You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for your excellent work!
When I run your demo, I notice that the input points are sent to progressive encoding. If I disable this module, the final result dosen't change a lot. So why do we need this module?
Here is the two picture of results( promt: an image of a shoe made of cactus, obj: shoe), the first one is WITH progressive encoding, the second one is WITHOUT progressive encoding.
The text was updated successfully, but these errors were encountered:
Hi thanks for the kind comment and apologies for the delayed response. The progressive encoding is based on the implementation described in the SAPE paper. Our experiments also found it doesn't really change the result for a given run, but it does somewhat stabilize training to be more consistent across runs.
Thanks for your excellent work!
When I run your demo, I notice that the input points are sent to progressive encoding. If I disable this module, the final result dosen't change a lot. So why do we need this module?
Here is the two picture of results( promt: an image of a shoe made of cactus, obj: shoe), the first one is WITH progressive encoding, the second one is WITHOUT progressive encoding.
The text was updated successfully, but these errors were encountered: