From 059f74cf4c935e824e9177d42502372a641a7c84 Mon Sep 17 00:00:00 2001
From: DefTruth <qiustudent_r@163.com>
Date: Wed, 4 Aug 2021 22:35:27 +0800
Subject: [PATCH] add GPU Compatibility for CUDAExecutionProvider (#10)

---
 README.md | 148 +++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 112 insertions(+), 36 deletions(-)

diff --git a/README.md b/README.md
index 977fcc3c..5ab2262c 100644
--- a/README.md
+++ b/README.md
@@ -22,7 +22,7 @@
 
 <div id="lite.ai-Introduction"></div> 
 
-*Lite.AI* 🚀🚀🌟 is a simple and user-friendly C++ library of awesome🔥🔥🔥 AI models. It's a collection of personal interests. such as YOLOX, YoloV5, YoloV4, DeepLabV3, ArcFace, etc. *Lite.AI* 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-object-detection), [face detection](#lite.ai-face-detection), [style transfer](#lite.ai-style-transfer), [face alignment](#lite.ai-face-alignment), [face recognition](#lite.ai-face-recognition), [segmentation](#lite.ai-segmentation), [colorization](#lite.ai-colorization), [face attributes analysis](#lite.ai-face-attributes-analysis), [image classification](#lite.ai-image-classification), [matting](#lite.ai-matting), etc. You can use these awesome models simply through *lite::cv::Type::Class* syntax, such as *[lite::cv::detection::YoloV5](#lite.ai-object-detection)*. Have a good travel ~ 🙃🤪🍀
+*Lite.AI* 🚀🚀🌟 is a simple and user-friendly C++ library of awesome🔥🔥🔥 AI models. It's a collection of personal interests. such as YOLOX, YoloV5, YoloV4, DeepLabV3, ArcFace, etc. *Lite.AI* 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-object-detection), [face detection](#lite.ai-face-detection), [style transfer](#lite.ai-style-transfer), [face alignment](#lite.ai-face-alignment), [face recognition](#lite.ai-face-recognition), [segmentation](#lite.ai-segmentation), [colorization](#lite.ai-colorization), [face attributes analysis](#lite.ai-face-attributes-analysis), [image classification](#lite.ai-image-classification), [matting](#lite.ai-matting), etc. You can use these awesome models simply through *lite::cv::Type::Class* syntax, such as *[lite::cv::detection::YoloV5](#lite.ai-object-detection)*. Star 🌟👆🏻 this repo if it does any helps to you ~ Have a good travel ~ 🙃🤪🍀
 
 ## Important Notes !!!  
 
@@ -310,23 +310,6 @@ For example, ArcFace in [insightface](https://github.com/deepinsight/insightface
 |[SSDMobileNetV1](https://github.com/onnx/models/blob/master/vision/object_detection_segmentation/ssd-mobilenetv1)|27M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-object-detection) | *detection* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ssd_mobilenetv1.cpp) |
 |[YoloX](https://github.com/Megvii-BaseDetection/YOLOX)|3.5M| [YOLOX]( https://github.com/Megvii-BaseDetection/YOLOX) | 🔥🔥new↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-object-detection) | *detection* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_yolox.cpp) |
 
-<details>
-<summary> ⚠️ Expand More Details for Lite.AI's Model Zoo.</summary>  
-
-* Classification.
-
-|Class|Size|From|Awesome|File|Type|State|Usage|
-|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-|[EfficientNetLite4](https://github.com/onnx/models/blob/master/vision/classification/efficientnet-lite4)|49M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficientnet_lite4.cpp) |
-|[ShuffleNetV2](https://github.com/onnx/models/blob/master/vision/classification/shufflenet)|8.7M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_shufflenetv2.cpp) |
-|[DenseNet121](https://pytorch.org/hub/pytorch_vision_densenet/)|30.7M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_densenet.cpp) |
-|[GhostNet](https://pytorch.org/hub/pytorch_vision_ghostnet/)|20M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ghostnet.cpp) |
-|[HdrDNet](https://pytorch.org/hub/pytorch_vision_hardnet//)|13M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification) | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_hardnet.cpp) |
-|[IBNNet](https://pytorch.org/hub/pytorch_vision_ibnnet/)|97M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ibnnet.cpp) |
-|[MobileNetV2](https://pytorch.org/hub/pytorch_vision_mobilenet_v2/)|13M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_mobilenetv2.cpp) |
-|[ResNet](https://pytorch.org/hub/pytorch_vision_resnet/)|44M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_resnet.cpp) |
-|[ResNeXt](https://pytorch.org/hub/pytorch_vision_resnext/)|95M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_resnext.cpp) |
-
 
 * Face Detection.  
 
@@ -349,22 +332,6 @@ For example, ArcFace in [insightface](https://github.com/deepinsight/insightface
 |[FaceLandmark1000](https://github.com/Single430/FaceLandmark1000)|2.0M| [FaceLandm...](https://github.com/Single430/FaceLandmark1000) | 🔥↑ |  [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-alignment) | *face::align* | ✅️ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_face_landmarks_1000.cpp) |
 
 
-* Face Attributes.  
-
-|Class|Size|From|Awesome|File|Type|State|Usage|
-|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-|[AgeGoogleNet](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|23M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_age_googlenet.cpp) |
-|[GenderGoogleNet](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|23M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_gender_googlenet.cpp) |
-|[EmotionFerPlus](https://github.com/onnx/models/blob/master/vision/body_analysis/emotion_ferplus)|33M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_emotion_ferplus.cpp) |
-|[VGG16Age](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|514M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_vgg16_age.cpp) |
-|[VGG16Gender](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|512M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_vgg16_gender.cpp) |
-|[SSRNet](https://github.com/oukohou/SSR_Net_Pytorch)|190K| [SSR_Net...](https://github.com/oukohou/SSR_Net_Pytorch) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ssrnet.cpp) |
-|[EfficientEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|15M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅️ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficient_emotion7.cpp) |
-|[EfficientEmotion8](https://github.com/HSE-asavchenko/face-emotion-recognition)|15M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficient_emotion8.cpp) |
-|[MobileEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|13M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* |  ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_mobile_emotion7.cpp) |
-|[ReXNetEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|30M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* |  ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_rexnet_emotion7.cpp) |
-
-
 * Face Recognition.  
 
 |Class|Size|From|Awesome|File|Type|State|Usage|
@@ -386,6 +353,9 @@ For example, ArcFace in [insightface](https://github.com/deepinsight/insightface
 |[CavaCombinedFace](https://github.com/cavalleria/cavaface.pytorch)| 250M | [cavaface...](https://github.com/cavalleria/cavaface.pytorch) |  🔥🔥↑  | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-recognition) | *faceid* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_cava_combined_face.cpp) |
 |[MobileSEFocalFace](https://github.com/grib0ed0v/face_recognition.pytorch)|4.5M| [face_recog...](https://github.com/grib0ed0v/face_recognition.pytorch) | 🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-recognition) | *faceid* | ✅ |  [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_mobilese_focal_face.cpp) |
 
+<details>
+<summary> ⚠️ Expand More Details for Lite.AI's Model Zoo.</summary>  
+
 
 * Head Pose Estimation.  
 
@@ -394,6 +364,37 @@ For example, ArcFace in [insightface](https://github.com/deepinsight/insightface
 |[FSANet](https://github.com/omasaht/headpose-fsanet-pytorch)|1.2M| [...fsanet...](https://github.com/omasaht/headpose-fsanet-pytorch) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-head-pose-estimation) | *face::pose* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_fsanet.cpp) |  
 
 
+* Face Attributes.
+
+|Class|Size|From|Awesome|File|Type|State|Usage|
+|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+|[AgeGoogleNet](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|23M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_age_googlenet.cpp) |
+|[GenderGoogleNet](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|23M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_gender_googlenet.cpp) |
+|[EmotionFerPlus](https://github.com/onnx/models/blob/master/vision/body_analysis/emotion_ferplus)|33M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_emotion_ferplus.cpp) |
+|[VGG16Age](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|514M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_vgg16_age.cpp) |
+|[VGG16Gender](https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender)|512M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_vgg16_gender.cpp) |
+|[SSRNet](https://github.com/oukohou/SSR_Net_Pytorch)|190K| [SSR_Net...](https://github.com/oukohou/SSR_Net_Pytorch) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ssrnet.cpp) |
+|[EfficientEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|15M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅️ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficient_emotion7.cpp) |
+|[EfficientEmotion8](https://github.com/HSE-asavchenko/face-emotion-recognition)|15M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* | ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficient_emotion8.cpp) |
+|[MobileEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|13M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* |  ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_mobile_emotion7.cpp) |
+|[ReXNetEmotion7](https://github.com/HSE-asavchenko/face-emotion-recognition)|30M| [face-emo...](https://github.com/HSE-asavchenko/face-emotion-recognition) | 🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-face-attributes) | *face::attr* |  ✅  | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_rexnet_emotion7.cpp) |
+
+
+* Classification.
+
+|Class|Size|From|Awesome|File|Type|State|Usage|
+|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+|[EfficientNetLite4](https://github.com/onnx/models/blob/master/vision/classification/efficientnet-lite4)|49M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_efficientnet_lite4.cpp) |
+|[ShuffleNetV2](https://github.com/onnx/models/blob/master/vision/classification/shufflenet)|8.7M|        [onnx-models](https://github.com/onnx/models)         | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_shufflenetv2.cpp) |
+|[DenseNet121](https://pytorch.org/hub/pytorch_vision_densenet/)|30.7M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_densenet.cpp) |
+|[GhostNet](https://pytorch.org/hub/pytorch_vision_ghostnet/)|20M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ghostnet.cpp) |
+|[HdrDNet](https://pytorch.org/hub/pytorch_vision_hardnet//)|13M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification) | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_hardnet.cpp) |
+|[IBNNet](https://pytorch.org/hub/pytorch_vision_ibnnet/)|97M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_ibnnet.cpp) |
+|[MobileNetV2](https://pytorch.org/hub/pytorch_vision_mobilenet_v2/)|13M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_mobilenetv2.cpp) |
+|[ResNet](https://pytorch.org/hub/pytorch_vision_resnet/)|44M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_resnet.cpp) |
+|[ResNeXt](https://pytorch.org/hub/pytorch_vision_resnext/)|95M|       [torchvision](https://github.com/pytorch/vision)       | 🔥🔥🔥↑ | [![](https://img.shields.io/badge/onnx-done-brightgreen.svg)](https://github.com/DefTruth/lite.ai/tree/main/docs/hub/lite.ai.hub.onnx.md#lite.ai.hub.onnx-classification)  | *classification* | ✅ | [demo](https://github.com/DefTruth/lite.ai/blob/main/examples/lite/cv/test_lite_resnext.cpp) |
+
+
 * Segmentation.   
 
 |Class|Size|From|Awesome|File|Type|State|Usage|
@@ -528,13 +529,88 @@ The output is:
   <img src='logs/test_lite_siggraph17_colorizer_1.jpg' height="224px" width="224px">
   <img src='logs/test_lite_siggraph17_colorizer_2.jpg' height="224px" width="224px">
   <img src='logs/test_lite_siggraph17_colorizer_3.jpg' height="224px" width="224px">
-</div>  
+</div>    
 
 <div id="lite.ai-face-recognition"></div>  
+
+#### Example3: Face Recognition using [ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch). Download model from Model-Zoo[<sup>2</sup>](#lite.ai-2).
+
+```c++
+#include "lite/lite.h"
+
+static void test_default()
+{
+  std::string onnx_path = "../../../hub/onnx/cv/ms1mv3_arcface_r100.onnx";
+  std::string test_img_path0 = "../../../examples/lite/resources/test_lite_faceid_0.png";
+  std::string test_img_path1 = "../../../examples/lite/resources/test_lite_faceid_1.png";
+  std::string test_img_path2 = "../../../examples/lite/resources/test_lite_faceid_2.png";
+
+  auto *glint_arcface = new lite::cv::faceid::GlintArcFace(onnx_path);
+
+  lite::cv::types::FaceContent face_content0, face_content1, face_content2;
+  cv::Mat img_bgr0 = cv::imread(test_img_path0);
+  cv::Mat img_bgr1 = cv::imread(test_img_path1);
+  cv::Mat img_bgr2 = cv::imread(test_img_path2);
+  glint_arcface->detect(img_bgr0, face_content0);
+  glint_arcface->detect(img_bgr1, face_content1);
+  glint_arcface->detect(img_bgr2, face_content2);
+
+  if (face_content0.flag && face_content1.flag && face_content2.flag)
+  {
+    float sim01 = lite::cv::utils::math::cosine_similarity<float>(
+        face_content0.embedding, face_content1.embedding);
+    float sim02 = lite::cv::utils::math::cosine_similarity<float>(
+        face_content0.embedding, face_content2.embedding);
+    std::cout << "Detected Sim01: " << sim  << " Sim02: " << sim02 << std::endl;
+  }
+
+  delete glint_arcface;
+}
+```
+
+The output is:
+<div align='center'>
+  <img src='examples/lite/resources/test_lite_arcface_resnet_0.png' height="224px" width="224px">
+  <img src='examples/lite/resources/test_lite_arcface_resnet_1.png' height="224px" width="224px">
+  <img src='examples/lite/resources/test_lite_arcface_resnet_2.png' height="224px" width="224px">
+</div>  
+
+> Detected Sim01: 0.721159  Sim02: -0.0626267  
+
+<div id="lite.ai-face-detection"></div>
+
+#### Example4: Face Detection using [UltraFace](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB). Download model from Model-Zoo[<sup>2</sup>](#lite.ai-2).
+```c++
+#include "lite/lite.h"
+
+static void test_default()
+{
+  std::string onnx_path = "../../../hub/onnx/cv/ultraface-rfb-640.onnx";
+  std::string test_img_path = "../../../examples/lite/resources/test_lite_ultraface.jpg";
+  std::string save_img_path = "../../../logs/test_lite_ultraface.jpg";
+
+  auto *ultraface = new lite::cv::face::detect::UltraFace(onnx_path);
+
+  std::vector<lite::cv::types::Boxf> detected_boxes;
+  cv::Mat img_bgr = cv::imread(test_img_path);
+  ultraface->detect(img_bgr, detected_boxes);
+  lite::cv::utils::draw_boxes_inplace(img_bgr, detected_boxes);
+  cv::imwrite(save_img_path, img_bgr);
+
+  delete ultraface;
+}
+```
+The output is:
+<div align='center'>
+  <img src='logs/test_lite_ultraface.jpg' height="224px" width="224px">
+  <img src='logs/test_lite_ultraface_2.jpg' height="224px" width="224px">
+  <img src='logs/test_lite_ultraface_3.jpg' height="224px" width="224px">
+</div>  
+
+
 <div id="lite.ai-segmentation"></div>  
 <div id="lite.ai-face-attributes-analysis"></div>  
 <div id="lite.ai-image-classification"></div>  
-<div id="lite.ai-face-detection"></div>
 <div id="lite.ai-head-pose-estimation"></div>
 <div id="lite.ai-style-transfer"></div>
 <div id="lite.ai-matting"></div>