π **Lite.Ai.ToolKit**: A lite C++ toolkit of 100+ Awesome AI models, such as [Object Detection](#lite.ai.toolkit-object-detection), [Face Detection](#lite.ai.toolkit-face-detection), [Face Recognition](#lite.ai.toolkit-face-recognition), [Segmentation](#lite.ai.toolkit-segmentation), [Matting](#lite.ai.toolkit-matting), etc. See [Model Zoo](#lite.ai.toolkit-Model-Zoo) and [ONNX Hub](https://github.com/xlite-dev/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.onnx.md), [MNN Hub](https://github.com/xlite-dev/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.mnn.md), [TNN Hub](https://github.com/xlite-dev/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.tnn.md), [NCNN Hub](https://github.com/xlite-dev/lite.ai.toolkit/tree/main/docs/hub/lite.ai.toolkit.hub.ncnn.md). Welcome to πππ»star this repo to support me, many thanks ~ ππ
Or you can use Newest π₯π₯ ! YOLO series's detector [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) or [YoloR](https://github.com/WongKinYiu/yolor). They got the similar results.
More classes for general object detection (80 classes, COCO).
```
/* Detailed source-code truncated for AI context efficiency. */
```
****
#### Example1: Video Matting using [RobustVideoMatting2021π₯π₯π₯](https://github.com/PeterL1n/RobustVideoMatting). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/rvm_mobilenetv3_fp32.onnx";
std::string video_path = "../../../examples/lite/resources/test_lite_rvm_0.mp4";
std::string output_path = "../../../examples/logs/test_lite_rvm_0.mp4";
std::string background_path = "../../../examples/lite/resources/test_lite_matting_bgr.jpg";
auto *rvm = new lite::cv::matting::RobustVideoMatting(onnx_path, 16); // 16 threads
std::vector contents;
// 1. video matting.
cv::Mat background = cv::imread(background_path);
rvm->detect_video(video_path, output_path, contents, false, 0.4f,
20, true, true, background);
delete rvm;
}
```
The output is:
More classes for matting (image matting, video matting, trimap/mask-free, trimap/mask-based)
```c++
auto *matting = new lite::cv::matting::RobustVideoMatting:(onnx_path); // WACV 2022.
auto *matting = new lite::cv::matting::MGMatting(onnx_path); // CVPR 2021
auto *matting = new lite::cv::matting::MODNet(onnx_path); // AAAI 2022
auto *matting = new lite::cv::matting::MODNetDyn(onnx_path); // AAAI 2022 Dynamic Shape Inference.
auto *matting = new lite::cv::matting::BackgroundMattingV2(onnx_path); // CVPR 2020
auto *matting = new lite::cv::matting::BackgroundMattingV2Dyn(onnx_path); // CVPR 2020 Dynamic Shape Inference.
auto *matting = new lite::cv::matting::MobileHumanMatting(onnx_path); // 3Mb only !!!
```
****
#### Example2: 1000 Facial Landmarks Detection using [FaceLandmarks1000](https://github.com/Single430/FaceLandmark1000). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/FaceLandmark1000.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_face_landmarks_0.png";
std::string save_img_path = "../../../examples/logs/test_lite_face_landmarks_1000.jpg";
auto *face_landmarks_1000 = new lite::cv::face::align::FaceLandmark1000(onnx_path);
lite::types::Landmarks landmarks;
cv::Mat img_bgr = cv::imread(test_img_path);
face_landmarks_1000->detect(img_bgr, landmarks);
lite::utils::draw_landmarks_inplace(img_bgr, landmarks);
cv::imwrite(save_img_path, img_bgr);
delete face_landmarks_1000;
}
```
The output is:
More classes for face alignment (68 points, 98 points, 106 points, 1000 points)
```c++
auto *align = new lite::cv::face::align::PFLD(onnx_path); // 106 landmarks, 1.0Mb only!
auto *align = new lite::cv::face::align::PFLD98(onnx_path); // 98 landmarks, 4.8Mb only!
auto *align = new lite::cv::face::align::PFLD68(onnx_path); // 68 landmarks, 2.8Mb only!
auto *align = new lite::cv::face::align::MobileNetV268(onnx_path); // 68 landmarks, 9.4Mb only!
auto *align = new lite::cv::face::align::MobileNetV2SE68(onnx_path); // 68 landmarks, 11Mb only!
auto *align = new lite::cv::face::align::FaceLandmark1000(onnx_path); // 1000 landmarks, 2.0Mb only!
auto *align = new lite::cv::face::align::PIPNet98(onnx_path); // 98 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet68(onnx_path); // 68 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet29(onnx_path); // 29 landmarks, CVPR2021!
auto *align = new lite::cv::face::align::PIPNet19(onnx_path); // 19 landmarks, CVPR2021!
```
****
#### Example3: Colorization using [colorization](https://github.com/richzhang/colorization). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/eccv16-colorizer.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_colorizer_1.jpg";
std::string save_img_path = "../../../examples/logs/test_lite_eccv16_colorizer_1.jpg";
auto *colorizer = new lite::cv::colorization::Colorizer(onnx_path);
cv::Mat img_bgr = cv::imread(test_img_path);
lite::types::ColorizeContent colorize_content;
colorizer->detect(img_bgr, colorize_content);
if (colorize_content.flag) cv::imwrite(save_img_path, colorize_content.mat);
delete colorizer;
}
```
The output is:
More classes for colorization (gray to rgb)
```c++
auto *colorizer = new lite::cv::colorization::Colorizer(onnx_path);
```
****
#### Example4: Face Recognition using [ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/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::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::utils::math::cosine_similarity(
face_content0.embedding, face_content1.embedding);
float sim02 = lite::utils::math::cosine_similarity(
face_content0.embedding, face_content2.embedding);
std::cout << "Detected Sim01: " << sim << " Sim02: " << sim02 << std::endl;
}
delete glint_arcface;
}
```
The output is:
> Detected Sim01: 0.721159 Sim02: -0.0626267
More classes for face recognition (face id vector extract)
```c++
auto *recognition = new lite::cv::faceid::GlintCosFace(onnx_path); // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::GlintArcFace(onnx_path); // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::GlintPartialFC(onnx_path); // DeepGlint(insightface)
auto *recognition = new lite::cv::faceid::FaceNet(onnx_path);
auto *recognition = new lite::cv::faceid::FocalArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::FocalAsiaArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::TencentCurricularFace(onnx_path); // Tencent(TFace)
auto *recognition = new lite::cv::faceid::TencentCifpFace(onnx_path); // Tencent(TFace)
auto *recognition = new lite::cv::faceid::CenterLossFace(onnx_path);
auto *recognition = new lite::cv::faceid::SphereFace(onnx_path);
auto *recognition = new lite::cv::faceid::PoseRobustFace(onnx_path);
auto *recognition = new lite::cv::faceid::NaivePoseRobustFace(onnx_path);
auto *recognition = new lite::cv::faceid::MobileFaceNet(onnx_path); // 3.8Mb only !
auto *recognition = new lite::cv::faceid::CavaGhostArcFace(onnx_path);
auto *recognition = new lite::cv::faceid::CavaCombinedFace(onnx_path);
auto *recognition = new lite::cv::faceid::MobileSEFocalFace(onnx_path); // 4.5Mb only !
```
****
#### Example5: Face Detection using [SCRFD 2021](https://github.com/deepinsight/insightface/blob/master/detection/scrfd/). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/scrfd_2.5g_bnkps_shape640x640.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_face_detector.jpg";
std::string save_img_path = "../../../examples/logs/test_lite_scrfd.jpg";
auto *scrfd = new lite::cv::face::detect::SCRFD(onnx_path);
std::vector detected_boxes;
cv::Mat img_bgr = cv::imread(test_img_path);
scrfd->detect(img_bgr, detected_boxes);
lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);
cv::imwrite(save_img_path, img_bgr);
delete scrfd;
}
```
The output is:
More classes for face detection (super fast face detection)
```c++
auto *detector = new lite::face::detect::UltraFace(onnx_path); // 1.1Mb only !
auto *detector = new lite::face::detect::FaceBoxes(onnx_path); // 3.8Mb only !
auto *detector = new lite::face::detect::FaceBoxesv2(onnx_path); // 4.0Mb only !
auto *detector = new lite::face::detect::RetinaFace(onnx_path); // 1.6Mb only ! CVPR2020
auto *detector = new lite::face::detect::SCRFD(onnx_path); // 2.5Mb only ! CVPR2021, Super fast and accurate!!
auto *detector = new lite::face::detect::YOLO5Face(onnx_path); // 2021, Super fast and accurate!!
auto *detector = new lite::face::detect::YOLOv5BlazeFace(onnx_path); // 2021, Super fast and accurate!!
```
****
#### Example6: Object Segmentation using [DeepLabV3ResNet101](https://pytorch.org/hub/pytorch_vision_deeplabv3_resnet101/). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/deeplabv3_resnet101_coco.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_deeplabv3_resnet101.png";
std::string save_img_path = "../../../examples/logs/test_lite_deeplabv3_resnet101.jpg";
auto *deeplabv3_resnet101 = new lite::cv::segmentation::DeepLabV3ResNet101(onnx_path, 16); // 16 threads
lite::types::SegmentContent content;
cv::Mat img_bgr = cv::imread(test_img_path);
deeplabv3_resnet101->detect(img_bgr, content);
if (content.flag)
{
cv::Mat out_img;
cv::addWeighted(img_bgr, 0.2, content.color_mat, 0.8, 0., out_img);
cv::imwrite(save_img_path, out_img);
if (!content.names_map.empty())
{
for (auto it = content.names_map.begin(); it != content.names_map.end(); ++it)
{
std::cout << it->first << " Name: " << it->second << std::endl;
}
}
}
delete deeplabv3_resnet101;
}
```
The output is:
More classes for object segmentation (general objects segmentation)
```c++
auto *segment = new lite::cv::segmentation::FCNResNet101(onnx_path);
auto *segment = new lite::cv::segmentation::DeepLabV3ResNet101(onnx_path);
```
****
#### Example7: Age Estimation using [SSRNet](https://github.com/oukohou/SSR_Net_Pytorch) . Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/ssrnet.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_ssrnet.jpg";
std::string save_img_path = "../../../examples/logs/test_lite_ssrnet.jpg";
auto *ssrnet = new lite::cv::face::attr::SSRNet(onnx_path);
lite::types::Age age;
cv::Mat img_bgr = cv::imread(test_img_path);
ssrnet->detect(img_bgr, age);
lite::utils::draw_age_inplace(img_bgr, age);
cv::imwrite(save_img_path, img_bgr);
delete ssrnet;
}
```
The output is:
More classes for face attributes analysis (age, gender, emotion)
```c++
auto *attribute = new lite::cv::face::attr::AgeGoogleNet(onnx_path);
auto *attribute = new lite::cv::face::attr::GenderGoogleNet(onnx_path);
auto *attribute = new lite::cv::face::attr::EmotionFerPlus(onnx_path);
auto *attribute = new lite::cv::face::attr::VGG16Age(onnx_path);
auto *attribute = new lite::cv::face::attr::VGG16Gender(onnx_path);
auto *attribute = new lite::cv::face::attr::EfficientEmotion7(onnx_path); // 7 emotions, 15Mb only!
auto *attribute = new lite::cv::face::attr::EfficientEmotion8(onnx_path); // 8 emotions, 15Mb only!
auto *attribute = new lite::cv::face::attr::MobileEmotion7(onnx_path); // 7 emotions, 13Mb only!
auto *attribute = new lite::cv::face::attr::ReXNetEmotion7(onnx_path); // 7 emotions
auto *attribute = new lite::cv::face::attr::SSRNet(onnx_path); // age estimation, 190kb only!!!
```
****
#### Example8: 1000 Classes Classification using [DenseNet](https://pytorch.org/hub/pytorch_vision_densenet/). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/densenet121.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_densenet.jpg";
auto *densenet = new lite::cv::classification::DenseNet(onnx_path);
lite::types::ImageNetContent content;
cv::Mat img_bgr = cv::imread(test_img_path);
densenet->detect(img_bgr, content);
if (content.flag)
{
const unsigned int top_k = content.scores.size();
if (top_k > 0)
{
for (unsigned int i = 0; i < top_k; ++i)
std::cout << i + 1
<< ": " << content.labels.at(i)
<< ": " << content.texts.at(i)
<< ": " << content.scores.at(i)
<< std::endl;
}
}
delete densenet;
}
```
The output is:
More classes for image classification (1000 classes)
```c++
auto *classifier = new lite::cv::classification::EfficientNetLite4(onnx_path);
auto *classifier = new lite::cv::classification::ShuffleNetV2(onnx_path); // 8.7Mb only!
auto *classifier = new lite::cv::classification::GhostNet(onnx_path);
auto *classifier = new lite::cv::classification::HdrDNet(onnx_path);
auto *classifier = new lite::cv::classification::IBNNet(onnx_path);
auto *classifier = new lite::cv::classification::MobileNetV2(onnx_path); // 13Mb only!
auto *classifier = new lite::cv::classification::ResNet(onnx_path);
auto *classifier = new lite::cv::classification::ResNeXt(onnx_path);
```
****
#### Example9: Head Pose Estimation using [FSANet](https://github.com/omasaht/headpose-fsanet-pytorch). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/fsanet-var.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_fsanet.jpg";
std::string save_img_path = "../../../examples/logs/test_lite_fsanet.jpg";
auto *fsanet = new lite::cv::face::pose::FSANet(onnx_path);
cv::Mat img_bgr = cv::imread(test_img_path);
lite::types::EulerAngles euler_angles;
fsanet->detect(img_bgr, euler_angles);
if (euler_angles.flag)
{
lite::utils::draw_axis_inplace(img_bgr, euler_angles);
cv::imwrite(save_img_path, img_bgr);
std::cout << "yaw:" << euler_angles.yaw << " pitch:" << euler_angles.pitch << " row:" << euler_angles.roll << std::endl;
}
delete fsanet;
}
```
The output is:
More classes for head pose estimation (euler angle, yaw, pitch, roll)
```c++
auto *pose = new lite::cv::face::pose::FSANet(onnx_path); // 1.2Mb only!
```
****
#### Example10: Style Transfer using [FastStyleTransfer](https://github.com/onnx/models/tree/master/vision/style_transfer/fast_neural_style). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/style-candy-8.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_fast_style_transfer.jpg";
std::string save_img_path = "../../../examples/logs/test_lite_fast_style_transfer_candy.jpg";
auto *fast_style_transfer = new lite::cv::style::FastStyleTransfer(onnx_path);
lite::types::StyleContent style_content;
cv::Mat img_bgr = cv::imread(test_img_path);
fast_style_transfer->detect(img_bgr, style_content);
if (style_content.flag) cv::imwrite(save_img_path, style_content.mat);
delete fast_style_transfer;
}
```
The output is:
More classes for style transfer (neural style transfer, others)
```c++
auto *transfer = new lite::cv::style::FastStyleTransfer(onnx_path); // 6.4Mb only
```
****
#### Example11: Human Head Segmentation using [HeadSeg](https://github.com/minivision-ai/photo2cartoon). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/minivision_head_seg.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_head_seg.png";
std::string save_img_path = "../../../examples/logs/test_lite_head_seg.jpg";
auto *head_seg = new lite::cv::segmentation::HeadSeg(onnx_path, 4); // 4 threads
lite::types::HeadSegContent content;
cv::Mat img_bgr = cv::imread(test_img_path);
head_seg->detect(img_bgr, content);
if (content.flag) cv::imwrite(save_img_path, content.mask * 255.f);
delete head_seg;
}
```
The output is:
More classes for human segmentation (head, portrait, hair, others)
```c++
auto *segment = new lite::cv::segmentation::HeadSeg(onnx_path); // 31Mb
auto *segment = new lite::cv::segmentation::FastPortraitSeg(onnx_path); // <= 400Kb !!!
auto *segment = new lite::cv::segmentation::PortraitSegSINet(onnx_path); // <= 380Kb !!!
auto *segment = new lite::cv::segmentation::PortraitSegExtremeC3Net(onnx_path); // <= 180Kb !!! Extreme Tiny !!!
auto *segment = new lite::cv::segmentation::FaceHairSeg(onnx_path); // 18M
auto *segment = new lite::cv::segmentation::HairSeg(onnx_path); // 18M
auto *segment = new lite::cv::segmentation::MobileHairSeg(onnx_path); // 14M
```
****
#### Example12: Photo transfer to Cartoon [Photo2Cartoon](https://github.com/minivision-ai/photo2cartoon). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string head_seg_onnx_path = "../../../examples/hub/onnx/cv/minivision_head_seg.onnx";
std::string cartoon_onnx_path = "../../../examples/hub/onnx/cv/minivision_female_photo2cartoon.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_female_photo2cartoon.jpg";
std::string save_mask_path = "../../../examples/logs/test_lite_female_photo2cartoon_seg.jpg";
std::string save_cartoon_path = "../../../examples/logs/test_lite_female_photo2cartoon_cartoon.jpg";
auto *head_seg = new lite::cv::segmentation::HeadSeg(head_seg_onnx_path, 4); // 4 threads
auto *female_photo2cartoon = new lite::cv::style::FemalePhoto2Cartoon(cartoon_onnx_path, 4); // 4 threads
lite::types::HeadSegContent head_seg_content;
cv::Mat img_bgr = cv::imread(test_img_path);
head_seg->detect(img_bgr, head_seg_content);
if (head_seg_content.flag && !head_seg_content.mask.empty())
{
cv::imwrite(save_mask_path, head_seg_content.mask * 255.f);
// Female Photo2Cartoon Style Transfer
lite::types::FemalePhoto2CartoonContent female_cartoon_content;
female_photo2cartoon->detect(img_bgr, head_seg_content.mask, female_cartoon_content);
if (female_cartoon_content.flag && !female_cartoon_content.cartoon.empty())
cv::imwrite(save_cartoon_path, female_cartoon_content.cartoon);
}
delete head_seg;
delete female_photo2cartoon;
}
```
The output is:
More classes for photo style transfer.
```c++
auto *transfer = new lite::cv::style::FemalePhoto2Cartoon(onnx_path);
```
****
#### Example13: Face Parsing using [FaceParsing](https://github.com/zllrunning/face-parsing.PyTorch). Download model from Model-Zoo[2](#lite.ai.toolkit-2).
```c++
#include "lite/lite.h"
static void test_default()
{
std::string onnx_path = "../../../examples/hub/onnx/cv/face_parsing_512x512.onnx";
std::string test_img_path = "../../../examples/lite/resources/test_lite_face_parsing.png";
std::string save_img_path = "../../../examples/logs/test_lite_face_parsing_bisenet.jpg";
auto *face_parsing_bisenet = new lite::cv::segmentation::FaceParsingBiSeNet(onnx_path, 8); // 8 threads
lite::types::FaceParsingContent content;
cv::Mat img_bgr = cv::imread(test_img_path);
face_parsing_bisenet->detect(img_bgr, content);
if (content.flag && !content.merge.empty())
cv::imwrite(save_img_path, content.merge);
delete face_parsing_bisenet;
}
```
The output is:
