A pytorch module (and function) to reverse gradients.

Project description

`pytorch-revgrad`

python version

This package implements a gradient reversal layer for pytorch modules.

Example usage

import torch

from pytorch_revgrad import RevGrad

model = torch.nn.Sequential(
    torch.nn.Linear(10, 5),
    torch.nn.Linear(5, 2),
    RevGrad()
)

Project details

Release history Release notifications | RSS feed

0.2.0

Jan 9, 2021

This version

0.1.1

Jan 31, 2020

0.0.1

Mar 30, 2019

Download files

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

Source Distribution

pytorch_revgrad-0.1.1.tar.gz (6.9 kB view hashes)

Uploaded Jan 31, 2020 Source

Built Distribution

pytorch_revgrad-0.1.1-py3-none-any.whl (4.5 kB view hashes)

Uploaded Jan 31, 2020 Python 3

Hashes for pytorch_revgrad-0.1.1.tar.gz

Hashes for pytorch_revgrad-0.1.1.tar.gz
Algorithm	Hash digest
SHA256	`1d11bc61184d86d1d194244a20054a9c4c675ea55de34c5f8d5089b6979a6864`
MD5	`df925fa106b2264db04106672909ea97`
BLAKE2b-256	`db9a6dde240b8cfffb21b06c57571771490afcd08e5f7c38f2a203fa6bef3b33`

Hashes for pytorch_revgrad-0.1.1-py3-none-any.whl

Hashes for pytorch_revgrad-0.1.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`bb6aab9d64b5400adbcfbfa1622f1ffeb8dfe05842d3e8b9f940eba43f1a939c`
MD5	`ae53d0f50b1a8ac077958b6d1deaa67c`
BLAKE2b-256	`bd5c7f8398a6e3951b7bd11da9cc530b82a37240e1fb1faac349e7290c5af618`