For a bit of background, this past year at my university I ran my own “study group” where I proctored my own rendition of Practical Deep Learning for Coders. In this I focused more on a datatype by datatype basis each lecture and went in-depth into each. I knew that eventually I wanted to redo these notebooks into 2.0 for the Spring when I kicked it off again, but as I designed the whole thing to be intro friendly, I have decided to do it now and port 2.0 over. In these notebooks I will go over the high-level API differences so that those who may only stay at this level right now don’t get too overwhelmed by all the new information that 2.0 brings.
The first few notebooks will be very similar to the original course as it’s a great introduction, and then branching off from there. The first one is available here where I go over PETs! Over the next week or two I’ll slowly be bringing in more notebooks and converting them over.
01 Image Classification (and an introduction to the library!)
02 Custom Image Classification (and how to use
03a Tabular Data (and how to use labeled test sets)
03b K-Fold Validation and Ensembling
04b Permutation Importance
05 Multi-Label and Variations with the DataBlock API
06 Utilizing the State of the Art
07 Image Regression
08a IMDB Sample (text in a DataFrame or csv)
- Note these notebooks were originally made in Colab so they will work in that environment as well as regular Jupyter