Muutke küpsiste eelistusi

Computer Vision Using Deep Learning: Neural Network Architectures with Python and Keras 1st ed. [Pehme köide]

3.50/5 (4 hinnangut Goodreads-ist)
  • Formaat: Paperback / softback, 308 pages, kõrgus x laius: 235x155 mm, kaal: 510 g, 115 Illustrations, color; 36 Illustrations, black and white; XXI, 308 p. 151 illus., 115 illus. in color., 1 Paperback / softback
  • Ilmumisaeg: 15-Feb-2021
  • Kirjastus: APress
  • ISBN-10: 1484266153
  • ISBN-13: 9781484266151
Teised raamatud teemal:
  • Pehme köide
  • Hind: 53,33 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 62,74 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Computer Vision Using Deep Learning: Neural Network Architectures with Python and Keras 1st ed.Suurem pilt
  • Formaat: Paperback / softback, 308 pages, kõrgus x laius: 235x155 mm, kaal: 510 g, 115 Illustrations, color; 36 Illustrations, black and white; XXI, 308 p. 151 illus., 115 illus. in color., 1 Paperback / softback
  • Ilmumisaeg: 15-Feb-2021
  • Kirjastus: APress
  • ISBN-10: 1484266153
  • ISBN-13: 9781484266151
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781484266151.html
Organizations spend huge resources in developing software that can perform the way a human does. Image classification, object detection and tracking, pose estimation, facial recognition, and sentiment estimation all play a major role in solving computer vision problems. 

This book will bring into focus these and other deep learning architectures and techniques to help you create solutions using Keras and the TensorFlow library. You'll also review mutliple neural network architectures, including LeNet, AlexNet, VGG, Inception, R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, YOLO, and SqueezeNet and see how they work alongside Python code via best practices, tips, tricks, shortcuts, and pitfalls. All code snippets will be broken down and discussed thoroughly so you can implement the same principles in your respective environments.



Computer Vision Using Deep Learning offers a comprehensive yet succinct guide that stitches DL and CV together to automate operations, reduce human intervention, increase capability, and cut the costs. 



What You'll Learn











Examine deep learning code and concepts to apply guiding principals to your own projects Classify and evaluate various architectures to better understand your options in various use cases Go behind the scenes of basic deep learning functions to find out how they work





Who This Book Is For

Professional practitioners working in the fields of software engineering and data science. A working knowledge of Python is strongly recommended. Students and innovators working on advanced degrees in areas related to computer vision and Deep Learning.
About the Author xi
About the Technical Reviewer xiii
Acknowledgments xv
Introduction xvii
Foreword xix
Chapter 1 Introduction to Computer Vision and Deep Learning 1(40)
1.1 Technical requirements
2(1)
1.2 Image Processing using OpenCV
3(3)
1.2.1 Color detection using OpenCV
4(2)
1.3 Shape detection using OpenCV
6(6)
1.3.1 Face detection using OpenCV
9(3)
1.4 Fundamentals of Deep Learning
12(20)
1.4.1 The motivation behind Neural Network
14(1)
1.4.2 Layers in a Neural Network
15(1)
1.4.3 Neuron
16(1)
1.4.4 Hyperparameters
17(1)
1.4.5 Connections and weight of ANN
18(1)
1.4.6 Bias term
18(1)
1.4.7 Activation functions
19(6)
1.4.8 Learning rate
25(1)
1.4.9 Backpropagation
26(2)
1.4.10 Overfitting
28(1)
1.4.11 Gradient descent
29(2)
1.4.12 Loss functions
31(1)
1.5 How Deep Learning works?
32(6)
1.5.1 Popular Deep Learning libraries
36(2)
1.6 Summary
38(3)
1.6.1 Further readings
39(2)
Chapter 2 Nuts and Bolts of Deep Learning for Computer Vision 41(26)
2.1 Technical requirements
42(1)
2.2 Deep Learning using TensorFlow and Keras
42(1)
2.3 What is a tensor?
43(10)
2.3.1 What is a Convolutional Neural Network?
45(1)
2.3.2 What is convolution?
46(5)
2.3.3 What is a Pooling Layer?
51(1)
2.3.4 What is a Fully Connected Layer?
52(1)
2.4 Developing a DL solution using CNN
53(11)
2.5 Summary
64(3)
2.5.1 Further readings
66(1)
Chapter 3 Image Classification Using LeNet 67(36)
3.1 Technical requirements
68(1)
3.2 Deep Learning architectures
68(1)
3.3 LeNet architecture
69(1)
3.4 LeNet-1 architecture
70(1)
3.5 LeNet-4 architecture
71(1)
3.6 LeNet-5 architecture
72(3)
3.7 Boosted LeNet-4 architecture
75(1)
3.8 Creating image classification models using LeNet
76(1)
3.9 MNIST classification using LeNet
77(7)
3.10 German traffic sign identification using LeNet
84(16)
3.11 Summary
100(3)
3.11.1 Further readings
101(2)
Chapter 4 VGGNet and AlexNet Networks 103(38)
4.1 Technical requirements
104(1)
4.2 AlexNet and VGG Neural Networks
104(1)
4.3 What is AlexNet Neural Network?
105(2)
4.4 What is VGG Neural Network?
107(1)
4.5 VGG16 architecture
107(3)
4.6 Difference between VGG16 and VGG19
110(1)
4.7 Developing solutions using AlexNet and VGG
111(2)
4.8 Working on CIFAR-10 using AlexNet
113(15)
4.9 Working on CIFAR-10 using VGG
128(8)
4.10 Comparing AlexNet and VGG
136(1)
4.11 Working with CIFAR-100
137(1)
4.12 Summary
138(3)
4.12.1 Further readings
139(2)
Chapter 5 Object Detection Using Deep Learning 141(46)
5.1 Technical requirements
142(1)
5.2 Object Detection
142(4)
5.2.1 Object classification vs. object localization vs. object detection
143(1)
5.2.2 Use cases of Object Detection
144(2)
5.3 Object Detection methods
146(1)
5.4 Deep Learning frameworks for Object Detection
147(3)
5.4.1 Sliding window approach for Object Detection
148(2)
5.5 Bounding box approach
150(2)
5.6 Intersection over Union (IoU)
152(2)
5.7 Non-max suppression
154(1)
5.8 Anchor boxes
155(2)
5.9 Deep Learning architectures
157(3)
5.9.1 Region-based CNN (R-CNN)
157(3)
5.10 Fast R-CNN
160(2)
5.11 Faster R-CNN
162(3)
5.12 You Only Look Once (YOLO)
165(7)
5.12.1 Salient features of YOLO
166(1)
5.12.2 Loss function in YOLO
167(2)
5.12.3 YOLO architecture
169(3)
5.13 Single Shot MultiBox Detector (SSD)
172(5)
5.14 Transfer Learning
177(2)
5.15 Python implementation
179(3)
5.16 Summary
182(5)
5.16.1 Further readings
184(3)
Chapter 6 Face Recognition and Gesture Recognition 187(34)
6.1 Technical toolkit
188(1)
6.2 Face recognition
188(29)
6.2.1 Applications of face recognition
190(2)
6.2.2 Process of face recognition
192(2)
6.2.3 DeepFace solution by Facebook
194(5)
6.2.4 FaceNet for face recognition
199(7)
6.2.5 Python implementation using FaceNet
206(2)
6.2.6 Python solution for gesture recognition
208(9)
6.3 Summary
217(4)
6.3.1 Further readings
219(2)
Chapter 7 Video Analytics Using Deep Learning 221(36)
7.1 Technical toolkit
222(1)
7.2 Video processing
222(1)
7.3 Use cases of video analytics
223(2)
7.4 Vanishing gradient and exploding gradient problem
225(5)
7.5 ResNet architecture
230(13)
7.5.1 ResNet and skip connection
230(4)
7.5.2 Inception network
234(3)
7.5.3 GoogLeNet architecture
237(2)
7.5.4 Improvements in Inception v2
239(4)
7.6 Video analytics
243(1)
7.7 Python solution using ResNet and Inception v3
244(10)
7.8 Summary
254(3)
7.8.1 Further readings
255(2)
Chapter 8 End-to-End Model Development 257(40)
8.1 Technical requirements
258(1)
8.2 Deep Learning project requirements
258(4)
8.3 Deep Learning project process
262(1)
8.4 Business problem definition
263(7)
8.4.1 Face detection for surveillance
265(3)
8.4.2 Source data or data discovery phase
268(2)
8.5 Data ingestion or data management
270(2)
8.6 Data preparation and augmentation
272(7)
8.6.1 Image augmentation
274(5)
8.7 Deep Learning modeling process
279(10)
8.7.1 Transfer learning
282(2)
8.7.2 Common mistakes/challenges and boosting performance
284(5)
8.8 Model deployment and maintenance
289(5)
8.9 Summary
294(3)
8.9.1 Further readings
296(1)
References 297(6)
Major activation functions and layers used in CNN
297(1)
Google Colab
298(5)
Index 303
Vaibhav Verdhan is a seasoned data science professional with rich experience spanning across geographies and retail, telecom, manufacturing, health-care and utilities domain. He is a hands-on technical expert and has led multiple engagements in Machine Learning and Artificial Intelligence. He is a leading industry expert, is a regular speaker at conferences and meet-ups and mentors students and professionals. Currently he resides in Ireland and is working as a Principal Data Scientist.