A collection of homogeneous optimizers for PyTorch
Project description
HomOpt
HomOpt is a collection of homogeneous optimizers for PyTorch, designed to improve the performance of deep learning models. The optimizers are based on homogeneous dynamical systems and aim to provide more stable and efficient training.
Features
- A set of homogeneous optimizers for PyTorch, including the
HomMoptimizer. - Optimizers designed to improve the training stability and convergence rates for deep learning tasks.
- Easy-to-use and integrate into your PyTorch training workflows.
Installation
You can install HomOpt using pip. First, ensure that you have Python 3.6 or later and PyTorch 1.6.0 or later installed.
To install directly from PyPI:
pip install HomOpt
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file homopt-0.1.1.tar.gz.
File metadata
- Download URL: homopt-0.1.1.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
682371636e9b3bd3bbef05dd9154356b03faf7385357cc1df092a93dae6e5946
|
|
| MD5 |
e17b5b7ba7d5dc2c39b70180bb999248
|
|
| BLAKE2b-256 |
9b23e43418db91ddf53f0916722ea1f20705b4dc2d10a051582d71dbf17fc769
|
File details
Details for the file homopt-0.1.1-py3-none-any.whl.
File metadata
- Download URL: homopt-0.1.1-py3-none-any.whl
- Upload date:
- Size: 3.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e8bca76bda3bd28ba59a1f777c42727dcbdc6835f8c26ec42699740d248da183
|
|
| MD5 |
1f9237a4661bbef6811bc7a318f84f1e
|
|
| BLAKE2b-256 |
35ad1aac8704604a841da8c82247ca33685bbfa52c7001bc7ff01c5699d1d5a8
|
