tonysy

Deep-Feature-Flow-Segmentation

Deep Feature Flow for Video Semantic Segmentation

PyAction

A Toolkit for Video Action Recognition(Classification/Detection)

STANet-PyTorch

A Dual Attention Network with Semantic Embedding for Few-shot Learning(AAAI 2019)

PyTransformer

A Collection of the Popular Vision Transformer Structure with Support for Downstream Tasks.

tonysy.github.io

accv_storage

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

CMMLU

cvpods

All-in-one Toolbox for Computer Vision Research.

dotfiles

Collection of configuration used on Mac or Linux(dot files)

ecosystem

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

InternLM

InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

LEval

Data and code for L-Eval, a comprehensive long context language models evaluation benchmark

LongBench

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

lvis-api

Python API for LVIS Dataset

mmclassification

OpenMMLab Image Classification Toolbox and Benchmark

mmdetection

Open MMLab Detection Toolbox and Benchmark

mmediting

MMEditing is a low-level vision toolbox based on PyTorch, supporting super-resolution, inpainting, matting, video interpolation, etc.

mmengine

OpenMMLab Foundational Library for Training Deep Learning Models

mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.

pre-commit-hooks

tonysy

TransformerCompression

For releasing code related to compression methods for transformers, accompanying our publications

tutorial

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM)

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported.