SVGR optimizer for Keras
Project description
Stochastic Variance Reduction Gradient Descent (SVRG) optimizer for Keras
Reference
Test results on MNIST
The following figure shows the train loss.
The results on test set:
SVRG | SGD | |
---|---|---|
Loss | 0.0893619 | 0.05765046 |
Accuracy | 0.9722 | 0.9817 |
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
Built Distribution
Close
Hashes for svrg-optimizer-keras-0.1.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | ee673d327dbb9804c0a0346c6f4c95724e22a97891cf7035252e506038862c61 |
|
MD5 | bf85cc62d7cd0af8d8ad405ec5dc41cc |
|
BLAKE2b-256 | 23e2d7dc77c7ef3d3b1b23b0bc6d50b3514d1faf3d1ed92b2bfe9104011d1597 |
Close
Hashes for svrg_optimizer_keras-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b4f8ca7f04be835134b25e6aee8a9c89e642fa9aed5fc2c55ea073e4000824ba |
|
MD5 | 1fb8ec2fc39b2a7d8c86fd48af1f5ac4 |
|
BLAKE2b-256 | cf186d5bc37c7217f2a9c975358a6ba7f1ef1314083b27e9ebddc9a5e9d8a9b8 |