diff options
Diffstat (limited to 'candle-transformers/src/models/dinov2.rs')
| -rw-r--r-- | candle-transformers/src/models/dinov2.rs | 38 |
1 files changed, 36 insertions, 2 deletions
diff --git a/candle-transformers/src/models/dinov2.rs b/candle-transformers/src/models/dinov2.rs index df8834d1..4d46941f 100644 --- a/candle-transformers/src/models/dinov2.rs +++ b/candle-transformers/src/models/dinov2.rs @@ -1,8 +1,42 @@ //! Implementation of the DINOv2 models from Meta Research. //! -//! See: -//! - DINOv2: ["DINOv2: Learning Robust Visual Features without Supervision"](https://github.com/facebookresearch/dinov2) +//! This module implements the DINOv2 vision transformer model from Meta AI Research. +//! DINOv2 is a self-supervised learning model that can learn visual features +//! without using any labeled data. See: ["DINOv2: Learning Robust Visual Features without Supervision"](https://github.com/facebookresearch/dinov2) //! +//! ## Running an example with color map and CUDA +//! +//! ```bash +//! cargo run \ +//! --features cuda,depth_anything_v2 \ +//! --package candle-examples \ +//! --example depth_anything_v2 \ +//! -- --color-map \ +//! --image candle-examples/examples/yolo-v8/assets/bike.jpg +//! ``` +//! +//! ## Running as an ImageNet classifier +//! +//! The model returns the probability for the image to belong to each of the 1000 ImageNet categories. +//! +//! <div align=center> +//! <img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/yolo-v8/assets/bike.jpg" alt="" width=640> +//! </div> +//! +//! ```bash +//! cargo run \ +//! --example dinov2 \ +//! --release \ +//! -- --image candle-examples/examples/yolo-v8/assets/bike.jpg +//! +//! > mountain bike, all-terrain bike, off-roader: 43.67% +//! > bicycle-built-for-two, tandem bicycle, tandem: 33.20% +//! > crash helmet : 13.23% +//! > unicycle, monocycle : 2.44% +//! > maillot : 2.42% +//! ``` +//! + use candle::{IndexOp, Result, Tensor, D}; use candle_nn::{layer_norm, LayerNorm, Linear, Module, VarBuilder}; |