Li Lai's repositories
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
SmoothNet
This is an official implementation for "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos" (ECCV 2022)
yolov5_obb
yolov5 + csl_label.(Oriented Object Detection)(Rotation Detection)(Rotated BBox)基于yolov5的旋转目标检测
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
digest
R package to create compact hash digests of R objects
movenet.pytorch
A Pytorch implementation of MoveNet from Google. Include training code and pre-trained model.
SummaryOfLoanSuspension
全国各省市停贷通知汇总
MiniMeta
数字人开源项目 (Digital human project)
awesome-ncnn
😎 A Collection of Awesome NCNN-based Projects
rotate-yolov5-opencv-onnxrun
分别使用OpenCV、ONNXRuntime部署yolov5旋转目标检测,包含C++和Python两个版本的程序
BlazePose_torch
pytorch implement of google blazePose
ganhacks
starter from "How to Train a GAN?" at NIPS2016
External-Attention-pytorch
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
PocketNet
PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation
3DDFA_V2
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
Class-balanced-loss-pytorch
Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"
vision
Datasets, Transforms and Models specific to Computer Vision
speed_up_pytorch
简单易懂、且通用的 加速pytorch 的 training 方法
MaskTheFace
Convert face dataset to masked dataset
face-parsing.PyTorch
Using modified BiSeNet for face parsing in PyTorch
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
RepVGG-caffe
此网只应天上有,人间能得几回训Making VGG-style ConvNets Great Again (Caffe)
models
Models and examples built with TensorFlow
AnchorFace
AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses(AAAI 2021)
Ultra-Light-Fast-Generic-Face-Detector-1MB
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)