I will start Chapter 2 by filling out the questionnaire, before reading the text or watching the lesson video.
Q1. Provide an example of where the bear classification model might work poorly in production, due to structural or style differences in the training data.
Q2. Where do text models currently have a major deficiency?
Q3. What are possible negative societal implications of text generation models?
Q4. In situations where a model might make mistakes, and those mistakes could be harmful, what is a good alternative to automating a process?
Q5. What kind of tabular data is deep learning particularly good at?
Q6. What's a key downside of directly using a deep learning model for recommendation systems?
Q7. What are the steps of the Drivetrain Approach?
Q8. How do the steps of the Drivetrain Approach map to a recommendation system?
Q9. Create an image recognition model using data you curate, and deploy it on the web.
Q10. What is
DataLoaderobjects: one with training data and one with validation data.
from fastai.vision.all import *
Q11. What four things do we need to tell fastai to create
pathto the data, the filenames
fnames, how to get labels using
label_funcand the batch size
Q12. What does the
splitter parameter to
splitterseems to be a function that takes the full dataset and splits it into subsets, which are then wrapped into a
Datasetsobject and returned on a
Q13. How do we ensure a random split always gives the same validation set?
Q14. What letters are often used to signify the independent and dependent variables?
Q15. What's the difference between the crop, pad, and squish resize approaches? When might you choose one over the others?
sizeis chosen for the training
size, then fills the gap between the original image and the area of
sizewith a reflection of the image (by default) with other options (like padding with zeroes which keeps a black border around the image).
sizewhich will change the proportions of the image
Q16. What is data augmentation? Why is it needed?
Q17. What is the difference between
item_tfms: a transform applied to a single image
batch_tfms: a transform applied to a batch
Q18. What is a confusion matrix?
Q19. What does
.pklfile of the model
Q20. What is it called when we use a model for getting predictions, instead of training?
Q21. What are IPython widgets?
Q22. When might you want to use CPU for deployment? When might GPU be better?
Q23. What are the downsides of deploying your app to a server, instead of to a client (or edge) device such as a phone or PC?
Q24. What are three examples of problems that could occur when rolling out a bear warning system in practice?
Q25. What is "out-of-domain data"?
Q26. What is "domain shift"?
Q27. What are the three steps in the deployment process?