aws / aws/amazon-sagemaker-examples
fastai_oxford_pets update fastaiv2
- Dominant language
- Jupyter Notebook
- Stars
- 11k
- Forks
- 7k
- Avg merge
- 8h 29m
- Merged PRs (30d)
- 8
Description
I loved your notebook!!
@mattmcclean and @kwwaikar could you please update the tutorial to fastai v2?
The new version of the library was recently released and your tutorial is great but outdated. I updated the code and training works, but having trouble with the input_fn function to make it work when it comes to deployment, i.e. the endpoint is having trouble in deserializing the json / jpeg image. Should be a very quick fix for the awesome fastai community https://drive.google.com/file/d/1hhFoljBME6uh89uQmjaBTDFaZYugVyLu/view?usp=sharing
Contributor guide
Research direction
Start with the fastai_oxford_pets tutorial and inspect its input_fn and deployment endpoint path, using the linked example as context. Run the notebook and deployment flow to reproduce JSON/JPEG deserialization, then verify the tutorial works with fastai v2 and the endpoint accepts the documented inputs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, jupyter-notebook, machine-learning
- Domain
- cloud, documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100