Convolutional Neural Networks (CNN)

By Prof. Seungchul Lee
http://iai.postech.ac.kr/
Industrial AI Lab at POSTECH

Table of Contents

0. Video Lectures

%%html 
<center><iframe src="https://www.youtube.com/embed/oK3Q6yCsXAg?rel=0" 
width="560" height="315" frameborder="0" allowfullscreen></iframe></center>

%%html 
<center><iframe src="https://www.youtube.com/embed/RgsliaqKjRc?rel=0" 
width="560" height="315" frameborder="0" allowfullscreen></iframe></center>

%%html
<center><iframe src="https://www.youtube.com/embed/UyGy4eu1u90?end=728&rel=0" 
width="560" height="315" frameborder="0" allowfullscreen></iframe></center>

1. Convolution

1.1. 1D Convolution

1.2. Convolution on Image (= Convolution in 2D)

Filter (or Kernel)

• Modify or enhance an image by filtering
• Filter images to emphasize certain features or remove other features

• Filtering includes smoothing, sharpening and edge enhancement

• Discrete convolution can be viewed as element-wise multiplication by a matrix

How to find the right Kernels

• We learn many different kernels that make specific effect on images

• Let’s apply an opposite approach

• We are not designing the kernel, but are learning the kernel from data

• Can learn feature extractor from data using a deep learning framework

2. Convolutional Neural Networks (CNN)

2.1. Motivation: Learning Visual Features

The bird occupies a local area and looks the same in different parts of an image. We should construct neural networks which exploit these properties.

• ANN structure for object detecion in image

  • does not seem the best
  • did not make use of the fact that we are dealing with images
  • Spatial organization of the input is destroyed by flattening

• Locality: objects tend to have a local spatial support
  • fully and convolutionally connected layer $\rightarrow$ locally and convolutionally connected layer

- __Translation invariance__: object appearance is independent of location - Weight sharing: untis connected to different locations have the same weights - We are not designing the kernel, but are learning the kernel from data - _i.e._ We are learning visual feature extractor from data

2.2. Convolutional Operator

Convolution of CNN

• Local connectivity
• Weight sharing

• Typically have sparse interactions

• Convolutional Neural Networks

  • Simply neural networks that use the convolution in place of general matrix multiplication in at least one of their layers

• Multiple channels

• Multiple kernels

2.3 Stride and Padding

• Strides: increment step size for the convolution operator
  • Reduces the size of the output map

• No stride and no padding

• Stride example with kernel size 3×3 and a stride of 2

• Padding: artificially fill borders of image
  • Useful to keep spatial dimension constant across filters
  • Useful with strides and large receptive fields
  • Usually fill with 0s

2.4. Nonlinear Activation Function

2.5. Pooling

• Compute a maximum value in a sliding window (max pooling)
  • Reduce spatial resolution for faster computation
  • Achieve invariance to any permutation inside one of the cell

• Pooling size : $2\times2$ for example

2.6. CNN for Classification

• CONV and POOL layers output high-level features of input
• Fully connected layer uses these features for classifying input image
• Express output as probability of image belonging to a particular class

3. Lab: CNN with TensorFlow (MNIST)

• MNIST example
• To classify handwritten digits

3.1. Training

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

mnist = tf.keras.datasets.mnist

(train_x, train_y), (test_x, test_y) = mnist.load_data()

train_x, test_x = train_x/255.0, test_x/255.0

train_x = train_x.reshape((train_x.shape[0], 28, 28, 1))
test_x = test_x.reshape((test_x.shape[0], 28, 28, 1))

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters = 32, 
                           kernel_size = (3,3), 
                           activation = 'relu',
                           padding = 'SAME',
                           input_shape = (28, 28, 1)),
    
    tf.keras.layers.MaxPool2D((2,2)),
    
    tf.keras.layers.Conv2D(filters = 64, 
                           kernel_size = (3,3), 
                           activation = 'relu',
                           padding = 'SAME',
                           input_shape = (14, 14, 32)),
    
    tf.keras.layers.MaxPool2D((2,2)),
    
    tf.keras.layers.Flatten(),
    
    tf.keras.layers.Dense(units = 128, activation = 'relu'),
    
    tf.keras.layers.Dense(units = 10, activation = 'softmax')
])

model.compile(optimizer = 'adam',
              loss = 'sparse_categorical_crossentropy',
              metrics = 'accuracy')

model.fit(train_x, train_y, batch_size = 50, epochs = 3)

Epoch 1/3
1200/1200 [==============================] - 46s 36ms/step - loss: 0.1394 - accuracy: 0.95720s - l
Epoch 2/3
1200/1200 [==============================] - 40s 33ms/step - loss: 0.0436 - accuracy: 0.9868
Epoch 3/3
1200/1200 [==============================] - 42s 35ms/step - loss: 0.0294 - accuracy: 0.9904

<tensorflow.python.keras.callbacks.History at 0x29c84722d68>

3.2. Testing or Evaluating

test_loss, test_acc = model.evaluate(test_x, test_y)

313/313 [==============================] - 3s 9ms/step - loss: 0.0318 - accuracy: 0.9894

test_img = test_x[[1495]]

predict = model.predict(test_img)
mypred = np.argmax(predict, axis = 1)

plt.figure(figsize = (12,5))

plt.subplot(1,2,1)
plt.imshow(test_img.reshape(28, 28), 'gray')
plt.axis('off')
plt.subplot(1,2,2)
plt.stem(predict[0])
plt.show()

print('Prediction : {}'.format(mypred[0]))

Prediction : 3

4. Lab: CNN with Tensorflow (Steel Surface Defects)

• NEU steel surface defects example
• To classify defects images into 6 classes

Download NEU steel surface defects images and labels

• NEU train images
• NEU train labels
• NEU test images
• NEU test labels

4.1. Training

train_x = np.load('./data_files/NEU_train_imgs.npy')
train_y = np.load('./data_files/NEU_train_labels.npy')

test_x = np.load('./data_files/NEU_test_imgs.npy')
test_y = np.load('./data_files/NEU_test_labels.npy')

print(train_x.shape)
print(train_y.shape)

(1500, 200, 200, 1)
(1500,)

print(test_x.shape)
print(test_y.shape)

(300, 200, 200, 1)
(300,)

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters = 32, 
                           kernel_size = (3,3), 
                           activation = 'relu',
                           padding = 'SAME',
                           input_shape = (200, 200, 1)),
    
    tf.keras.layers.MaxPool2D((2,2)),
    
    tf.keras.layers.Conv2D(filters = 64, 
                           kernel_size = (3,3), 
                           activation = 'relu',
                           padding = 'SAME',
                           input_shape = (100, 100, 32)),
    
    tf.keras.layers.MaxPool2D((2,2)),
    
    tf.keras.layers.Conv2D(filters = 128, 
                           kernel_size = (3,3), 
                           activation = 'relu',
                           padding = 'SAME',
                           input_shape = (50, 50, 64)),
    
    tf.keras.layers.MaxPool2D((2,2)),
    
    tf.keras.layers.Flatten(),    
    
    tf.keras.layers.Dense(units = 128, activation = 'relu'),    
    
    tf.keras.layers.Dense(units = 6, activation = 'softmax')
])

model.compile(optimizer = 'adam',
              loss = 'sparse_categorical_crossentropy',
              metrics = 'accuracy')

model.fit(train_x, train_y, batch_size = 50, epochs = 4)

Epoch 1/4
30/30 [==============================] - 48s 2s/step - loss: 1.8941 - accuracy: 0.2180
Epoch 2/4
30/30 [==============================] - 46s 2s/step - loss: 1.1320 - accuracy: 0.5267
Epoch 3/4
30/30 [==============================] - 45s 2s/step - loss: 0.8194 - accuracy: 0.6733
Epoch 4/4
30/30 [==============================] - 45s 2s/step - loss: 0.5473 - accuracy: 0.8000

<tensorflow.python.keras.callbacks.History at 0x29c8b7eb898>

4.2. Testing or Evaluating

test_loss, test_acc = model.evaluate(test_x, test_y)

10/10 [==============================] - 2s 200ms/step - loss: 0.5172 - accuracy: 0.8400

name = ['scratches', 'rolled-in scale', 'pitted surface', 'patches', 'inclusion', 'crazing']

idx = np.random.choice(test_x.shape[0], 1)
test_img = test_x[idx]
test_label = test_y[idx]

predict = model.predict(test_img)
mypred = np.argmax(predict, axis = 1)

plt.figure(figsize = (12,5))
plt.subplot(1,2,1)
plt.imshow(test_img.reshape(200, 200), 'gray')
plt.axis('off')
plt.subplot(1,2,2)
plt.stem(predict[0])
plt.show()

print('Prediction : {}'.format(name[mypred[0]]))
print('True Label : {}'.format(name[test_label[0]]))

Prediction : pitted surface
True Label : pitted surface

%%javascript
$.getScript('https://kmahelona.github.io/ipython_notebook_goodies/ipython_notebook_toc.js')