DOHA-HWANG

ALBFL

awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

code2vec

A PyTorch implementation of `code2vec: Learning Distributed Representations of Code` (Alon et al., 2018)

code2vec-1

TensorFlow code for the neural network presented in the paper: "code2vec: Learning Distributed Representations of Code"

CodeBERT

CodeBERT

Cream

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

DAQ

An official PyTorch implementation of the paper "Distance-aware Quantization", ICCV 2021.

Deep-Learning-Paper-Review-and-Practice

꼼꼼한 딥러닝 논문 리뷰와 코드 실습

deeprl4fl-2021-icse

DSQ

pytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"

DOHA-HWANG/awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

DOHA-HWANG/code2vec-1

TensorFlow code for the neural network presented in the paper: "code2vec: Learning Distributed Representations of Code"

DOHA-HWANG/CodeBERT

CodeBERT

DOHA-HWANG/Cream

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

DOHA-HWANG/DAQ

An official PyTorch implementation of the paper "Distance-aware Quantization", ICCV 2021.

DOHA-HWANG/Deep-Learning-Paper-Review-and-Practice

꼼꼼한 딥러닝 논문 리뷰와 코드 실습

DOHA-HWANG/deeprl4fl-2021-icse

DOHA-HWANG/EWGS

An official implementation of "Network Quantization with Element-wise Gradient Scaling" (CVPR 2021) in PyTorch.

DOHA-HWANG/FQ-ViT

The official implementation for "FQ-ViT: Fully Quantized Vision Transformer without Retraining".

DOHA-HWANG/ghn3

Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?"

DOHA-HWANG/HAWQ

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

DOHA-HWANG/I-BERT

[ICML'21 Oral] I-BERT: Integer-only BERT Quantization

DOHA-HWANG/Intriguing-Properties-of-Vision-Transformers

Official repository for "Intriguing Properties of Vision Transformers" (NeurIPS 2021--Spotlight)

DOHA-HWANG/lightweightViT

VIT is a lightweight, fast, curses-based front end to Taskwarrior

DOHA-HWANG/mini-imagenet-tools

Tools for generating mini-ImageNet dataset and processing batches

DOHA-HWANG/ppuda

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

DOHA-HWANG/pt.darts

PyTorch Implementation of DARTS: Differentiable Architecture Search

DOHA-HWANG/PyChatGPT

⚡️ Python client for the unofficial ChatGPT API with auto token regeneration, conversation tracking, proxy support and more.

DOHA-HWANG/PyHessian

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

DOHA-HWANG/pytorch-cifar

95.47% on CIFAR10 with PyTorch

DOHA-HWANG/pytorch-cifar100

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

DOHA-HWANG/pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

DOHA-HWANG/QBERT

DOHA-HWANG/SOFT

[NeurIPS 2021 Spotlight] SOFT: Softmax-free Transformer with Linear Complexity

DOHA-HWANG/subpruning

DOHA-HWANG/TRANSFER

Fault localization and automated program repair techniques

DOHA-HWANG/transformer-quantization

DOHA-HWANG/vision-transformers-cifar10

Let's train vision transformers (ViT) for cifar 10!

DOHA-HWANG/ViT

Implementing Vi(sion)T(transformer)

DOHA-HWANG/ViT-CIFAR

PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).