PaRT: Parallel Learning for Robust and Transparent AI

Related tags

Deep LearningPaRT
Overview

PaRT: Parallel Learning for Robust and Transparent AI

This repository contains the code for PaRT, an algorithm for training a base network on multiple tasks in parallel. The diagram of PaRT is shown in the figure below.

Below, we provide details regarding dependencies and the instructions for running the code for each experiment. We have prepared scripts for each experiment to help the user have a smooth experience.

Dependencies

  • python >= 3.8
  • pytorch >= 1.7
  • scikit-learn
  • torchvision
  • tensorboard
  • matplotlib
  • pillow
  • psutil
  • scipy
  • numpy
  • tqdm

SETUP ENVIRONMENT

To setup the conda env and create the required directories go to the scripts directory and run the following commands in the terminal:

conda init bash
bash -i setupEnv.sh

Check that the final output of these commands is:

Installed torch version {---}
Virtual environment was made successfully

CIFAR 100 EXPERIMENTS

Instructions to run the code for the CIFAR100 experiments:

--------------------- BASELINE EXPERIMENTS ---------------------

To run the baseline experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i runCIFAR100Baseline.sh ../../scripts/test_case0_cifar100_baseline.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_cifar100_baseline.json to 1,2,3, or 4.

--------------------- PARALLEL EXPERIMENTS ---------------------

To run the parallel experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i runCIFAR100Parallel.sh ../../scripts/test_case0_cifar100_parallel.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_cifar100_parallel.json to 1,2,3, or 4.

CIFAR 10 AND CIFAR 100 EXPERIMENTS

Instructions to run the code for the CIFAR10 and CIFAR100 experiments:

--------------------- BASELINE EXPERIMENTS ---------------------

To run the parallel experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i runCIFAR10_100Baseline.sh ../../scripts/test_case0_cifar10_100_baseline.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_cifar10_100_baseline.json to 1,2,3, or 4.

--------------------- PARALLEL EXPERIMENTS ---------------------

To run the baseline experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i runCIFAR10_100Parallel.sh ../../scripts/test_case0_cifar10_100_parallel.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_cifar10_100_parallel.json to 1,2,3, or 4.

FIVETASKS EXPERIMENTS

The dataset for this experiment can be downloaded from the link provided by the CPG GitHub Page or Here. Instructions to run the code for the FiveTasks experiments:

--------------------- BASELINE EXPERIMENTS ---------------------

To run the baseline experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i run5TasksBaseline.sh ../../scripts/test_case0_5tasks_baseline.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_5tasks_baseline.json to 1,2,3, or 4.

--------------------- PARALLEL EXPERIMENTS ---------------------

To run the parallel experiments for the first seed, go to the scripts directory and run the following command in the terminal:

bash -i run5TasksParallel.sh ../../scripts/test_case0_5tasks_parallel.json

To run the experiment for other seeds, simply change the value of test_case in test_case0_5tasks_parallel.json to 1,2,3, or 4.

Paper

Please cite our paper:

Paknezhad, M., Rengarajan, H., Yuan, C., Suresh, S., Gupta, M., Ramasamy, S., Lee H. K., PaRT: Parallel Learning Towards Robust and Transparent AI, arXiv:2201.09534 (2022)

Owner
Mahsa
I develop DL, ML, computer vision, and image processing algorithms for problems in deep learning and medical domain.
Mahsa
Ground truth data for the Optical Character Recognition of Historical Classical Commentaries.

OCR Ground Truth for Historical Commentaries The dataset OCR ground truth for historical commentaries (GT4HistComment) was created from the public dom

Ajax Multi-Commentary 3 Sep 08, 2022
Face uncertainty quantification or estimation using PyTorch.

Face-uncertainty-pytorch This is a demo code of face uncertainty quantification or estimation using PyTorch. The uncertainty of face recognition is af

Kaen 3 Sep 16, 2022
Bridging Composite and Real: Towards End-to-end Deep Image Matting

Bridging Composite and Real: Towards End-to-end Deep Image Matting Please note that the official repository of the paper Bridging Composite and Real:

Jizhizi_Li 30 Oct 31, 2022
【ACMMM 2021】DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning (ACMMM 2021) Overview We release the code of the DSANet (Dynamic S

Wenhao Wu 46 Dec 27, 2022
FMA: A Dataset For Music Analysis

FMA: A Dataset For Music Analysis Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, Xavier Bresson. International Society for Music Information

Michaël Defferrard 1.8k Dec 29, 2022
Implementation of gaze tracking and demo

Predicting Customer Demand by Using Gaze Detecting and Object Tracking This project is the integration of gaze detecting and object tracking. Predict

2 Oct 20, 2022
Orchestrating Distributed Materials Acceleration Platform Tutorial

Orchestrating Distributed Materials Acceleration Platform Tutorial This tutorial for orchestrating distributed materials acceleration platform was pre

BIG-MAP 1 Jan 25, 2022
Make Watson Assistant send messages to your Discord Server

Make Watson Assistant send messages to your Discord Server Prerequisites Sign up for an IBM Cloud account. Fill in the required information and press

1 Jan 10, 2022
NaturalProofs: Mathematical Theorem Proving in Natural Language

NaturalProofs: Mathematical Theorem Proving in Natural Language NaturalProofs: Mathematical Theorem Proving in Natural Language Sean Welleck, Jiacheng

Sean Welleck 83 Jan 05, 2023
A Structured Self-attentive Sentence Embedding

Structured Self-attentive sentence embeddings Implementation for the paper A Structured Self-Attentive Sentence Embedding, which was published in ICLR

Kaushal Shetty 488 Nov 28, 2022
Stream images from a connected camera over MQTT, view using Streamlit, record to file and sqlite

mqtt-camera-streamer Summary: Publish frames from a connected camera or MJPEG/RTSP stream to an MQTT topic, and view the feed in a browser on another

Robin Cole 183 Dec 16, 2022
(AAAI2020)Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing This repository contains pytorch source code for AAAI2020 oral paper: Grapy-ML

54 Aug 04, 2022
Talk covering the features of skorch

Skorch Talk Skorch - A Union of Scikit-learn and PyTorch Presentation The slides can be downloaded at: download link. Google Colab Part One - MNIST Pa

Thomas J. Fan 3 Oct 20, 2020
Codes for NeurIPS 2021 paper "On the Equivalence between Neural Network and Support Vector Machine".

On the Equivalence between Neural Network and Support Vector Machine Codes for NeurIPS 2021 paper "On the Equivalence between Neural Network and Suppo

Leslie 8 Oct 25, 2022
Pytorch implementation of BRECQ, ICLR 2021

BRECQ Pytorch implementation of BRECQ, ICLR 2021 @inproceedings{ li&gong2021brecq, title={BRECQ: Pushing the Limit of Post-Training Quantization by Bl

Yuhang Li 148 Dec 28, 2022
Learning 3D Part Assembly from a Single Image

Learning 3D Part Assembly from a Single Image This repository contains a PyTorch implementation of the paper: Learning 3D Part Assembly from A Single

18 Dec 21, 2022
[NeurIPS 2021] PyTorch Code for Accelerating Robotic Reinforcement Learning with Parameterized Action Primitives

Robot Action Primitives (RAPS) This repository is the official implementation of Accelerating Robotic Reinforcement Learning via Parameterized Action

Murtaza Dalal 55 Dec 27, 2022
Generate Contextual Directory Wordlist For Target Org

PathPermutor Generate Contextual Directory Wordlist For Target Org This script generates contextual wordlist for any target org based on the set of UR

8 Jun 23, 2021
Hack Camera, Microphone, Location, Clipboard With Just a Link. Also, Get Many Details About Victim's Device. And So On...

An Automated Tool to Hack Victim's Camera, Microphone, Location, Clipboard. Has 2 Extra Features. Version 1.1 Update Fixed Some Major Bugs Data Saving

ToxicNoob 36 Jan 07, 2023