STAWM

KO | EN

gitlite — search

#python #hacktoberfest #ai #go #golang #rust #macos #java #nodejs #windows #awesome #awesome-list #pytorch #security

(★ 21)

Code for the paper 'A Biologically Inspired Visual Working Memory for Deep Networks'

STAWM 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# STAWM

Code for the paper ['A Biologically Inspired Visual Working Memory for Deep Networks'](https://arxiv.org/abs/1901.03665), originally submitted to ICLR2019, reviews can be found [here](https://openreview.net/forum?id=B1fbosCcYm).
The memory module can be found in memory.py and each experiment has its own file.

## Examples

### MNIST

Reconstruction (sketch) sequences for 36 glimpses / sketches of size 4, memory size: 128, latent size: 4. Note that this is significantly more glimpses than used in the paper in order to obtain a reasonable animation, but also shows that the memory can learn a useful representation over very long sequences.

![mnist gif](https://raw.githubusercontent.com/ethanwharris/STAWM/master/img/mnist.gif)

### CelebA

Segmentation over time for the model from the paper. Here we plot the masked images according to the alpha channel of the final sketch. As the model trains this alpha channel moves from a uniform representation, to a segmented facial region.

![celeb gif](https://raw.githubusercontent.com/ethanwharris/STAWM/master/img/celeb_demo.gif)

STAWM

STAWM 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

STAWM

STAWM 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README