sradc / SmallPebble
A minimalist deep learning library written from scratch in Python
Why this job: says: from scratch
What it does
- Compact. < 1000 lines of core logic.
- Educational. Prioritizes code clarity over raw performance (CPU-only).
- Feature-rich. Supports matmul, conv2d, maxpool2d, and array broadcasting.
- Flexible. Supports eager execution and implicit graph building.
- Extensible. Easy API for adding custom operations.
Get started
pip install smallpebble- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 135
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v3.0.5
- Released 9 months ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 8 merged
- 0 waiting
- Releases
- 6
- 6 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| neonwatty / machine-learning-refined | 2,313 | 31 days ago | Custom | No downloads |
| n2cholas / awesome-jax | 2,176 | 9 months ago | CC0-1.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Makefile 1%
Topics
- autodiff
- cupy
- deep-learning
- machine-learning
- neural-network
- numpy
- python
Project record
- JobLists and guides
- StatusListed
- Commits189
- Forks14
- Watching2
- Stars in 28 days0
- CreatedFeb 3, 2021
- First seen by usNov 7, 2026
- CheckedNov 8, 2026