burn_dino

Crates.ioburn_dino
lib.rsburn_dino
version0.6.0
created_at2024-11-22 19:34:42.525092+00
updated_at2025-11-18 01:04:26.715918+00
descriptionburn dino model inference and training
homepagehttps://github.com/mosure/burn_dino
repositoryhttps://github.com/mosure/burn_dino
max_upload_size
id1457646
size262,388
Mitchell Mosure (mosure)

documentation

README

burn_dino 🔥🦖

test GitHub License GitHub Last Commit GitHub Releases GitHub Issues Average time to resolve an issue crates.io

burn dinov2 model, view the live demo

input fg pca
Alt text Alt text
Alt text Alt text
Alt text Alt text
Alt text Alt text

cargo run --example pca cargo run -p bevy_burn_dino

features

  • inference

  • pca transform layer

  • ViT configurations

  • real-time camera demo

  • training (loss + dropout)

  • optimized attention

  • automatic weights cache/download

  • quantization

  • feature upsampling

setup

  • download pre-trained model (ViT-S|B, /wo registers) from here
  • place in ./assets/models
  • run import tool cargo run --bin import

benchmarks

  • cargo bench
  • open target/criterion/report/index.html
Commit count: 33

cargo fmt