/burn_dino

burn dinov2 model inference and training 🔥🦖

Primary LanguageRustApache License 2.0Apache-2.0

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