Skip to content

A python tensorflow implementation of nips2015-action-conditional-video-prediction

Notifications You must be signed in to change notification settings

williamd4112/tensorflow-action-conditional-video-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Installtion

cd tensorflow-action-conditional-video-prediction
source setup.sh

Train

Atari

./train_atari.sh ${game name} ${num_act} ${colorspace [rgb|gray]} {gpu id}
e.g. ./train_atari.sh MsPacman-v0 9 gray 0

You can use tensorboard to monitor training process.
e.g. tensorboard --port 6006 --logdir=train:models/Pong-v0/train,test:models/Pong-v0/test

NOTE: I don't test model during training currently.

Test

Model zoo

Since size of model is too large, please download pretrained models from here

About

A python tensorflow implementation of nips2015-action-conditional-video-prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published