daquexian Claim this profile

OneFlow is a performance-centered and open-source deep learning framework.

Open Neural Network Exchange

No description.

A language server based on gtags

A view showing LaTeX, images, codes... You can customize tags as you want

《数据结构与算法分析：C语言描述》答案中文版

No description.

Chaoli Forum Android app

No description.

[Deprecated] Convert caffemodel to DNNLibrary's daq format

An example app of DNNLibrary :)

A drop-in replacement for `codex resume` that shows local sessions across providers

No description.

Files received in QQ, telegram, or images downloaded in WeChat, will all appear in download manager

Temporary repo to play around with Github's new merge queue. Will be deleted soon.

ONNX Runtime: cross-platform, high performance scoring engine for ML models

For myself

Tengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.

**[WIP]** Vim plugin for project configuration managing like JetBrains IDEs

AndroidFlux+Retrofit+RxJava+Dagger2

No description.

real time face swap and one-click video deepfake with only a single image (uncensored)

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

No description.

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.

中科院软件所智能软件中心实习生社区

博客啦～

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

🇨🇳 Chinese translation for vuejs.org

Convert TensorFlow models to ONNX

Tensors and Dynamic neural networks in Python with strong GPU acceleration

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

Googletest - Google Testing and Mocking Framework

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

No description.

Sui, a next-generation smart contract platform with high throughput, low latency, and an asset-oriented programming model powered by the Move programming language

The clmm sdk on Sui.

Development repository for the Triton language and compiler

No description.

Vast.ai python and cli api client

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

No description.

No description.

通过MXNet/Gluon来动手学习深度学习

Transform ONNX model to PyTorch representation

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

No description.

No description.

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

OpenMMLab Detection Toolbox and Benchmark

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

OpenMMLab Image Classification Toolbox and Benchmark

a copilot.vim fork that plays better with coc.nvim

Multi-platform high performance deep learning inference engine (飞桨多端多平台高性能深度学习推理引擎）

PaddlePaddle Developer Community

Haskell library for the Microsoft Language Server Protocol

Defines a common protocol for language servers.

a pythonic generic language server

面向产业应用的AI开源评测基准

Clean & Elegant Color Scheme inspired by Atom One and Material

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.

No description.

Fast Library for Approximate Nearest Neighbors

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

Tengine is a lite, high performance, modular inference engine for embedded device

The friendly PIL fork (Python Imaging Library)

Android NDK samples with Android Studio

fzf :heart: vim

Asynchronous linting/fixing for Vim and Language Server Protocol (LSP) integration

Simple, fast, safe, compiled language for developing maintainable software. Supports translation from C and (soon) C++. Compiles itself in <1s.

MNN is a lightweight deep neural network inference engine.

Source code of AppImage project's documentation

AndroidRate is a library to help you promote your Android app by prompting users to rate the app after using it for a few days.

No description.

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Language Server Protocol (LSP) support for vim & neovim, featured as VSCode

[EXPERIMENTAL]

async language server protocol plugin for vim and neovim

This convert tools is base on TensorRT 2.0 Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).

auto generate function definition or declaration

C++ wrapper around libcURL

For dnnlibrary testing

Caffe: a fast open framework for deep learning.

ONNX models

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Models and examples built with TensorFlow

Computation using data flow graphs for scalable machine learning

Firebase Cloud Messaging for Mojo-Webqq.

A Lightweight & Flexible Deep Learning (Neural Network) Framework in Python

FOPL 课期末大作业，仿照 POPL'11 的一篇文章-w-

K-9 Mail – Advanced Email for Android 📧

OpenKeychain is an OpenPGP implementation for Android.

at least solve one problem <del>every day</del>

The Google I/O 2015 Android App