deep-learning-plan Goto Github PK

aichess

使用alphazero算法打造属于你自己的象棋AI

aitemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

cchess-zero

AlphaZero implemented Chinese chess. AlphaGo Zero / AlphaZero实践项目，实现**象棋。

chinese-chess-ai

A Chinese Chess program and a AI based on Monte Carlo Tree Search and Neural Network（like AlphaGo）一个**象棋程序和一个配套的基于蒙特卡洛算法及神经网络的人工智能（模仿阿尔法狗）

dali

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

dcnv2_trt

TensorRT plugin forDCNv2 layer in ONNX model

deeplearningexamples

Deep Learning Examples

evidently

Evaluate and monitor ML models from validation to production. Join our Discord: https://discord.com/invite/xZjKRaNp8b

feast

Feature Store for Machine Learning

gradio

Create UIs for your machine learning model in Python in 3 minutes

lego51515blearduinotensorflow

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, MODNet, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

mlrun

Machine Learning automation and tracking

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mobilevit_tensorrt

mst-plus-plus-tensorrt

:poodle: :poodle: :poodle: TensorRT 2022复赛方案： 首个基于Transformer的图像重建模型MST++的TensorRT模型推断优化

nuclio

High-Performance Serverless event and data processing platform

onnx-modifier

A tool to modify onnx models in a visualization fashion, based on Netron and flask.

opentransformer

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

pinferencia

Python + Inference - Model Deployment library in Python. Simplest model inference server ever.

ppl.cv

ppl.cv is a high-performance image processing library of openPPL supporting various platforms.

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

serving

A flexible, high-performance carrier for machine learning models（『飞桨』服务化部署框架）

stable-diffusion-webui

Stable Diffusion web UI

streamlit

Streamlit — The fastest way to build data apps in Python

towhee

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

unicorn

[ECCV'22 Oral] Towards Grand Unification of Object Tracking