Before starting fast.ai, I tried to learn from people who had already passed through the class. Many of them have blogs and wrote about what they would do differently.
Most consistent piece of advice: “Really listen to Jeremy and spend your time how he suggests”
Most consistent regret: “I should have listened when Jeremy said don’t spend hours lost in theory trying to understand everything right away”.
For each lesson I’m going to make a list of everything Jeremy says to do, and then I’m going to do it. I hope others will join me.
- Don’t try to stop and understand everything.
- Don’t waste your time, learn Jupyter keyboard shortcuts. Learn 4 to 5 each day.
- Please run the code, really run the code. Don’t go deep on theory. Play with the code, see what goes in and what comes out.
- Pick one project. Do it really well. Make it fantastic.
- Run this notebook (lesson1-pets.ipynb), but then get your own dataset and run it! (extra emphasis: do this!)
- If you have a lot of categories, don’t run confusion matrix, run…
If forum posts are overwhelming, click “summarize this topic” at the bottom of the first post.
Please follow the official server install/setup instructions, they work and are easy.
It’s okay to feel intimidated, there’s a lot, but just pick one piece and dig into it. Try to push a piece of code, or learn a concept like regular expressions, or create a classifier, or whatever. Context: Lesson 2: It’s okay to feel intimidated
If you’re stuck, keep going. See image below! Context: Lesson 2: If you’re stuck, keep going
If you’re not sure which learning rate is best from plot, try both and see.
When you put a model into production, you probably want to use CPU for inference, except at massive scale. Context: Lesson 2: Putting Model into Production
Most organizations spend too much time gathering data. Get a small amount first, see how it goes.
If you think you’re not a math person, check out Rachel’s talk: There’s no such thing as “not a math person”. My own input: only 6 minutes, everyone should watch it!
- If you use a dataset, it would be very nice of you to cite the creator and thank them for their dataset.
- This week, see if you can come up with a problem that you would like to solve that is either multi-label classification or image regression or image segmentation or something like that and see if you can solve that problem. Context: Fast.ai Lesson 3 Homework
- Always use the same stats that the model was trained with. Context: Lesson 3: Normalized data and ImageNet
- In response to “Is there a reason you shouldn’t deliberately make lots of smaller datasets to step up from in tuning, let’s say 64x64 to 128x128 to 256x256?”: Yes you should totally do that, it works great, try it! Context: Lesson 3: 64x64 vs 128x128 vs 256x256
If you’re doing NLP stuff, make sure you use all of the text you have (including unlabeled validation set) to train your model, because there’s no reason not to. Lesson 4: A little NLP trick
In response to “What are the 10% of cases where you would not use neural nets”. You may as well try both. Try a random forest and try a neural net. Lesson 4: How to know when to use neural nets
Use these terms (parameters, layers, activations…etc) and use them accurately. Lesson 4: Important vocabulary for talking about ML
- The answer to the question “Should I try blah?” is to try blah and see, that’s how you become a good practitioner. Lesson 5: Should I try blah?