david-leon/Dandelion

A light weight deep learning framework, on top of Theano, offering better balance between flexibility and abstraction

40
/ 100
Emerging

This project helps deep learning researchers and practitioners rapidly experiment with and build custom neural network architectures. It takes raw data tensors and deep learning modules as input to produce trained models and predictions, enabling greater flexibility than other frameworks. The intended users are researchers and practitioners who need to design and test nonstandard or complex neural network structures.

No commits in the last 6 months. Available on PyPI.

Use this if you are a deep learning researcher who needs to rapidly prototype and test experimental or highly customized neural network designs while maintaining a balance of convenience and granular control.

Not ideal if you are new to deep learning or prefer a highly abstracted, 'out-of-the-box' experience for standard network types without needing to delve into tensor-level operations.

deep-learning-research neural-network-design machine-learning-experimentation custom-model-development artificial-intelligence-prototyping
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Python

License

Last pushed

Oct 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/david-leon/Dandelion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.