Pytorch&Hugginface Deep Learning Course(Colab Hands-On)

Welcome to Pytorch Deep Learning From Zero To Hero Series.

If you have already mastered the basic syntax of python and don't know what to do next, this course will be a rocket booster to skyrocket your programming skill to a business applicable level.

In this course, you will be able to master implementing deep neural network from the very beginning(simple perceptron) to BERT transfer learning/Google's T5 by using pytorch and huggingface yourself by colab. Each Section will have one assignment for you to think and code yourself.

The Agenda is below.

Agenda:

1. Introduction

2. Google Colaboratory

3. Neuron

4. Perceptron

5. Make Your Perceptron Trainable

6. Normalize Data

7. Activation Function

8. Loss Function

9. Gradient Descent

10. Elegant Pytorch Gradient Descent

11. Final Project

12. Final Project Explained

13. Multi Layer Perceptron(MLP)

14. One Hot Encoding

15. Prepare data for MLP

16. Define MLP

17. Train & Evaluate MLP

18. Final Project for MLP

19. FCNN Explained

20. FCNN LOVE Letters Classification using MLP

21. Final Project For FCNN

22. CNN Explained

23. CNN Prepare data(Fashion MNIST)

24. CNN Define Model

25. CNN Train&Evaluate Model

26. CNNInference

27. Final Project For CNN

28. RNN Explained

29. RNN Prepare data

30. RNN Define Model

31. RNN Train Model

32. RNN Inference

33. BERT Sesame Street

34. BERT Prepare Data IMDB

35. BERT Model definition

36. BERT Model Training

37. BERT Model Evaluation

38. BERT Model Prediction

39. BERT Final Project

40. T5 Prepare Data

41. T5 Model definition

42. T5 Model Training

43. T5 Model Evaluation

44. T5 Model Prediction

45. T5 Final Project

Let's start our journey together.

Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Flat is better than nested.
Sparse is better than dense.
Readability counts.
Special cases aren’t special enough to break the rules.
Although practicality beats purity.
Errors should never pass silently.
Unless explicitly silenced.
In the face of ambiguity, refuse the temptation to guess.
There should be one– and preferably only one –obvious way to do it.
Although that way may not be obvious at first unless you’re Dutch.
Now is better than never.
Although never is often better than *right* now.
If the implementation is hard to explain, it’s a bad idea.
If the implementation is easy to explain, it may be a good idea.
Namespaces are one honking great idea — let’s do more of those!