Part 2 Lesson 8 wiki

Wiki: Lesson 9 >>>

Lesson resources:


  • Quick summary of how to download the dataset:
     cd ~/fastai/courses/dl2
     ln -s ~/data data && cd $_
     mkdir pascal && cd $_
     curl -OL
     curl -OL
     tar -xf VOCtrainval_06-Nov-2007.tar
     mv PASCAL_VOC/*.json .
     rmdir PASCAL_VOC

Returning to AWS?

  • Login to AWS and get your public IP (xx.xx.xx.xx). Then, follow commands:
ssh ubuntu@xx.xx.xx.xx -L8888:localhost:8888
git pull
conda env update
jupyter notebook
  • For PyCharm and Mac users - a list of the shortcuts Jeremy provided for Visual Studio Code:
    • Action (PyCharm + Mac shortcut)
    • Command palette- (Shift + Command + A)
    • Select interpreter (for fastai env) - (Shift+Command+A) and then look for “interpreter”
    • Select terminal shell- (Shift+Command+A) and then look for “terminal shell”
    • Go to symbol (Option + Command + O)
    • Find references (Command+ G)(go down in the references) (Command + Shift + G) (go up)(Command + Function + F7) (look for all)
    • Go to definition (Command + Down Arrow Key)
    • Go back (Command + [ )
    • View documentation (Option + Space) for viewing source and (Function + F1) for viewing documentation
    • Zen mode (Control + Command + F) and same to get out too
    • Hide sidebar (Command + 1) redoing it will bring it back
    • Find them all with the (Shift + Command+ A) palette option for reference.

Time line for videos

Resources related to stuff that Jermey mentioned we can learn/Homework

  • Python debugger (pdb cheat sheet):
    • You can use the python debugger pdb to step through code:
      • pdb.set_trace() to set a breakpoint
      • %debug magic to trace an error
    • Commands you need to know:
      • s - step: execute and step into function
      • n - next: execute current line
      • c - continue: continue execution until next breakpoint
      • u - up: move one level up in the stack trace
      • d - down: move one level down in the stack trace
      • p - print: print variable, example: “p x” prints variable x
      • l - list: lists 11 lines of code around the current line
  • Alternative debugger that is more easy to use (
    It’s more intuitive than the recommended by the course, But it’s still in developing phase.
    • Demo of debugger:
    • Install: pip install pixiedust
    • Import in top of the juputer notebook: import pixiedust
      *In the top of the cell you like to debugg, type: %%pixie_debugger and run the cell.
    • Use the interactive buttons to step your code even outside of the jupyter notebook.
  • OO Matplotlib
  • Learn Greek letters / List of mathematical symbols at Wikipedia
  • Editor
  • Jupyter Lab video


This is a wiki thread - feel free to add links to resources covered in, or relevant to, the lesson. If you have questions or comments during class, add them below.


Let’s do this! I’m so excited to be part of this again. Best class I’ve ever had. Thank you for making this available to the world - it is amazing.


All set up in NYC!


Wrote a answer on Stack - DataScience explaining Transfer Learning ( thanks to Jeremy)

Read it here if you like…

Can you share the resource you saw the PCI-e profiling of x8 vs x16?


Here’s a good link for Greek Alphabets . Please reply if you have a better link.


This one contains a couple of benchmarks run on TitanX


Jeremy mentioned developing parts of this course on Windows.

I would love references to his Windows Setup (pytorch and fastai libraries on Windows?).


Here is a quick summary for downloading the dataset:

cd ~/fastai/courses/dl2
ln -s ~/data data && cd $_
mkdir pascal && cd $_
curl -OL
curl -OL
tar -xf VOCtrainval_06-Nov-2007.tar
mv PASCAL_VOC/*.json .

Can one access the pascal dataset from the website instead of downloading it? Can Path() do it?

Why did you choose upper-left + lower-right instead of upper-left + dimensions?


Thank you for posting this. Where did you get the google link with the .Json files? I seemed to have missed that one.

Great blog post about object-oriented matplotlib API:


Found it, it is after the PATH command. Still wondering where the original xml files are though

In case anyone likes to solidify things with a song, you can sing the greek alphabet to the tune of the song “row row row your boat”. :slight_smile:


Actually, there is a link in one of the Markdown cells with description, after list(PATH.iterdir()). It’s easily missable. I, too, didn’t see it immediately.

1 Like

I believe working with/specifying 2 parameters is less cumbersome than 3?

1 Like

Does using bottom-left corner instead of width/height of the box impact accuracy of the model?

How is bounding box identified in this example. Which algorithm is used, ie YOLO, R-CNN?