Skip to content

Commit 5c64f61

Browse files
DefTruthDefTruth
committed
update README.md
1 parent d22bd34 commit 5c64f61

File tree

1 file changed

+21
-20
lines changed

1 file changed

+21
-20
lines changed

‎README.md

+21-20
Original file line numberDiff line numberDiff line change
@@ -1,36 +1,37 @@
11

22

3-
# Lite.AI.ToolKit 🚀🚀🌟
3+
## Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models.
4+
5+
[![](https://img.shields.io/badge/MacOS-pass-brightgreen.svg)](https://github.com/DefTruth/lite.ai.toolkit/releases/tag/v0.0.1) ![](https://img.shields.io/badge/Linux-pass-brightgreen.svg) ![](https://img.shields.io/badge/Windows-pass-brightgreen.svg) [![](https://img.shields.io/badge/Version-0.0.1-green.svg)](https://github.com/DefTruth/lite.ai.toolkit/releases/tag/v0.0.1) ![](https://img.shields.io/badge/Language-C/C%2B%2B-orange.svg) ![](https://img.shields.io/badge/Device-GPU/CPU-yellow.svg) ![](https://img.shields.io/badge/License-MIT-blue.svg)
6+
7+
[![Stargazers repo roster for @DefTruth/lite.ai.toolkit](https://reporoster.com/stars/DefTruth/lite.ai.toolkit)](https://github.com/DefTruth/lite.ai.toolkit/stargazers)
48

5-
<div align='center'>
6-
<img src='logs/test_lite_yolov5_1.jpg' height="200px" width="200px">
7-
<img src='docs/resources/efficientdet_d0.jpg' height="200px" width="200px">
8-
<img src='docs/resources/street.jpg' height="200px" width="200px">
9-
<img src='logs/test_lite_ultraface.jpg' height="200px" width="200px">
10-
<br>
11-
<img src='logs/test_lite_face_landmarks_1000.jpg' height="200px" width="200px">
12-
<img src='logs/test_lite_fsanet.jpg' height="200px" width="200px">
13-
<img src='logs/test_lite_deeplabv3_resnet101.jpg' height="200px" width="200px">
14-
<img src='logs/test_lite_fast_style_transfer_mosaic.jpg' height="200px" width="200px">
15-
</div>
169

1710

1811
## Introduction.
1912

20-
[![](https://img.shields.io/badge/MacOS-pass-brightgreen.svg)](https://github.com/DefTruth/lite.ai.toolkit/releases/tag/v0.0.1) ![](https://img.shields.io/badge/Linux-pass-brightgreen.svg) ![](https://img.shields.io/badge/Windows-pass-brightgreen.svg) [![](https://img.shields.io/badge/Version-0.0.1-green.svg)](https://github.com/DefTruth/lite.ai.toolkit/releases/tag/v0.0.1) ![](https://img.shields.io/badge/Language-C/C%2B%2B-orange.svg) ![](https://img.shields.io/badge/Device-GPU/CPU-yellow.svg) ![](https://img.shields.io/badge/License-MIT-blue.svg)
13+
<div id="lite.ai.toolkit-Introduction"></div>
2114

22-
[![Stargazers repo roster for @DefTruth/lite.ai.toolkit](https://reporoster.com/stars/DefTruth/lite.ai.toolkit)](https://github.com/DefTruth/lite.ai.toolkit/stargazers)
15+
<div align='center'>
16+
<img src='logs/test_lite_yolov5_1.jpg' height="100px" width="100px">
17+
<img src='docs/resources/efficientdet_d0.jpg' height="100px" width="100px">
18+
<img src='docs/resources/street.jpg' height="100px" width="100px">
19+
<img src='logs/test_lite_ultraface.jpg' height="100px" width="100px">
20+
<img src='logs/test_lite_face_landmarks_1000.jpg' height="100px" width="100px">
21+
<img src='logs/test_lite_fsanet.jpg' height="100px" width="100px">
22+
<img src='logs/test_lite_deeplabv3_resnet101.jpg' height="100px" width="100px">
23+
<img src='logs/test_lite_fast_style_transfer_mosaic.jpg' height="100px" width="100px">
24+
</div>
2325

24-
<div id="lite.ai.toolkit-Introduction"></div>
2526

26-
*Lite.AI.ToolKit* 🚀🚀🌟 is a simple and user-friendly C++ library of *[70+](https://github.com/DefTruth/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.onnx.md)* awesome 🔥🔥🔥 AI models. It's a collection of personal interests. such as YOLOX, YoloV5, YoloV4, DeepLabV3, ArcFace, etc. *Lite.AI.ToolKit* based on *[onnxruntime c++](https://github.com/microsoft/onnxruntime)* by default. I do have plans to reimplement it with *[ncnn](https://github.com/Tencent/ncnn)* and *[MNN](https://github.com/alibaba/MNN)*, but not coming soon. It includes [object detection](#lite.ai.toolkit-object-detection), [face detection](#lite.ai.toolkit-face-detection), [style transfer](#lite.ai.toolkit-style-transfer), [face alignment](#lite.ai.toolkit-face-alignment), [face recognition](#lite.ai.toolkit-face-recognition), [segmentation](#lite.ai.toolkit-segmentation), [colorization](#lite.ai.toolkit-colorization), [matting](#lite.ai.toolkit-matting), etc. You can use these awesome models simply through *lite::cv::Type::Class* syntax, such as *[lite::cv::detection::YoloV5](#lite.ai.toolkit-object-detection)*.
27+
*Lite.AI.ToolKit* 🚀🚀🌟is a lite C++ toolkit of awesome AI models which contains *[70+](https://github.com/DefTruth/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.onnx.md)* models now. It's a collection of personal interests. Such as YOLOX, YOLOP, YOLOR, YoloV5, YoloV4, DeepLabV3, ArcFace, etc. *Lite.AI.ToolKit* based on *[onnxruntime](https://github.com/microsoft/onnxruntime)* by default. I do have plans to reimplement it with *[ncnn](https://github.com/Tencent/ncnn)* and *[MNN](https://github.com/alibaba/MNN)*, but not coming soon. It includes [object detection](#lite.ai.toolkit-object-detection), [face detection](#lite.ai.toolkit-face-detection), [face alignment](#lite.ai.toolkit-face-alignment), [face recognition](#lite.ai.toolkit-face-recognition), [segmentation](#lite.ai.toolkit-segmentation), [colorization](#lite.ai.toolkit-colorization), [matting](#lite.ai.toolkit-matting), etc. You can use these awesome models simply through *lite::cv::Type::Class* syntax, such as *[lite::cv::detection::YoloV5](#lite.ai.toolkit-object-detection)*.
2728

2829
## Citations.
2930

3031
Cite it as follows if you use *Lite.AI.ToolKit*. Star 🌟👆🏻 this repo if it does any helps to you ~ 🙃🤪🍀
3132
```BibTeX
3233
@misc{lite.ai.toolkit2021,
33-
title={lite.ai.toolkit: A simple and user friendly C++ library of awesome AI models.},
34+
title={lite.ai.toolkit: A lite C++ toolkit of awesome AI models.},
3435
url={https://github.com/DefTruth/lite.ai.toolkit},
3536
note={Open-source software available at https://github.com/DefTruth/lite.ai.toolkit},
3637
author={Yan Jun},
@@ -40,7 +41,7 @@ Cite it as follows if you use *Lite.AI.ToolKit*. Star 🌟👆🏻 this repo if
4041

4142
## Important Notes !!!
4243

43-
* ⚠️ (20210919) *Lite.AI.ToolKit* was rename from the *Lite.AI* repo! *Lite.AI* will no longer be maintained.
44+
* ⚠️ (20210919) *Lite.AI.ToolKit* was rename from the *Lite.AI* repo!
4445
* 🔥 (20210915) Added [YOLOP](https://github.com/hustvl/YOLOP) Panoptic 🚗 Perception! Use it through [*lite::cv::detection::YOLOP*](#lite.ai.toolkit-object-detection) ! See [demo](https://github.com/DefTruth/lite.ai.toolkit/blob/main/examples/lite/cv/test_lite_yolop.cpp).
4546
* 🔥 (20210807) Added [YoloR](https://github.com/WongKinYiu/yolor) ! Use it through [*lite::cv::detection::YoloR*](#lite.ai.toolkit-object-detection) syntax ! See [demo](https://github.com/DefTruth/lite.ai.toolkit/blob/main/examples/lite/cv/test_lite_yolor.cpp).
4647
* ✅ (20210731) Added [RetinaFace-CVPR2020](https://github.com/biubug6/Pytorch_Retinaface) for face detection, 1.6Mb only! See [demo](https://github.com/DefTruth/lite.ai.toolkit/blob/main/examples/lite/cv/test_lite_retinaface.cpp).
@@ -154,13 +155,13 @@ Build the shared lib of *Lite.AI.ToolKit* for *MacOS* from sources. Note that Li
154155

155156
* Windows: You can reference to [issue#6](https://github.com/DefTruth/lite.ai.toolkit/issues/6)
156157
* Linux: The Docs and Docker image for Linux will be coming soon ~ [issue#2](https://github.com/DefTruth/lite.ai.toolkit/issues/2)
157-
* Happy News !!! : 🚀 You can download the latest *ONNXRuntime* official built libs of Windows, Linux, MacOS and Arm !!! Both CPU and GPU versions are available. No more attentions needed pay to build it from source. Download the official built libs from [v1.8.1](https://github.com/microsoft/onnxruntime/releases). I have used version 1.7.0 for Lite.AI now, you can downlod it from [v1.7.0](https://github.com/microsoft/onnxruntime/releases/tag/v1.7.0), but version 1.8.1 should also work, I guess ~ 🙃🤪🍀. For *OpenCV*, try to build from source(Linux) or down load the official built(Windows) from [OpenCV 4.5.3](https://github.com/opencv/opencv/releases). Then put the includes and libs into *third_party* directory of Lite.AI.
158+
* Happy News !!! : 🚀 You can download the latest *ONNXRuntime* official built libs of Windows, Linux, MacOS and Arm !!! Both CPU and GPU versions are available. No more attentions needed pay to build it from source. Download the official built libs from [v1.8.1](https://github.com/microsoft/onnxruntime/releases). I have used version 1.7.0 for Lite.AI.ToolKit now, you can downlod it from [v1.7.0](https://github.com/microsoft/onnxruntime/releases/tag/v1.7.0), but version 1.8.1 should also work, I guess ~ 🙃🤪🍀. For *OpenCV*, try to build from source(Linux) or down load the official built(Windows) from [OpenCV 4.5.3](https://github.com/opencv/opencv/releases). Then put the includes and libs into *third_party* directory of Lite.AI.
158159

159160
</details>
160161

161162

162163

163-
* Clone the Lite.AI from sources:
164+
* Clone the Lite.AI.ToolKit from sources:
164165
```shell
165166
git clone --depth=1 https://github.com/DefTruth/lite.ai.toolkit.git # latest
166167
```

0 commit comments

Comments
 (0)