ShuLiu1993

mmdeploy

OpenMMLab Model Deployment Framework

poolformer

PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)

turicreate

Turi Create simplifies the development of custom machine learning models.

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

ImageNet21K

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

ppuda

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

g2o

g2o: A General Framework for Graph Optimization

Cream

This is a collection of our NAS and Vision Transformer work.

FLAML

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

open-box

Generalized and Efficient Blackbox Optimization System

triton

Development repository for the Triton language and compiler

YOLOX

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

YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLO ModelCompression MultidatasetTraining

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

fairscale

PyTorch extensions for high performance and large scale training.

d2go

D2Go is a toolkit for efficient deep learning

determined

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

ultraopt

Distributed Asynchronous Hyperparameter Optimization better than HyperOpt. 比HyperOpt更强的分布式异步超参优化库。

Auto-PyTorch

Automatic architecture search and hyperparameter optimization for PyTorch

mobile-vision

Mobile vision models and code

autoalbument

AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/

model_search

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

zenml

ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

optuna

A hyperparameter optimization framework

HAWQ

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

cml

♾️ CML - Continuous Machine Learning | CI/CD for ML

deit

Official DeiT repository

cvpods

All-in-one Toolbox for Computer Vision Research.