I'm implementing the basic architecture from this paper: https://arxiv.org/pdf/1705.08260.pdf in PyTorch. It consists of an autoencoder and Spatial Transformer.
pipes-filters
gaussian-process
iab
glossary
android-hardware-keyboard
piecewise
geotiff
derived
rategate
app-themes
python-schedule
qdebug
uislider
classpath
multiple-gpu
selenium-hub
http-headers
dispatchertimer
django-grappelli
introspection
pkware
teraterm
finite-field
.net-fiddle
icss
angular2-aot
memory-leak-detector
pyatom
mfcc
declspec