Python library for building preconditiioner with Graph Neural Network
Project description
# DeepNPG: Deep Neural Preconditioner with Graph Neural Networks
DeepNPG is a Python library for building preconditiioner with Graph Neural Networks. It provides straightforward interfaces to convert matrix into graph and perform efficient neural network training.
All data (e.g., numpy.ndarray, spicpy.sparse.csc/csr/bsr) will be automatically converted into sparse COOrdinate format (COO format), and then to gemetric data format.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
deepnpg-0.0.1.tar.gz
(9.8 kB
view details)
File details
Details for the file deepnpg-0.0.1.tar.gz.
File metadata
- Download URL: deepnpg-0.0.1.tar.gz
- Upload date:
- Size: 9.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c03171680877e6ad891886478b2845b1f307304c24670581f14f1fa47d6037cf
|
|
| MD5 |
341741867e7484ab50929b6a84300cf7
|
|
| BLAKE2b-256 |
ae4b2ac7282143b136d8353bce6c424cda7dd0ae8f271955665f0e634f5f92e1
|