pdh930105

6DRepNet

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

adabits_simple

simple adabits test

AFPQ

AFPQ code implementation

and_yolotest

awesome-reparameterize

BFA

Pytorch implementation of Bit-Flip based adversarial weight Attack (BFA)

bfp_transformers_pl

bit

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

cafe_with_memories

ZeBRA

pdh930105/ZeBRA

pdh930105/awesome-reparameterize

pdh930105/6DRepNet

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

pdh930105/AFPQ

AFPQ code implementation

pdh930105/bfp_transformers_pl

pdh930105/bit

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

pdh930105/cutlass

CUDA Templates for Linear Algebra Subroutines

pdh930105/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.

pdh930105/dof_inference

dof_inference

pdh930105/DyNAS-T

Dynamic Neural Architecture Search Toolkit

pdh930105/efficient-ai-study

pdh930105/Efficient-Computing

Efficient-Computing

pdh930105/flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

pdh930105/FQ-ViT

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

pdh930105/I-ViT

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

pdh930105/kjh_bfp_test

kjh_bfp_test

pdh930105/LBC

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

pdh930105/lightning-hydra-wandb-template

pdh930105/lightning_simple_test

pdh930105/lightweight-neural-architecture-search

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

pdh930105/lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

pdh930105/mcunet

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

pdh930105/ml-cvnets

CVNets: A library for training computer vision networks

pdh930105/MultiQuant

arbitrary bit-width quantization; network quantization; model compression

pdh930105/Q-ViT-deit

DeiT implementation for Q-ViT

pdh930105/Reparam

pdh930105/RepQ-ViT

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

pdh930105/TBN

TBNv2: Convolutional Neural Network With Ternary Inputs and Binary Weights

pdh930105/torchinfo

View model summaries in PyTorch!

pdh930105/yolov7-face

yolov7 face detection with landmark