模型压缩与优化,移动端模型部署's starred repositories
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
text-generation-inference
Large Language Model Text Generation Inference
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
annotated-transformer
An annotated implementation of the Transformer paper.
FACEGOOD-Audio2Face
http://www.facegood.cc
minimal-hand
A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.
Awesome-Image-Colorization
:books: A collection of Deep Learning based Image Colorization and Video Colorization papers.
tflite_gles_app
GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT
Minimal-Hand-pytorch
PyTorch reimplementation of minimal-hand (CVPR2020)
hand_tracking_samples
:wave: :ok_hand: research codebase for depth-based hand pose estimation using dynamics based tracking and CNNs
PhysCap_demo_release
PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time The implementation is based on [SIGGRAPH Aisa'20](https://vcai.mpi-inf.mpg.de/projects/PhysCap/).
Nonrigid-ICP-Pytorch
Non-rigid alignment of two depth scans using Adam
non_rigid_icp
Modified version of non-rigid Iterative closest point algorithm for fitting to noisy point clouds
sphereHand
This project corresponds to __Self-supervised 3D hand pose estimation through training by fitting__, which is accepted in CVPR 2019.