This is the process and outcomes of optimizing a Multi-Layer Perceptron (MLP) to classify 10 digits (0-9) from 32×32-pixel RGB images. Starting with a baseline model designed using PyTorch, various modifications to the network architecture and data augmentation techniques were explored, ultimately achieving an 86.32% test accuracy.
active 2025-08-18 → 2025-08-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1 days from 2025-08-18 to 2025-08-18. Pushes: 16 total, peak 16 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Recorded stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Recorded stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| JuliaHandiprima | 16 | 16 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
No issue or PR events — this repo's activity is pushes only.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.