smsop's Introduction

Statistically-motivated Second-order Pooling (ECCV2018)

Code for our work on ECCV2018. Paper URL: https://arxiv.org/abs/1801.07492

It is implemented in Keras with Tensorflow as backend.

Requirements:

Tensorflow: 1.4.0
Keras 2.1.2

Notes

The first version of the code is put in snapshot folder, which containing only the implementation of SMSOP structure. You can obtain these by calling get_cov_block(option) function in the main.py.

def get_cov_block(cov_branch):
    if cov_branch == 'smsop':
        covariance_block = covariance_block_newn_wv
    elif cov_branch == "smsop-equ":
        covariance_block = covariance_block_pv_equivelent
    else:
        raise ValueError('covariance cov_mode not supported')

    return covariance_block

smsop's People

Contributors

Stargazers

Watchers

smsop's Issues

Scripts?

Hi Kaicheng,

It's very interesting to read the paper, entitled Statistically Motivated Second Order Pooling. I would like to try to use it for my own research. Can you please share the code? Thanks! If it's not ready, I would appreciate it if you can share the the pooling layer by email.

Thanks and best,
Jun

About supporting safe_sign_sqrt

Thank you for support the smsop gitbub.
Could you please sunport the function safe_sign_sqrt for normalization step of class SignedSqrt(Layer).
and in elif output_normalization == 'cubicroot':
x = PowLayer(scale=0.5, center=np.power(49. / 2 - 1.0 / 3, 1.0 / 3))(x) , what is the meaning of the number 49. / 2 - 1.0 / 3
Thank you,
Truc

Recommend Projects

kcyu2014 / smsop Goto Github PK

smsop's Introduction

Statistically-motivated Second-order Pooling (ECCV2018)

Notes

smsop's People

Contributors

Stargazers

Watchers

Forkers

smsop's Issues

Scripts?

About supporting safe_sign_sqrt

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent