W1), sess.run(W2) , sess.run(b),sess.run(loss))
Iteration 1
Iteration 2
Iteration 3
Iteration 4
Iteration 5
Iteration 6
Iteration 7
Iteration 8
Iteration 9
Iteration 10
Iteration 11
Iteration 12
Iteration 13
Iteration 14
Iteration 15
Iteration 16
Iteration 17
Iteration 18
Iteration 19
Iteration 20
Updated Weights and
Calculated Loss
