Data

Tools

Indexes

Applications

Experiments

Open Source Science

mldec

https://github.com/peterse/mldec

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.2%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: peterse
  • Language: Jupyter Notebook
  • Default Branch: master
  • Size: 7.63 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed 9 months ago
Metadata Files
Readme Citation

README.md

Codebase for "Sample importance for data-driven decoding"

Installation

You will need to install the mldec python package locally. From this directory, call python -m pip install -e .

Running experiments

The two main experiment scripts are: - mldec/pipelines/main (repetition code and surface code DDD with FNN, CNN, transformer) - mldec/pipelines/reps_main (Detector DDD with GNN).

Each file has a mode ("train" or "tune"), dataset_module (to determine the type of experiment), MODEL to determine the architecture, and a config dictionary that specifies fixed run parameters. If in train mode, you can specify all config entries to run a specific experiment with the above options. In tune mode, you can specify sets of hyperparameters and dataset parameters to use for large parallel-processing runs using a yaml configuration file in mldec/hyper_config. Further instructions are provided in mldec/pipelines/README.md.

Generating figures

Notebooks for generating all figures are in src/mldec/analysis. All of the post-processed data are in that directory, with descriptions in manifest.md.

Owner

  • Name: Evan Peters
  • Login: peterse
  • Kind: user
  • Location: University of Waterloo

Quantum computing at University of Waterloo IQC

Citation (CITATION.cff) 

cff-version: 1.2.0
title: Code for "Sample importance for data-driven decoding"
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Evan
    family-names: Peters
    email: peterse583@gmail.com
repository-code: 'https://github.com/peterse/mldec'

GitHub Events

Total
  • Push event: 6
  • Public event: 1
Last Year
  • Push event: 6
  • Public event: 1

Dependencies

pyproject.toml pypi
requirements.txt pypi
  • matplotlib ==3.7.2
  • numpy ==1.26.4
  • pandas *
  • pandas ==2.1.0
  • pymatching *
  • pyyaml *
  • qiskit *
  • qiskit-aer *
  • qiskit-ibm-runtime *
  • seaborn ==0.12.2
  • stim *
  • streamlit ==1.32.0
  • torch *