diff options
| -rw-r--r-- | CHANGELOG.md | 8 | ||||
| -rw-r--r-- | README.md | 5 |
2 files changed, 11 insertions, 2 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index 7f997cb0..f533710b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,14 @@ This documents the main changes to the `candle` crate. ## Unreleased ### Added +- Add pose estimation to the yolo example + [589](https://github.com/huggingface/candle/pull/589). +- Api to write GGUF files + [585](https://github.com/huggingface/candle/pull/585). +- Support more quantization types + [580](https://github.com/huggingface/candle/pull/580). +- Add EfficientNet as an example Computer Vision model + [572](https://github.com/huggingface/candle/pull/572). - Add a group parameter to convolutions [566](https://github.com/huggingface/candle/pull/566). - New dtype: int64 @@ -62,7 +62,8 @@ Check out our [examples](./candle-examples/examples/): the LLaMA model using the same quantization techniques as [llama.cpp](https://github.com/ggerganov/llama.cpp). - [yolo-v3](./candle-examples/examples/yolo-v3/) and - [yolo-v8](./candle-examples/examples/yolo-v8/): object detection models. + [yolo-v8](./candle-examples/examples/yolo-v8/): object detection and pose + estimation models. Run them using the following commands: ``` cargo run --example whisper --release @@ -74,7 +75,7 @@ cargo run --example stable-diffusion --release -- --prompt "a rusty robot holdin cargo run --example dinov2 --release -- --image path/to/myinput.jpg cargo run --example quantized --release cargo run --example yolo-v3 --release -- myimage.jpg -cargo run --example yolo-v8 --release -- myimage.jpg +cargo run --example yolo-v8 --release -- myimage.jpg # for pose estimation, add --task pose ``` In order to use **CUDA** add `--features cuda` to the example command line. If |