david-leon/Dandelion
A light weight deep learning framework, on top of Theano, offering better balance between flexibility and abstraction
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.
Stars
16
Forks
2
Language
Python
License
—
Category
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.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility