Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

Last update: Dec 18, 2022

Related tags

Overview

HKD

Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

cifia-100 result

The implementation of compared methods are based on the author-provided code and a open-source benchmark https://github.com/HobbitLong/RepDistiller.

Installation

conda install --yes --file requirements.txt

Running

Fetch the pretrained teacher models by:
```
sh scripts/fetch_pretrained_teachers.sh
```
which will download and save the models to save/models

Run distillation by commands in scripts\run_cifar_distill.sh. An example of running HKD is given by:

python train_student.py --path_t ./save/models/resnet32x4_vanilla/ckpt_epoch_240.pth --distill hkd --model_s resnet8x4 -a 1 -b 3 --mode hkd --trial 1

Citation

The final version of the paper will also be released soon.

Owner

Wang Yucheng

It leads my burning heart to a dark side-road.

GitHub Repository

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations Implementation of the method described in the Speech Resynthesis from Di

253 Jan 06, 2023

Multi Task RL Baselines

MTRL Multi Task RL Algorithms Contents Introduction Setup Usage Documentation Contributing to MTRL Community Acknowledgements Introduction M

171 Jan 09, 2023

Make a Turtlebot3 follow a figure 8 trajectory and create a robot arm and make it follow a trajectory

HW2 - ME 495 Overview Part 1: Makes the robot move in a figure 8 shape. The robot starts moving when launched on a real turtlebot3 and can be paused a

0 Oct 21, 2022

A 2D Visual Localization Framework based on Essential Matrices [ICRA2020]

A 2D Visual Localization Framework based on Essential Matrices This repository provides implementation of our paper accepted at ICRA: To Learn or Not

27 Nov 07, 2022

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval (NeurIPS'21)

Baleen Baleen is a state-of-the-art model for multi-hop reasoning, enabling scalable multi-hop search over massive collections for knowledge-intensive

22 Dec 05, 2022

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Self Supervised Learning with Fastai Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks. Install pip install self-

276 Dec 23, 2022

VOGUE: Try-On by StyleGAN Interpolation Optimization

VOGUE is a StyleGAN interpolation optimization algorithm for photo-realistic try-on. Top: shirt try-on automatically synthesized by our method in two different examples.

66 Dec 09, 2022

GluonMM is a library of transformer models for computer vision and multi-modality research

GluonMM is a library of transformer models for computer vision and multi-modality research. It contains reference implementations of widely adopted baseline models and also research work from Amazon

42 Dec 02, 2022

The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"

Hierarchical Token Semantic Audio Transformer Introduction The Code Repository for "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound

134 Jan 01, 2023

Unofficial PyTorch implementation of Guided Dropout

Unofficial PyTorch implementation of Guided Dropout This is a simple implementation of Guided Dropout for research. We try to reproduce the algorithm

2 Jan 07, 2022

Age Progression/Regression by Conditional Adversarial Autoencoder

Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE) TensorFlow implementation of the algorithm in the paper Age Progression/Regre

603 Dec 22, 2022

TorchX is a library containing standard DSLs for authoring and running PyTorch related components for an E2E production ML pipeline.

TorchX is a library containing standard DSLs for authoring and running PyTorch related components for an E2E production ML pipeline

193 Dec 22, 2022

Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

Related tags

Overview

HKD

cifia-100 result

Installation

Running

Citation

Owner

Wang Yucheng

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Multi Task RL Baselines

Make a Turtlebot3 follow a figure 8 trajectory and create a robot arm and make it follow a trajectory

A 2D Visual Localization Framework based on Essential Matrices [ICRA2020]

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval (NeurIPS'21)

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

VOGUE: Try-On by StyleGAN Interpolation Optimization

GluonMM is a library of transformer models for computer vision and multi-modality research

The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"

Unofficial PyTorch implementation of Guided Dropout

Age Progression/Regression by Conditional Adversarial Autoencoder

TorchX is a library containing standard DSLs for authoring and running PyTorch related components for an E2E production ML pipeline.

PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.

A keras implementation of ENet (abandoned for the foreseeable future)

GAN example for Keras. Cuz MNIST is too small and there should be something more realistic.

Supervised 3D Pre-training on Large-scale 2D Natural Image Datasets for 3D Medical Image Analysis

Interactive Image Generation via Generative Adversarial Networks

Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

The Most Efficient Temporal Difference Learning Framework for 2048

OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis