Kaggle sandbox
This is a simple template project to Kaggle participation…
Expected content:
- a core package with functionalities used across scripts and notebooks
- tutorial/experiment notebooks (in notebook folder if needed)
- [optional] some functionality testing aka unittests or doctests
What to write here:
- simple completion description + link
- shortly what task it is to solve
- list/link online sources
- link kernels/submissions
Showcases
Some derived projects
- Multiple image classification
- Herbarium 2022
- Plant Pathology 2021 - FGVC8 as multi-label classification on apple tree leaf
- iMet Collection 2021 x AIC - FGVC8 as multi-label classification on museum objects
- Cassava Leaf Disease Classification
- etc.
- Multiple Image segmentation
- Tract Image Segmentation as semantic 3D segmentation from MRI scans
- Cell Instance Segmentation in microscopy images
- etc.
- COVID detection as object detection on CT (DICOM format) scans
- Brain Tumor 3D as image classification on MRI scans
Author’s writing
- Best Practices to Rank on Kaggle Competition with PyTorch Lightning and Grid.ai Spot Instances
- Practical Lighting Tips to Rank on Kaggle Image Challenges
- Tackling the Kaggle COVID Detection Challenge with Lightning Flash and IceVision
- Simple 3D MRI classification ranked bronze on Kaggle
- Tabular Classification and Regression Made Easy with Lightning Flash
- Easy Kaggle Offline Submission With Chaining Kernel Notebooks
- Kaggle hacking: Validate a simple hypothesis against a hidden dataset