TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

Related tags

Deep Learningtensorflowkerasvisionimage-classificationtransfer-learningknowledge-distillationtpubit-resnet
Overview

FunMatch-Distillation

TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

The techniques have been demonstrated using three datasets:

This repository provides Kaggle Kernel notebooks so that we can leverage the free TPu v3-8 to run the long training schedules. Please refer to this section.

Importance

The importance of knowledge distillation lies in its practical usefulness. With the recipes from "function matching", we can now perform knowledge distillation using a principled approach yielding student models that can actually match the performance of their teacher models. This essentially allows us to compress bigger models into (much) smaller ones thereby reducing storage costs and improving inference speed.

Key ingredients

  • No use of ground-truth labels during distillation.
  • Teacher and student should see same images during distillation as opposed to differently augmented views of same images.
  • Aggressive form of MixUp as the key augmentation recipe. MixUp is paired with "Inception-style" cropping (implemented in this script).
  • A LONG training schedule for distillation. At least 1000 epochs to get good results without overfitting. The importance of a long training schedule is paramount as studied in the paper.

Results

The table below summarizes the results of my experiments. In all cases, teacher is a BiT-ResNet101x3 model and student is a BiT-ResNet50x1. For fun, you can also try to distill into other model families. BiT stands for "Big Transfer" and it was proposed in this paper.

Dataset Teacher/Student Top-1 Acc on Test Location
Flowers102 Teacher 98.18% Link
Flowers102 Student (1000 epochs) 81.02% Link
Pet37 Teacher 90.92% Link
Pet37 Student (300 epochs) 81.3% Link
Pet37 Student (1000 epochs) 86% Link
Food101 Teacher 85.52% Link
Food101 Student (100 epochs) 76.06% Link

(Location denotes the trained model location.)

These results are consistent with Table 4 of the original paper.

It should be noted that none of the above student training regimes showed signs of overfitting. Further improvements can be done by training for longer. The authors also showed that Shampoo can get to similar performance much quicker than Adam during distillation. So, it may very well be possible to get this performance with fewer epochs with Shampoo.

A few differences from the original implementation:

  • The authors use BiT-ResNet152x2 as a teacher.
  • The mixup() variant I used will produce a pair of duplicate images if the number of images is even. Now, for 8 workers it will become 8 pairs. This may have led to the reduced performance. We can overcome this by using tf.roll(images, 1, axis=0) instead of tf.reverse in the mixup() function. Thanks to Lucas Beyer for pointing this out.

About the notebooks

All the notebooks are fully runnable on Kaggle Kernel. The only requirement is that you'd need a billing enabled GCP account to use GCS Buckets to store data.

Notebook Description Kaggle Kernel
train_bit.ipynb Shows how to train the teacher model. Link
train_bit_keras_tuner.ipynb Shows how to run hyperparameter tuning using
Keras Tuner for the teacher model.		 Link
funmatch_distillation.ipynb Shows an implementation of the recipes
from "function matching".		 Link

These are only demonstrated on the Pet37 dataset but will work out-of-the-box for the other datasets too.

TFRecords

For convenience, TFRecords of different datasets are provided:

Dataset TFRecords
Flowers102 Link
Pet37 Link
Food101 Link

Paper citation

@misc{beyer2021knowledge,
      title={Knowledge distillation: A good teacher is patient and consistent}, 
      author={Lucas Beyer and Xiaohua Zhai and Amélie Royer and Larisa Markeeva and Rohan Anil and Alexander Kolesnikov},
      year={2021},
      eprint={2106.05237},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgements

Huge thanks to Lucas Beyer (first author of the paper) for providing suggestions on the initial version of the implementation.

Thanks to the ML-GDE program for providing GCP credits.

Thanks to TRC for providing Cloud TPU access.

You might also like...
Implementation of momentum^2 teacher

Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning Requirements All experiments are done with python3.6, torch

jemmy li 121 Sep 26, 2022
Code implementation of Data Efficient Stagewise Knowledge Distillation paper.
Code implementation of Data Efficient Stagewise Knowledge Distillation paper.

Data Efficient Stagewise Knowledge Distillation Table of Contents Data Efficient Stagewise Knowledge Distillation Table of Contents Requirements Image

IvLabs 112 Dec 2, 2022
The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation This repository is the official implementation of CVPR 2021 paper:

null 9 Nov 14, 2022
PyTorch implementation of paper A Fast Knowledge Distillation Framework for Visual Recognition.
PyTorch implementation of paper A Fast Knowledge Distillation Framework for Visual Recognition.

FKD: A Fast Knowledge Distillation Framework for Visual Recognition Official PyTorch implementation of paper A Fast Knowledge Distillation Framework f

Zhiqiang Shen 129 Dec 24, 2022
Official implementation of the paper
Official implementation of the paper "Lightweight Deep CNN for Natural Image Matting via Similarity Preserving Knowledge Distillation"

Lightweight-Deep-CNN-for-Natural-Image-Matting-via-Similarity-Preserving-Knowledge-Distillation Introduction Accepted at IEEE Signal Processing Letter

DongGeun-Yoon 19 Jun 7, 2022
Pcos-prediction - Predicts the likelihood of Polycystic Ovary Syndrome based on patient attributes and symptoms
Pcos-prediction - Predicts the likelihood of Polycystic Ovary Syndrome based on patient attributes and symptoms

PCOS Prediction 🥼 Predicts the likelihood of Polycystic Ovary Syndrome based on

Samantha Van Seters 1 Jan 10, 2022
[ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Undistillable: Making A Nasty Teacher That CANNOT teach students "Undistillable: Making A Nasty Teacher That CANNOT teach students" Haoyu Ma, Tianlong

VITA 71 Dec 28, 2022
Unet network with mean teacher for altrasound image segmentation

Unet network with mean teacher for altrasound image segmentation

null 5 Nov 21, 2022
Details about the wide minima density hypothesis and metrics to compute width of a minima

wide-minima-density-hypothesis Details about the wide minima density hypothesis and metrics to compute width of a minima This repo presents the wide m

Nikhil Iyer 9 Dec 27, 2022
Releases(v4.0.0)
Owner
Sayak Paul
Trying to learn how machines learn.
Sayak Paul
GitHub Repository
Official implementation of SynthTIGER (Synthetic Text Image GEneratoR) ICDAR 2021

🐯 SynthTIGER: Synthetic Text Image GEneratoR Official implementation of SynthTIGER | Paper | Datasets Moonbin Yim1, Yoonsik Kim1, Han-cheol Cho1, Sun

Clova AI Research 256 Jan 05, 2023
Source code of the paper Meta-learning with an Adaptive Task Scheduler.

ATS About Source code of the paper Meta-learning with an Adaptive Task Scheduler. If you find this repository useful in your research, please cite the

Huaxiu Yao 16 Dec 26, 2022
Source code for ZePHyR: Zero-shot Pose Hypothesis Rating @ ICRA 2021

ZePHyR: Zero-shot Pose Hypothesis Rating ZePHyR is a zero-shot 6D object pose estimation pipeline. The core is a learned scoring function that compare

R-Pad - Robots Perceiving and Doing 18 Aug 22, 2022
Deep Learning ❤️ OneFlow

Deep Learning with OneFlow made easy 🚀 ! Carefree? carefree-learn aims to provide CAREFREE usages for both users and developers. User Side Computer V

21 Oct 27, 2022
RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?

RaftMLP RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality? By Yuki Tatsunami and Masato Taki (Rikkyo University) [arxiv]

Okojo 20 Aug 31, 2022
This is the official repository of the paper Stocastic bandits with groups of similar arms (NeurIPS 2021). It contains the code that was used to compute the figures and experiments of the paper.

Experiments How to reproduce experimental results of Stochastic bandits with groups of similar arms submitted paper ? Section 5 of the paper To reprod

Fabien 0 Oct 25, 2021
Reference models and tools for Cloud TPUs.

Cloud TPUs This repository is a collection of reference models and tools used with Cloud TPUs. The fastest way to get started training a model on a Cl

5k Jan 05, 2023
Data, model training, and evaluation code for "PubTables-1M: Towards a universal dataset and metrics for training and evaluating table extraction models".

PubTables-1M This repository contains training and evaluation code for the paper "PubTables-1M: Towards a universal dataset and metrics for training a

Microsoft 365 Jan 04, 2023
LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation by Junjue Wang, Zhuo Zheng, Ailong Ma, Xiaoyan Lu, and Yanfei Zh

Payphone 8 Nov 21, 2022
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

ImageBART NeurIPS 2021 Patrick Esser*, Robin Rombach*, Andreas Blattmann*, Björn Ommer * equal contribution arXiv | BibTeX | Poster Requirements A sui

CompVis Heidelberg 110 Jan 01, 2023
Implementation of the state of the art beat-detection, downbeat-detection and tempo-estimation model

The ISMIR 2020 Beat Detection, Downbeat Detection and Tempo Estimation Model Implementation. This is an implementation in TensorFlow to implement the

Koen van den Brink 1 Nov 12, 2021
DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time

DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time Introduction This is official implementation for DR-GAN (IEEE TCS

Kang Liao 18 Dec 23, 2022
[CVPRW 21] "BNN - BN = ? Training Binary Neural Networks without Batch Normalization", Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

BNN - BN = ? Training Binary Neural Networks without Batch Normalization Codes for this paper BNN - BN = ? Training Binary Neural Networks without Bat

VITA 40 Dec 30, 2022
Reproduces the results of the paper "Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations".

Finite basis physics-informed neural networks (FBPINNs) This repository reproduces the results of the paper Finite Basis Physics-Informed Neural Netwo

Ben Moseley 65 Dec 28, 2022
Like a cowsay but without cows!

Foxsay This is a simple program that generates pictures of a cute fox with a message. It is like a cowsay but without cows! Fox girls are better! Usag

Anastasia Kim 28 Feb 20, 2022
Official Pytorch implementation for "End2End Occluded Face Recognition by Masking Corrupted Features, TPAMI 2021"

End2End Occluded Face Recognition by Masking Corrupted Features This is the Pytorch implementation of our TPAMI 2021 paper End2End Occluded Face Recog

Haibo Qiu 25 Oct 31, 2022
LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

LightHuBERT LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT | Github | Huggingface | SUPER

WangRui 46 Dec 29, 2022
[ACM MM 2021] Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers Installation pip install -r requirements.txt Dataset Preparation Given the

Yingchen Yu 25 Nov 09, 2022
Model search is a framework that implements AutoML algorithms for model architecture search at scale

Model search (MS) is a framework that implements AutoML algorithms for model architecture search at scale. It aims to help researchers speed up their exploration process for finding the right model a

Google 3.2k Dec 31, 2022
Implementation for the paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR2021).

Invertible Image Denoising This is the PyTorch implementation of paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR 20

157 Dec 25, 2022