Project description

Stochastic Variance Reduction Gradient Descent (SVRG) optimizer for Keras

The following figure shows the train loss. MNIST

The results on test set:

	SVRG	SGD
Loss	0.0893619	0.05765046
Accuracy	0.9722	0.9817

These details have not been verified by PyPI

This version

0.1.0

Aug 25, 2019

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Uploaded Aug 25, 2019 Source

Uploaded Aug 25, 2019 Python 3

Details for the file svrg-optimizer-keras-0.1.0.tar.gz.

Download URL: svrg-optimizer-keras-0.1.0.tar.gz
Upload date: Aug 25, 2019
Size: 2.5 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.35.0 CPython/3.6.8

Hashes for svrg-optimizer-keras-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`ee673d327dbb9804c0a0346c6f4c95724e22a97891cf7035252e506038862c61`
MD5	`bf85cc62d7cd0af8d8ad405ec5dc41cc`
BLAKE2b-256	`23e2d7dc77c7ef3d3b1b23b0bc6d50b3514d1faf3d1ed92b2bfe9104011d1597`

Details for the file svrg_optimizer_keras-0.1.0-py3-none-any.whl.

Download URL: svrg_optimizer_keras-0.1.0-py3-none-any.whl
Upload date: Aug 25, 2019
Size: 3.2 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.35.0 CPython/3.6.8

Hashes for svrg_optimizer_keras-0.1.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`b4f8ca7f04be835134b25e6aee8a9c89e642fa9aed5fc2c55ea073e4000824ba`
MD5	`1fb8ec2fc39b2a7d8c86fd48af1f5ac4`
BLAKE2b-256	`cf186d5bc37c7217f2a9c975358a6ba7f1ef1314083b27e9ebddc9a5e9d8a9b8`