Downloads · 30 days
0
capsule-pocket
ARotting/capsule-pocket
capsule-pocket is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Capsule Pocket trains seven primary capsules and ten eight-dimensional digit capsules with three rounds of routing by agreement. An ordinary MLP with exactly the same 4,060 trainable parameters is the control.
Access
Public
Updated Jul 30, 2026
Repo size
33 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors33 KB · 68%
At a glance
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- 79aa228a
Model card
From the Hugging Face model README
Capsule Pocket
Capsule Pocket trains seven primary capsules and ten eight-dimensional digit capsules with three rounds of routing by agreement. An ordinary MLP with exactly the same 4,060 trainable parameters is the control.
The benchmark separates clean accuracy from one-pixel translation and center occlusion robustness. The Space exposes the ten digit-capsule vector lengths for each transformed input.
Verified local result
At exactly 4,060 parameters, capsules reached 97.04% clean accuracy versus 97.41% for the MLP. They improved one-pixel translation accuracy from 44.72% to 46.20% and center-occlusion accuracy from 79.63% to 82.22%.
uv run python projects/capsule-pocket/train.py
uv run pytest tests/test_capsule_pocket.py
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026