80468d9c83
0.1.0-beta.1 ( #82 )
2025-04-27 13:01:51 +08:00
ca6e70b69c
Add RF-DETR model ( #73 )
2025-04-11 13:03:10 +08:00
fcc3ba94fd
Add YOLOv12 model
2025-02-20 16:49:25 +08:00
e2347353ba
Add SmolVLM model ( #65 )
...
* Add SmolVLM model
2025-02-08 00:28:35 +08:00
94fa832359
Add Owlv2 model ( #59 )
2025-01-22 23:49:51 +08:00
475a680703
Add moondream2
...
* Add moondream2
* Update README.md
2025-01-20 21:37:54 +08:00
0f2d84b8c5
🐍 v0.1.0 ( #53 )
2025-01-12 16:59:57 +08:00
4e932c4910
Bump the version to 0.0.20
2024-12-03 19:37:34 +08:00
57db14ce5d
Update README.md
2024-10-10 00:30:52 +08:00
64dc804a13
Update README.md
2024-09-30 22:48:07 +08:00
2cb9e57fc4
Update README.md
2024-09-28 10:49:06 +08:00
f2c4593672
Update README.md
2024-09-28 10:10:05 +08:00
f0fd4936e8
Add florence2 model
...
* Add florence2-base model for all tasks
* Update annotator.rs
2024-09-21 20:23:42 +08:00
5057c20565
Update README.md
2024-09-16 11:05:53 +08:00
0adddd3bbd
0.0.14: DataLoader now support video and streaming
...
- Added `Hub` for resource management
- Updated `DataLoader` to support video and streaming
- Updated `CI`
- Replaced `println!` with `tracing` for logging
2024-09-16 10:41:16 +08:00
9b969b9203
Fix polygon drawing
...
* Support auto download ort feature
* Fix polygon drawing
2024-09-03 00:01:34 +08:00
f6755a8be4
Bump the version to 0.0.12
...
* Add sapiens-seg model
2024-08-31 17:10:36 +08:00
f25f5cf2b5
Bump the version to v0.0.11
...
- ONNXRuntime -> 1.19.x
- CUDA -> 12.x
- TensorRT -> 10.x
2024-08-27 20:09:15 +08:00
b81b5e3cf5
Add GroundingDINO ( #30 )
2024-08-09 19:06:30 +08:00
451aa8cc7b
Update README.md
2024-07-31 23:16:35 +08:00
d9f2d6382b
Update README.md
2024-07-31 21:28:52 +08:00
1d74085158
0.0.7 ( #27 )
2024-07-31 21:27:41 +08:00
edc3a8897c
0.0.5 ( #24 )
...
* Using Rayon to accelarate YOLO post-processing
* Refactor YOLO with outputs format
* Optimize `conf * clss` for yolov5 v6 v7
* Add depth-anything-v2
* Update README.md
* Update CHANGELOG.md
2024-07-12 19:46:48 +08:00
f6fec32c7b
Docs update
2024-07-01 16:53:36 +08:00
20d2edce6a
Update README.md
2024-06-30 23:40:20 +08:00
a5141a53be
Accelerate model pre-processing and post-processing ( #23 )
...
* Add X struct to handle input and preprocessing
*Add Ops struct to manage common operations
* Use SIMD (fast_image_resize) to accelerate model pre-processing and post-processing
2024-06-30 15:19:34 +08:00
1db1dfa4bd
Update README.md
2024-06-06 13:18:23 +08:00
a65e2aff7b
feat: support yolov10 ( #15 )
...
Signed-off-by: oatiz <iamoatiz@gmail.com >
2024-06-01 16:42:38 +08:00
fc970fc117
Update ort and improve the speed of preprocessing
...
* Add onnx proto
* Update ort to 2.0.0-rc.2
* Improve the speed of resizing
* Fix yolo-seg bug
* Update README.md
2024-05-12 18:12:34 +08:00
371a08011f
Add MODNet model ( #11 )
...
* Add MODNet for portrait matting
* Minor fixes
* Move assets to home directory
* Add colormap
* ci
* Update README.md
2024-04-30 15:26:53 +08:00
9697f4d5b0
Update README.md
2024-04-25 11:18:52 +08:00
e614ca4136
Add Depth-Anything model ( #10 )
...
* Add Depth-Anything model
2024-04-25 00:41:29 +08:00
beda8ef803
Add YOLOv8-OBB and some bug fixes ( #9 )
...
* Add YOLOv8-Obb & Refactor outputs
* Update README.md
2024-04-21 17:06:58 +08:00
51b75e9a21
Add YOLOPv2 & Face-Parsing model ( #3 )
...
* Add YOLOP and face parsing model
2024-04-14 15:15:59 +08:00
ead175234c
Add RTMO model for keypoint detection ( #2 )
...
* Add RTMO
2024-04-08 20:45:38 +08:00
a0d410b46d
Dev ( #1 )
...
* Update imageproc crates
* Add top-p method for sampling
* Add SVTR for text recognition & bug fix
2024-04-06 16:16:53 +08:00
ce9a416b71
Add DB model for text detection
2024-03-31 02:14:53 +08:00
a5cee66dfd
Add query method for dinov2 and adjust DataLoader
2024-03-30 15:54:47 +08:00
af934086bb
Initial
2024-03-29 15:54:24 +08:00
abaf8c0d65
Initial commit
2024-03-29 15:36:09 +08:00
