pdh930105

ZeBRA

awesome-reparameterize

6DRepNet

Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.

AFPQ

AFPQ code implementation

bfp_transformers_pl

bit

Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer

cutlass

CUDA Templates for Linear Algebra Subroutines

diffq

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

dof_inference

dof_inference

DyNAS-T

Dynamic Neural Architecture Search Toolkit

efficient-ai-study

Efficient-Computing

Efficient-Computing

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

FQ-ViT

[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

I-ViT

[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

kjh_bfp_test

kjh_bfp_test

LBC

Pytorch implementation of our paper accepted by NeurIPS 2022 -- Learning Best Combination for Efficient N:M Sparsity

lightning-hydra-wandb-template

lightning_simple_test

lightweight-neural-architecture-search

This is a collection of our zero-cost NAS and efficient vision applications.

mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

ml-cvnets

CVNets: A library for training computer vision networks

MultiQuant

arbitrary bit-width quantization; network quantization; model compression

Q-ViT-deit

DeiT implementation for Q-ViT

QPyTorch

Low Precision Arithmetic Simulation in PyTorch

Reparam

RepQ-ViT

[ICCV 2023] RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers

TBN

TBNv2: Convolutional Neural Network With Ternary Inputs and Binary Weights

torchinfo

View model summaries in PyTorch!

yolov7-face

yolov7 face detection with landmark