Skip to main content
Help the Python Software Foundation raise $60,000 USD by December 31st!  Building the PSF Q4 Fundraiser

No project description provided

Project description


PyTorchFI

BackgroundUsageCodeContributorsCitationLicense

Background

PyTorchFI is a runtime perturbation tool for deep neural networks (DNNs), implemented for the popular PyTorch deep learning platform. PyTorchFI enables users to perform perturbation on weights or neurons of a DNN during runtime. It is extremely versatile for dependability and reliability research, with applications including resiliency analysis of classification networks, resiliency analysis of object detection networks, analysis of models robust to adversarial attacks, training resilient models, and for DNN interpertability.

For example, this is an object detection network before a fault injection

Golden Output Output with Fault Injection

Usage

Download on PyPI here, or take a look at our documentation at pytorchfi.github.io.

Installing

From Pip

Install using pip install pytorchfi

From Source

Download this repository into your project folder.

Importing

Import the entire package:

import pytorchfi

Import a specific module:

from pytorchfi import core

Testing

pytest

Code

Structure

The main source code of PyTorchFI is held in pytorchfi, which carries both core and util implementations.

Formatting

All python code is formatted with black.

Contributors

Before contributing, please refer to our contributing guidelines.

Citation

View the published paper. If you use or reference PyTorchFI, please cite:

@INPROCEEDINGS{9151812,
author={A. {Mahmoud} and N. {Aggarwal} and A. {Nobbe} and J. R. S. {Vicarte} and S. V. {Adve} and C. W. {Fletcher} and I. {Frosio} and S. K. S. {Hari}},
booktitle={2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)},
title={PyTorchFI: A Runtime Perturbation Tool for DNNs},
year={2020},
pages={25-31},
}

Funding Sources

This project was funded in part by the Applications Driving Architectures (ADA) Research Center, a JUMP Center co-sponsored by SRC and DARPA, and in collaboration with NVIDIA Research.

License

NCSA License. Copyright © 2020 RSim Research Group.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pytorchfi, version 0.3.0
Filename, size File type Python version Upload date Hashes
Filename, size pytorchfi-0.3.0-py3-none-any.whl (16.9 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size pytorchfi-0.3.0.tar.gz (13.0 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page