ty1231
Follow
Stars
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
State-of-the-art 2D and 3D Face Analysis Project
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Image augmentation for machine learning experiments.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Keras code and weights files for popular deep learning models.
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
A treasure chest for visual classification and recognition powered by PaddlePaddle
Torchreid: Deep learning person re-identification in PyTorch.
⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
SOTA Re-identification Methods and Toolbox
RepVGG: Making VGG-style ConvNets Great Again
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
Scaled-YOLOv4: Scaling Cross Stage Partial Network
mobilenetv3 with pytorch，provide pre-train model
静默活体检测（Silent-Face-Anti-Spoofing）
A trusty face analysis research platform developed by Tencent Youtu Lab
👫 Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) 👫
Code for 3rd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019,model only 0.35M!!! 1.88ms(CPU)
[ICCV-2021] TransReID: Transformer-based Object Re-Identification
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
FaceBagNet - Patch-based Methods for Multi-modal Face Anti-spoofing (FAS)
ChaLearn Face Anti-spoofing Attack Detection Challenge@CVPR2019
A simple method for face alignment based on wingloss and mutitask learning :)
Unsupervised Pre-training for Person Re-identification (LUPerson)