2_0. Welcome and what is deep learning.zh_en
3_1. Why use machine-deep learning.zh_en
4_2. The number one rule of ML.zh_en
5_3. Machine learning vs deep learning.zh_en
6_4. Anatomy of neural networks.zh_en
7_5. Different learning paradigms.zh_en
8_6. What can deep learning be used for.zh_en
9_7. What is-why PyTorch.zh_en
10_8. What are tensors.zh_en
12_10. How to (and how not to) approach this cours
13_11. Important resources.zh_en
14_12. Getting setup.zh_en
15.13. Introduction to tensors.zh_en(Av1001277993,P15)
16.14. Creating tensors.zh_en(Av1001277993,P16)
17.17. Tensor datatypes.zh_en(Av1001277993,P17)
18.18. Tensor attributes (information ab(Av1001277993,P18)
19.19. Manipulating tensors.zh_en(Av1001277993,P19)
20.20. Matrix multiplication.zh_en(Av1001277993,P20)
21.23. Finding the min, max, mean and su(Av1001277993,P21)
22.25. Reshaping, viewing and stacking.z(Av1001277993,P22)
23.26. Squeezing, unsqueezing and permut(Av1001277993,P23)
24.27. Selecting data (indexing).zh_en(Av1001277993,P24)
25.28. PyTorch and NumPy.zh_en(Av1001277993,P25)
26.29. Reproducibility.zh_en(Av1001277993,P26)
27.30. Accessing a GPU.zh_en(Av1001277993,P27)
28.31. Setting up device agnostic code.z(Av1001277993,P28)
29.33. Introduction to PyTorch Workflow.(Av1001277993,P29)
30.34. Getting setup.zh_en(Av1001277993,P30)
31.35. Creating a dataset with linear re(Av1001277993,P31)
32.36. Creating training and test sets ((Av1001277993,P32)
33.38. Creating our first PyTorch model.(Av1001277993,P33)
34.40. Discussing important model buildi(Av1001277993,P34)
35.41. Checking out the internals of our(Av1001277993,P35)
36.42. Making predictions with our model(Av1001277993,P36)
37.43. Training a model with PyTorch (in(Av1001277993,P37)
38.44. Setting up a loss function and op(Av1001277993,P38)
39.45. PyTorch training loop intuition.z(Av1001277993,P39)
40.48. Running our training loop epoch b(Av1001277993,P40)
41.49. Writing testing loop code.zh_en(Av1001277993,P41)
42.51. Saving-loading a model.zh_en(Av1001277993,P42)
43.54. Putting everything together.zh_en(Av1001277993,P43)
44.60. Introduction to machine learning (Av1001277993,P44)
45.61. Classification input and outputs.(Av1001277993,P45)
46.62. Architecture of a classification (Av1001277993,P46)
47.64. Turing our data into tensors.zh_e(Av1001277993,P47)
48.66. Coding a neural network for class(Av1001277993,P48)
49.68. Using torch.nn.Sequential.zh_en(Av1001277993,P49)
50.69. Loss, optimizer and evaluation fu(Av1001277993,P50)
51.70. From model logits to prediction p(Av1001277993,P51)
52.71. Train and test loops.zh_en(Av1001277993,P52)
53.73. Discussing options to improve a m(Av1001277993,P53)
54.76. Creating a straight line dataset.(Av1001277993,P54)
55.78. Evaluating our models predictions(Av1001277993,P55)
56.79. The missing piece non-linearity.z(Av1001277993,P56)
57.84. Putting it all together with a mu(Av1001277993,P57)
58.88. Troubleshooting a mutli-class mod(Av1001277993,P58)
59.92. Introduction to computer vision.z(Av1001277993,P59)
60.93. Computer vision input and outputs(Av1001277993,P60)
61.94. What is a convolutional neural ne(Av1001277993,P61)
62.95. TorchVision.zh_en(Av1001277993,P62)
63.96. Getting a computer vision dataset(Av1001277993,P63)
64.98. Mini-batches.zh_en(Av1001277993,P64)
65.99. Creating DataLoaders.zh_en(Av1001277993,P65)
66.103. Training and testing loops for b(Av1001277993,P66)
67.105. Running experiments on the GPU.z(Av1001277993,P67)
68.106. Creating a model with non-linear(Av1001277993,P68)
69.108. Creating a train-test loop.zh_en(Av1001277993,P69)
70.112. Convolutional neural networks (o(Av1001277993,P70)
71.113. Coding a CNN.zh_en(Av1001277993,P71)
72.114. Breaking down nn.Conv2d-nn.MaxPo(Av1001277993,P72)
73.118. Training our first CNN.zh_en(Av1001277993,P73)
74.120. Making predictions on random tes(Av1001277993,P74)
75.121. Plotting our best model predicti(Av1001277993,P75)
76.123. Evaluating model predictions wit(Av1001277993,P76)
77.126. Introduction to custom datasets.(Av1001277993,P77)
78.128. Downloading a custom dataset of (Av1001277993,P78)
79.129. Becoming one with the data.zh_en(Av1001277993,P79)
80.132. Turning images into tensors.zh_e(Av1001277993,P80)
81.136. Creating image DataLoaders.zh_en(Av1001277993,P81)
82.137. Creating a custom dataset class (Av1001277993,P82)
83.139. Writing a custom dataset class f(Av1001277993,P83)
84.142. Turning custom datasets into Dat(Av1001277993,P84)
85.143. Data augmentation.zh_en(Av1001277993,P85)
86.144. Building a baseline model.zh_en(Av1001277993,P86)
87.147. Getting a summary of our model w(Av1001277993,P87)
88.148. Creating training and testing lo(Av1001277993,P88)
89.151. Plotting model 0 loss curves.zh_(Av1001277993,P89)
90.152. Overfitting and underfitting.zh_(Av1001277993,P90)
91.155. Plotting model 1 loss curves.zh_(Av1001277993,P91)
92.156. Plotting all the loss curves.zh_(Av1001277993,P92)
93.157. Predicting on custom data.zh_en(Av1001277993,P93)