Decision Workspace
vit_tch vs oxicuda-vision vs torsh-vision
Side-by-side comparison of Rust crates
39
vit_tch
experimentalv0.1.0
Vision Transformer models and building blocks for Rust using tch.
52
oxicuda-vision
experimentalv0.5.5
Vision Transformer & CLIP primitives for OxiCUDA: ViT patch embedding, multi-head self-attention, CLIP contrastive learning, FPN, RoI align, DETR decoder — pure Rust, zero CUDA SDK dependency.
60
torsh-vision
growingv0.2.0
Computer vision utilities for ToRSh deep learning framework
Core Metrics
| vit_tch | oxicuda-vision | torsh-vision | |
|---|---|---|---|
| Health Score | 39 | 52 | 60 |
| Total Downloads | 21 | 233 | 855 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 10 |
| Releases | 1 | 13 | 9 |
| Last Updated | 138d ago | 57d ago | 57d ago |
| Age | 4m | 5m | 1y |
Health Breakdown
vit_tch
Maintenance
6
Quality
13
Community
5
Popularity
2
Documentation
13
oxicuda-vision
Maintenance
17
Quality
14
Community
6
Popularity
3
Documentation
12
torsh-vision
Maintenance
19
Quality
13
Community
9
Popularity
4
Documentation
15
Technical Details
| vit_tch | oxicuda-vision | torsh-vision | |
|---|---|---|---|
| Version | 0.1.0 | 0.5.5 | 0.2.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | Apache-2.0 | Apache-2.0 |
| Dependencies | 1 | 2 | 21 |
| Crate Size | 9.8MB | 262KB | 407KB |
| Features | 5 | 1 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | — | 1.85 | 1.87 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •torsh-vision leads with a health score of 60/100, but none of the options score above 80.