Anomaly-Detection-in-Surveillance-Videos icon indicating copy to clipboard operation
Anomaly-Detection-in-Surveillance-Videos copied to clipboard

Published 20 hours ago • verified publisher icon vantage-vision-vv

The implementation of loss function

Open YuxinZhaozyx opened this issue 5 years ago • 1 comments

The loss function in your paper is

image

image

However, you implement it in the following way.

https://github.com/abhay97ps/Anomaly-Detection-in-Surveillance-Videos/blob/4be07aba4a8dda7cea882f33782595622d248d3e/Anomaly_NN.py#L51

https://github.com/abhay97ps/Anomaly-Detection-in-Surveillance-Videos/blob/4be07aba4a8dda7cea882f33782595622d248d3e/Anomaly_NN.py#L66-L77

The image is implemented as a placeholder extra and calculated using python float type. Won't it make it impossible to back propagate gradient to extra? And the optimizer only minimizes the image .

Shouldn't the image be implemented in tensorflow functions rather than pure python?

YuxinZhaozyx avatar Mar 21 '19 13:03 YuxinZhaozyx

It seems the weight didn't get update every iteration in here. Have you figure out how to do it correctly?

fzp8656342 avatar Jun 26 '19 07:06 fzp8656342