burn dinov2 model, view the live demo
| input | fg pca |
|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
cargo run --features backend_wgpu --example pca
cargo run -p bevy_burn_dino
- inference
- pca transform layer
- ViT configurations
- real-time camera demo
- training (loss + dropout)
- optimized attention
- automatic weights cache/download
- quantization
- feature upsampling
- download pre-trained model (ViT-S|B, /wo registers) from here
- place in
./assets/models - run import tool
cargo run --features import --bin import
cargo bench --bench dinov2 --features backend_wgpu- open
target/criterion/report/index.html