TSGD optimizer for Pytorch
Project description
TAdam
The Pytorch implementation of TSGD algorithm in：'Scaling transition from SGDM to plain SGD' https://arxiv.org/abs/2106.06749
Usage
from tsgd import TSGD
...
optimizer = TSGD(model.parameters(), iters=required, momentum=0.9, lr=1e-3, moment=3/8, up_lr=0.1, low_lr=0.005)
#iters(int, required): iterations
# iters = (testSampleSize / batchSize) * epoch
#
#moment(float, optional): transition moment
# moment = transition_iters / iters
#set default value: momentum=0.9, moment=3/8, up_lr=0.1, low_lr=0.005
The code will be uploaded as soon as possible
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
tsgd-0.0.2.tar.gz
(2.7 kB
view details)
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
tsgd-0.0.2-py3-none-any.whl
(7.3 kB
view details)
File details
Details for the file tsgd-0.0.2.tar.gz.
File metadata
- Download URL: tsgd-0.0.2.tar.gz
- Upload date:
- Size: 2.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.5.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.7.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6ec082f05bf3e16802edb1a5c9099385ce86bb1e29cad9bdf3cc45042aee16ab
|
|
| MD5 |
c0c8169f4ad8557909359e6a15250862
|
|
| BLAKE2b-256 |
57001281bd00fc00c8c35c7837248664fbd01b2379f989a284786ca24e1ee8d7
|
File details
Details for the file tsgd-0.0.2-py3-none-any.whl.
File metadata
- Download URL: tsgd-0.0.2-py3-none-any.whl
- Upload date:
- Size: 7.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.5.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.7.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
84c228bbe405c4b15f269f9eeb43d7c5544e55df365b951e99b2a1fea80852a8
|
|
| MD5 |
bbb90106843fc0b5976ff0049aa6a733
|
|
| BLAKE2b-256 |
2b956d6b37df657e2d344a3734780eeaaa8f4eb658ddcf7ebc8395b28542767b
|
