Skip to main content

The Deep Data Profilerlibrary provides tools for analyzing the internal decision structure of a trained deep neural network.

Project description

The Deep Data Profiling (DDP) library provides tools for analyzing the internal decision structure of a trained deep neural network. The library was inspired by the work of Qiu, et al. in Adversarial Defense Through Network Profiling Based Path Extraction (2019), arXiv:1904.08089. Full documentation may be found at https://pnnl.github.io/DeepDataProfiler.

DDP contains code for generating graphical representations and feature visualizations, for VGG-like sequential and ResNet models implemented in PyTorch. DDP also provides tools from topological data analysis for analysis of these representations.

Notice

The research used in this repository is part of the Mathematics of Artificial Reasoning in Science (MARS) Initiative at Pacific Northwest National Laboratory (PNNL). It was conducted under the Laboratory Directed Research and Development Program at PNNL, a multiprogram national laboratory operated by Battelle for the U.S. Department of Energy.

Neither the United States Government nor the United States Department of Energy, nor Battelle, nor any of their employees, nor any jurisdiction or organization that has cooperated in the development of these materials, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness or any information, apparatus, product, software, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof, or Battelle Memorial Institute. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.

PACIFIC NORTHWEST NATIONAL LABORATORY operated by BATTELLE for the UNITED STATES DEPARTMENT OF ENERGY under Contract DE-AC05-76RL01830

Project details


Download files

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

Source Distribution

deep_data_profiler-2.0.1.tar.gz (50.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

deep_data_profiler-2.0.1-py3-none-any.whl (58.6 kB view details)

Uploaded Python 3

File details

Details for the file deep_data_profiler-2.0.1.tar.gz.

File metadata

  • Download URL: deep_data_profiler-2.0.1.tar.gz
  • Upload date:
  • Size: 50.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.8.13

File hashes

Hashes for deep_data_profiler-2.0.1.tar.gz
Algorithm Hash digest
SHA256 0eb294a2ea684af3bc612f7135ffa0fad518a76389344072661d9e9e72005d8d
MD5 1cdafc7dcb24d28e28e33233915f0fe1
BLAKE2b-256 fb2e35c7167ad841321e472fc245762e3343e4350ff4a45a1cd4d66f011287ee

See more details on using hashes here.

File details

Details for the file deep_data_profiler-2.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for deep_data_profiler-2.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 3efb634caba0c00d44f12e4a4a8eff0622089487d4c9eb2f43ccafa833717578
MD5 f50b2e22ebf97ed44b266289a500c97b
BLAKE2b-256 688db29bfea78ff297a95c9405f188093916adc7fcb3f7a57d7a96bb9ed7fde6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page