It is good to start from here:
This is a good one, but 2 years ago.
Probably, you can google or some good practice in stackoverflow or somewhere else for general ai practice, programming, etc. If you can think about something very specific for Fastai. Please add more here.
Thus, I add one more.
- Figure out what is the uniqueness of Fastai and yourself. Good practice by asking questins:
a. How fastai is a good match for you?
b. What is your learning rate -Lr?
c. What is your model, cf. ResNet?
d. What is your pattern and rhyme of your learning style?
e. What can be the loss rate of your learning?
f. How do you evaluate the accuracy and ways of validate what you learned?
g. How would you apply universal approximation theorem in your learning journey?
h. How would you deal with the data and info you get from Fastai?
I am inspired by FastAi that I can learn from about learning model and the process of develop AI fast or slow as my own learning journey, which can be extended much further beyond fastai. Thus, Thank you FastAI and the community.