Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай Deep Learning: Advanced Computer Vision, а также все другие курсы, прямо сейчас!
Премиум
  • Урок 1. 00:02:36
    Introduction
  • Урок 2. 00:06:50
    Outline and Perspective
  • Урок 3. 00:08:27
    Where to get the code
  • Урок 4. 00:11:56
    Anyone Can Succeed in this Course
  • Урок 5. 00:14:27
    What is Machine Learning?
  • Урок 6. 00:16:00
    Code Preparation (Classification Theory)
  • Урок 7. 00:04:39
    Beginner's Code Preamble
  • Урок 8. 00:08:41
    Classification Notebook
  • Урок 9. 00:07:19
    Code Preparation (Regression Theory)
  • Урок 10. 00:10:35
    Regression Notebook
  • Урок 11. 00:09:59
    The Neuron
  • Урок 12. 00:10:54
    How does a model "learn"?
  • Урок 13. 00:06:46
    Making Predictions
  • Урок 14. 00:04:28
    Saving and Loading a Model
  • Урок 15. 00:03:04
    Suggestion Box
  • Урок 16. 00:06:01
    Artificial Neural Networks Section Introduction
  • Урок 17. 00:09:41
    Forward Propagation
  • Урок 18. 00:09:44
    The Geometrical Picture
  • Урок 19. 00:17:19
    Activation Functions
  • Урок 20. 00:08:42
    Multiclass Classification
  • Урок 21. 00:12:37
    How to Represent Images
  • Урок 22. 00:12:43
    Code Preparation (ANN)
  • Урок 23. 00:08:37
    ANN for Image Classification
  • Урок 24. 00:11:06
    ANN for Regression
  • Урок 25. 00:16:39
    What is Convolution? (part 1)
  • Урок 26. 00:05:57
    What is Convolution? (part 2)
  • Урок 27. 00:06:42
    What is Convolution? (part 3)
  • Урок 28. 00:15:59
    Convolution on Color Images
  • Урок 29. 00:20:59
    CNN Architecture
  • Урок 30. 00:15:14
    CNN Code Preparation
  • Урок 31. 00:06:47
    CNN for Fashion MNIST
  • Урок 32. 00:04:29
    CNN for CIFAR-10
  • Урок 33. 00:08:52
    Data Augmentation
  • Урок 34. 00:05:15
    Batch Normalization
  • Урок 35. 00:10:23
    Improving CIFAR-10 Results
  • Урок 36. 00:03:05
    VGG Section Intro
  • Урок 37. 00:07:01
    What's so special about VGG?
  • Урок 38. 00:08:23
    Transfer Learning
  • Урок 39. 00:02:20
    Relationship to Greedy Layer-Wise Pretraining
  • Урок 40. 00:02:18
    Getting the data
  • Урок 41. 00:09:24
    Code pt 1
  • Урок 42. 00:03:42
    Code pt 2
  • Урок 43. 00:03:28
    Code pt 3
  • Урок 44. 00:01:49
    VGG Section Summary
  • Урок 45. 00:02:50
    ResNet Section Intro
  • Урок 46. 00:12:46
    ResNet Architecture
  • Урок 47. 00:02:26
    Building ResNet - Strategy
  • Урок 48. 00:05:17
    Uh-oh! What Happens if the Implementation Changes?
  • Урок 49. 00:03:35
    Building ResNet - Conv Block Details
  • Урок 50. 00:06:09
    Building ResNet - Conv Block Code
  • Урок 51. 00:01:24
    Building ResNet - Identity Block Details
  • Урок 52. 00:02:29
    Building ResNet - First Few Layers
  • Урок 53. 00:04:16
    Building ResNet - First Few Layers (Code)
  • Урок 54. 00:04:20
    Building ResNet - Putting it all together
  • Урок 55. 00:01:17
    Exercise: Apply ResNet
  • Урок 56. 00:02:40
    Applying ResNet
  • Урок 57. 00:04:04
    1x1 Convolutions
  • Урок 58. 00:06:48
    Optional: Inception
  • Урок 59. 00:04:14
    Different sized images using the same network
  • Урок 60. 00:02:28
    ResNet Section Summary
  • Урок 61. 00:05:05
    SSD Section Intro
  • Урок 62. 00:06:37
    Object Localization
  • Урок 63. 00:02:54
    What is Object Detection?
  • Урок 64. 00:08:41
    How would you find an object in an image?
  • Урок 65. 00:03:48
    The Problem of Scale
  • Урок 66. 00:03:53
    The Problem of Shape
  • Урок 67. 00:05:46
    2020 Update - More Fun and Excitement
  • Урок 68. 00:11:15
    Using Pretrained RetinaNet
  • Урок 69. 00:04:27
    RetinaNet with Custom Dataset (pt 1)
  • Урок 70. 00:09:21
    RetinaNet with Custom Dataset (pt 2)
  • Урок 71. 00:07:06
    RetinaNet with Custom Dataset (pt 3)
  • Урок 72. 00:05:07
    Optional: Intersection over Union & Non-max Suppression
  • Урок 73. 00:02:53
    SSD Section Summary
  • Урок 74. 00:02:53
    Style Transfer Section Intro
  • Урок 75. 00:11:24
    Style Transfer Theory
  • Урок 76. 00:08:03
    Optimizing the Loss
  • Урок 77. 00:07:47
    Code pt 1
  • Урок 78. 00:07:14
    Code pt 2
  • Урок 79. 00:03:51
    Code pt 3
  • Урок 80. 00:02:22
    Style Transfer Section Summary
  • Урок 81. 00:07:10
    Class Activation Maps (Theory)
  • Урок 82. 00:09:55
    Class Activation Maps (Code)
  • Урок 83. 00:15:52
    GAN Theory
  • Урок 84. 00:12:11
    GAN Code
  • Урок 85. 00:13:38
    Localization Introduction and Outline
  • Урок 86. 00:10:40
    Localization Code Outline (pt 1)
  • Урок 87. 00:09:11
    Localization Code (pt 1)
  • Урок 88. 00:04:53
    Localization Code Outline (pt 2)
  • Урок 89. 00:11:04
    Localization Code (pt 2)
  • Урок 90. 00:03:19
    Localization Code Outline (pt 3)
  • Урок 91. 00:04:17
    Localization Code (pt 3)
  • Урок 92. 00:03:20
    Localization Code Outline (pt 4)
  • Урок 93. 00:02:07
    Localization Code (pt 4)
  • Урок 94. 00:07:43
    Localization Code Outline (pt 5)
  • Урок 95. 00:08:40
    Localization Code (pt 5)
  • Урок 96. 00:07:07
    Localization Code Outline (pt 6)
  • Урок 97. 00:07:38
    Localization Code (pt 6)
  • Урок 98. 00:04:59
    Localization Code Outline (pt 7)
  • Урок 99. 00:12:08
    Localization Code (pt 7)
  • Урок 100. 00:07:28
    (Review) Tensorflow Basics
  • Урок 101. 00:09:44
    (Review) Tensorflow Neural Network in Code
  • Урок 102. 00:06:49
    (Review) Keras Discussion
  • Урок 103. 00:06:38
    (Review) Keras Neural Network in Code
  • Урок 104. 00:04:27
    (Review) Keras Functional API
  • Урок 105. 00:01:50
    (Review) How to easily convert Keras into Tensorflow 2.0 code
  • Урок 106. 00:20:21
    Windows-Focused Environment Setup 2018
  • Урок 107. 00:17:31
    How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
  • Урок 108. 00:15:55
    How to Code by Yourself (part 1)
  • Урок 109. 00:09:24
    How to Code by Yourself (part 2)
  • Урок 110. 00:12:30
    Proof that using Jupyter Notebook is the same as not using it
  • Урок 111. 00:04:39
    Python 2 vs Python 3
  • Урок 112. 00:10:25
    How to Succeed in this Course (Long Version)
  • Урок 113. 00:22:05
    Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
  • Урок 114. 00:11:20
    Machine Learning and AI Prerequisite Roadmap (pt 1)
  • Урок 115. 00:16:08
    Machine Learning and AI Prerequisite Roadmap (pt 2)
  • Урок 116. 00:02:49
    What is the Appendix?
  • Урок 117. 00:05:32
    BONUS: Where to get discount coupons and FREE deep learning material