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.
text-recognition
program-transformation
usb
client-side-attacks
mkuserlocation
datagridviewcolumn
apksigner
facebook-permissions
qtserial
linter
google-analytics
xmgrace
meson-build
sitemap
control-language
pymunk
react-bootstrap
bits
tun
freeglut
evernote-app-notebook
bdc
update-all
timeslots
wechat-auth
angular-services
roslibjs
susy-compass
archetypes
multi-project