rog93

rog93's Stars

• dongzhuoyao/admm_nn

  Training Neural Networks Without Gradients: A Scalable ADMM Approach python implement

  Language:Python153

• numpy/numpy

  The fundamental package for scientific computing with Python.

  Language:Python28.4k10.2k

• frankxu2004/gpt-neox

  An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

  Language:Python176

• VHellendoorn/Code-LMs

  Guide to using pre-trained large language models of source code

  Language:Python1.8k252

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python10.9k2.4k

• facebookresearch/fairseq

  Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

  Language:Python30.7k6.4k

• microsoft/SPACH

  Language:Python19628

• volcengine/veGiantModel

  Language:Python21224

• chengyangfu/retinamask

  RetinaMask

  Language:Python33952

• hpcaitech/ColossalAI

  Making large AI models cheaper, faster and more accessible

  Language:Python39k4.3k

• Oneflow-Inc/oneflow

  OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

  Language:C++6.4k713

• OpenPPL/ppq

  PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

  Language:Python1.6k239

• njuhope/cuda_sgemm

  Language:Cuda10629

• zhilin007/FFA-Net

  FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

  Language:Python611143

• facebookresearch/ConvNeXt

  Code release for ConvNeXt model

  Language:Python5.8k701

• yunxiaoshi/Neural-IMage-Assessment

  A PyTorch Implementation of Neural IMage Assessment

  Language:Python54095

• truskovskiyk/nima.pytorch

  NIMA: Neural IMage Assessment

  Language:Python33779

• onnx/onnx-tensorrt

  ONNX-TensorRT: TensorRT backend for ONNX

  Language:C++3k546

• shouxieai/tensorRT_Pro

  C++ library based on tensorrt integration

  Language:C++2.6k550

• open-mmlab/mmdeploy

  OpenMMLab Model Deployment Framework

  Language:Python2.8k643

• pengzhiliang/MAE-pytorch

  Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

  Language:Python2.6k342

• open-mmlab/mmgeneration

  MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

  Language:Python1.9k233

• SwinTransformer/Video-Swin-Transformer

  This is an official implementation for "Video Swin Transformers".

  Language:Python1.5k201

• bes-dev/pytorch_clip_guided_loss

  A simple library that implements CLIP guided loss in PyTorch.

  Language:Python775

• DanceTrack/DanceTrack

  [CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

  Language:Python39538

• ray-project/ray

  Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

  Language:Python34.6k5.9k

• PeterL1n/RobustVideoMatting

  Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

  Language:Python8.7k1.1k

• PeterL1n/BackgroundMattingV2

  Real-Time High-Resolution Background Matting

  Language:Python6.9k954

• microsoft/NUWA

  A unified 3D Transformer Pipeline for visual synthesis

  2.8k162

• 666DZY666/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

  Language:Python2.2k478