Discover sseung0703/Lightweighting_Cookbook Open Source project

Stars
23
Rank 985,382 (Top 20 %)
Language
Python
Created almost 2 years ago
Updated almost 2 years ago

sseung0703

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

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.

Knowledge_distillation_via_TF2.0

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

Python

104

Zero-shot_Knowledge_Distillation

Zero-Shot Knowledge Distillation in Deep Networks in ICML2019

Python

SSKD_SVD

Python

GALA_TF2.0

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

Python

Variational_Information_Distillation

Reproducing VID in CVPR2019 (on working)

Python

TF2-jit-compile-on-multi-gpu

Tensorflow2 training code with jit compiling on multi-GPU.

Python

EKG

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

Python

ADNet-tensorflow

Python

Google_Colab_tutorial

Google Colab tutorial with simple network training and Tensorboard.

Jupyter Notebook

Autoslim_TF2

Implementation of Autoslim using Tensorflow2

Python

MHGD

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

SSKD

IEPKT

Implementation of "Interpretable embedding procedure knowledge transfer" on AAAI2021

Python

sseung0703.github.io

SCSS

tensorflow2.0_wo_keras

Python

CNN_via_Tensorflow2_low-level

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

Python

ACCESS_KD

This project solves a problem of ZSKT in neurips2019

Jupyter Notebook

aingo03304.github.io

Minjae's Blog

CSS

sseung0703

sseung0703/Lightweighting_Cookbook

sseung0703

Reviews

Repository Details

More Repositories