Library for Jacobian Descent with PyTorch.
Project description
TorchJD
TorchJD is a library enabling Jacobian descent with PyTorch, for optimization of neural networks with multiple objectives.
[!IMPORTANT] This library is currently in an early development stage. The API is subject to significant changes in future versions. Use with caution in production environments and be prepared for potential breaking changes in upcoming releases.
Installation
TorchJD can be installed directly with pip:
pip install torchjd
Compatibility
TorchJD requires python 3.10, 3.11 or 3.12. It is only compatible with recent versions of PyTorch
(>= 2.0). For more information, read the dependencies in pyproject.toml.
Contribution
Please read the Contribution page.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file torchjd-0.1.0.tar.gz.
File metadata
- Download URL: torchjd-0.1.0.tar.gz
- Upload date:
- Size: 29.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: pdm/2.15.4 CPython/3.8.10 Linux/5.15.0-107-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 81f68052b67528d40e82513658d468d1073940f39a6b1dd8d662ef8d63e3f403 |
|
| MD5 | ac4b2c7f2063e720a4d71915ff314190 |
|
| BLAKE2b-256 | 9042e0d77d15d6007e2552b504044f4d321f195e7fa1120112ee18f9c8a9a169 |
File details
Details for the file torchjd-0.1.0-py3-none-any.whl.
File metadata
- Download URL: torchjd-0.1.0-py3-none-any.whl
- Upload date:
- Size: 47.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: pdm/2.15.4 CPython/3.8.10 Linux/5.15.0-107-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3bf91a117860a604b7237dc1b2fdeeba095de29531f99570ae96c5f731ab01ac |
|
| MD5 | 10e8a09352b65bfe0c1cb27a4956ef0b |
|
| BLAKE2b-256 | d00a58812be906ea77b5b63f20d7a45dc1b6cba654ddef6c2ba591c091563600 |
