Pytorch implementation for Patient Knowledge Distillation for BERT Model Compression

Overview

Patient Knowledge Distillation for BERT Model Compression

Knowledge distillation for BERT model

Installation

Run command below to install the environment

conda install pytorch torchvision cudatoolkit=10.0 -c pytorch
pip install -r requirements.txt

Training

Objective Function

L = (1 - \alpha) L_CE + \alpha * L_DS + \beta * L_PT,

where L_CE is the CrossEntropy loss, DS is the usual Distillation loss, and PT is the proposed loss. Please see our paper below for more details.

Data Preprocess

Modify the HOME_DATA_FOLDER in envs.py and put all data under it (by default it is ./data), RTE data is uploaded for your convenience.

  • The folder name under HOME_DATA_FOLDER should be
    • data_raw: store the raw datas of all tasks. So put downloaded raw data under here
      • MRPC
      • RTE
      • ... (other tasks)
    • data_feat: store the tokenized data under this folder (optional)
      • MRPC
      • RTE
      • ...
  • models
    • pretrained: put downloaded pretrained model (bert-base-uncased) under this folder

Predefinted Training

Run NLI_KD_training.py to start training, you can set DEBUG = True to run some pre-defined arguments

  • set argv = get_predefine_argv('glue', 'RTE', 'finetune_teacher') or argv = get_predefine_argv('glue', 'RTE', 'finetune_student') to start the normal fine-tuning
  • run run_glue_benchmark.py to get teacher's prediction for KD or PKD.
    • set output_all_layers = True for patient teacher
    • set output_all_layers = False for normal teacher
  • set argv = get_predefine_argv('glue', 'RTE', 'kd') to start the vanilla KD
  • set argv = get_predefine_argv('glue', 'RTE', 'kd.cls') to start the vanilla KD

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

Citation

If you find this code useful for your research, please consider citing:

@article{sun2019patient,
title={Patient Knowledge Distillation for BERT Model Compression},
author={Sun, Siqi and Cheng, Yu and Gan, Zhe and Liu, Jingjing},
journal={arXiv preprint arXiv:1908.09355},
year={2019}
}

Paper is available at here.

Owner
Siqi
Siqi
Official implementation of VaxNeRF (Voxel-Accelearated NeRF).

VaxNeRF Paper | Google Colab This is the official implementation of VaxNeRF (Voxel-Accelearated NeRF). VaxNeRF provides very fast training and slightl

naruya 132 Nov 21, 2022
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis

iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis Andreas Bl

CompVis Heidelberg 36 Dec 25, 2022
Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers

Visual Parser (ViP) This is the official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers. Key Feature

Shuyang Sun 117 Dec 11, 2022
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

DART Implementation for ICLR2022 paper Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners. Environment

ZJUNLP 83 Dec 27, 2022
Implementing DeepMind's Fast Reinforcement Learning paper

Fast Reinforcement Learning This is a repo where I implement the algorithms in the paper, Fast reinforcement learning with generalized policy updates.

Marcus Chiam 6 Nov 28, 2022
A simple code to perform canny edge contrast detection on images.

CECED-Canny-Edge-Contrast-Enhanced-Detection A simple code to perform canny edge contrast detection on images. A simple code to process images using c

Happy N. Monday 3 Feb 15, 2022
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

DeCLIP Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm. Our paper is available in arxiv Updates ** Ou

Sense-GVT 470 Dec 30, 2022
Multi Agent Reinforcement Learning for ROS in 2D Simulation Environments

IROS21 information To test the code and reproduce the experiments, follow the installation steps in Installation.md. Afterwards, follow the steps in E

11 Oct 29, 2022
We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

Auto-exposure fusion for single-image shadow removal We propose a new method for effective shadow removal by regarding it as an exposure fusion proble

Qing Guo 146 Dec 31, 2022
STEM: An approach to Multi-source Domain Adaptation with Guarantees

STEM: An approach to Multi-source Domain Adaptation with Guarantees Introduction This is the official implementation of ``STEM: An approach to Multi-s

5 Dec 19, 2022
Blind Video Temporal Consistency via Deep Video Prior

deep-video-prior (DVP) Code for NeurIPS 2020 paper: Blind Video Temporal Consistency via Deep Video Prior PyTorch implementation | paper | project web

Chenyang LEI 272 Dec 21, 2022
Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

Spacetimeformer Multivariate Forecasting This repository contains the code for the paper, "Long-Range Transformers for Dynamic Spatiotemporal Forecast

QData 440 Jan 02, 2023
Mmdetection3d Noted - MMDetection3D is an open source object detection toolbox based on PyTorch

MMDetection3D is an open source object detection toolbox based on PyTorch

Jiangjingwen 13 Jan 06, 2023
Lepard: Learning Partial point cloud matching in Rigid and Deformable scenes

Lepard: Learning Partial point cloud matching in Rigid and Deformable scenes [Paper] Method overview 4DMatch Benchmark 4DMatch is a benchmark for matc

103 Jan 06, 2023
CVPR2021 Content-Aware GAN Compression

Content-Aware GAN Compression [ArXiv] Paper accepted to CVPR2021. @inproceedings{liu2021content, title = {Content-Aware GAN Compression}, auth

52 Nov 06, 2022
Activity image-based video retrieval

Cross-modal-retrieval Our approach is focus on Activity Image-to-Video Retrieval (AIVR) task. The compared methods are state-of-the-art single modalit

BCMI 75 Oct 21, 2021
Yolov5 deepsort inference,使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中

使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中。

813 Dec 31, 2022
This repository contains the data and code for the paper "Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors" ([email protected])

GP-VAE This repository provides datasets and code for preprocessing, training and testing models for the paper: Diverse Text Generation via Variationa

Wanyu Du 18 Dec 29, 2022
OneFlow is a performance-centered and open-source deep learning framework.

OneFlow OneFlow is a performance-centered and open-source deep learning framework. Latest News Version 0.5.0 is out! First class support for eager exe

OneFlow 4.2k Jan 07, 2023
Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura, Hiroki Ohashi, and Tomoaki Yosh

105 Dec 23, 2022