qoherent/modrec-workflow
14
0
Fork 1
Code Issues 1 Pull Requests Workflows Packages Projects Releases 1 Wiki Activity
An example machine learning workflow for signal modulation classification, built using RIA Hub Workflows
46 Commits 2 Branches 1 Tag 85 MiB
Python 100%
Go to file
liyuxiao2 ff3d45653d formatted all files
2025-05-22 14:12:36 -04:00
.riahub/workflows Created dataset folder in workflow 2025-05-21 16:00:31 -04:00
checkpoint_files formatted all files 2025-05-22 14:12:36 -04:00
conf updated workflow scripts 2025-05-21 15:46:59 -04:00
data formatted all files 2025-05-22 14:12:36 -04:00
helpers formatted all files 2025-05-22 14:12:36 -04:00
onnx_files completed converting the pytorch model -> ONNX 2025-05-22 14:12:10 -04:00
results reorganized file struture 2025-05-21 15:46:28 -04:00
wheel reversed the changes, for now will install from the wheel folder 2025-05-16 14:17:08 -04:00
.gitattributes added LFS tracking to the .whl files 2025-05-16 13:23:13 -04:00
.gitignore removed data/ from the git ignore 2025-05-21 15:52:16 -04:00
convert_to_onnx.py formatted all files 2025-05-22 14:12:36 -04:00
README.md Add ReadME 2025-05-14 15:36:31 -04:00
requirements.txt Merge branch 'main' of https://riahub.qoherent.internal:3000/qoherent/modrec-workflow 2025-05-16 14:31:41 -04:00

README.md

RIA Hub Technical Demo

This repository demonstrates a full ML pipeline via Gitea Actions:

  • Recordings
    A collection of raw .npy radio recordings stored via Git LFS.

  • Workflows
    A CI pipeline that automatically:

    1. Builds a labeled dataset from raw recordings
    2. Trains a model on that dataset
    3. Optimizes the model and packages an inference application

  • Scripts

    • scripts/build_dataset.sh
      Reads through recordings/, applies preprocessing, and outputs training .npz or .csv files into data/.
    • scripts/train_model.sh
      Consumes data/, trains a PyTorch model, and writes checkpoints to checkpoints/.
    • scripts/build_app.sh
      Takes the best checkpoint and builds a small inference CLI or server in dist/.