Series Kaggle Getting Started
Baby steps towards competitions
Because Getting Started is:
Less chance of getting stuck
How we will do it?
focusing on the process rather than just getting the output.
starting with easier problems.
- PyTorch: A 60 Minute Blitz, Writing Custom Datasets
Expectations from this series
Time: 5–6 Hours per challenge or more.
Coding Style: fastai coding style
While coding, no function takes 10 seconds.
Heavy use of %timeit%
Explanation Style: Based on Kaggle Notebook Commits
Notebook Commit 1: Will focus on getting input and output
Next N-1 Commits: Will add new features/improvements. These will be linked.
Last Commit: Complete solution
This way one can see get a peek behind the finished product.
X = training_data y = training_label ds = dataset dl = dataloader o = optimizer
- Digit Recognition
- Facial Keypoints Detection - in progress