Discover @sseung0703 Open Source projects

Seunghyun Lee (@sseung0703)

sseung0703

Stars
691
Global Rank 43,418 (Top 2 %)
Followers 93
Following 11
Registered over 7 years ago
Most used languages

Python
77.8 %

Jupyter Notebook
11.1 %

CSS
5.6 %

SCSS 5.6 %
Location 🇰🇷 South Korea
Country Total Rank 349
Country Ranking

SCSS 55

Python
109

Jupyter Notebook
494

CSS
1,625

KD_methods_with_TF

Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)

Knowledge_distillation_via_TF2.0

The codes for recent knowledge distillation algorithms and benchmark results via TF2.0 low-level API

Zero-shot_Knowledge_Distillation

Zero-Shot Knowledge Distillation in Deep Networks in ICML2019

SSKD_SVD

GALA_TF2.0

Tensorflow 2.0 implementation of "Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning" in ICCV2019

Lightweighting_Cookbook

This project attempts to build neural network training and lightweighting cookbook including three kinds of lightweighting solutions, i.e., knowledge distillation, filter pruning, and quantization.

Variational_Information_Distillation

Reproducing VID in CVPR2019 (on working)

TF2-jit-compile-on-multi-gpu

Tensorflow2 training code with jit compiling on multi-GPU.

EKG

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

ADNet-tensorflow

Google_Colab_tutorial

Google Colab tutorial with simple network training and Tensorboard.

Jupyter Notebook

Autoslim_TF2

Implementation of Autoslim using Tensorflow2

MHGD

the presentation materials for Multi-head Graph Distillation ( BMVC2019 oral )

SSKD

IEPKT

Implementation of "Interpretable embedding procedure knowledge transfer" on AAAI2021

sseung0703.github.io

tensorflow2.0_wo_keras

CNN_via_Tensorflow2_low-level

Colvolutional neural network implementation with Tensorflow2.0 low level API only

ACCESS_KD

This project solves a problem of ZSKT in neurips2019

Jupyter Notebook

aingo03304.github.io

sseung0703