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
I wan't to call scene.trace_paths() batch by batch in a loop and them accumulate(concatenate) the traced paths after every iteration of the loop. The traced paths is a complex object with several tensors as properties and with batch_size position different in order for the different properties. Is there an easy way to concatenate along batch_size for all properties of traced paths?
The idea is to precompute traced_paths for a large number of UE's sampled on a scene, but by breaking up the compute into runs where traced paths are computed batch by batch. The final combined traced paths object is fed into a train function and reused for calibration of the ray tracer.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I wan't to call scene.trace_paths() batch by batch in a loop and them accumulate(concatenate) the traced paths after every iteration of the loop. The traced paths is a complex object with several tensors as properties and with batch_size position different in order for the different properties. Is there an easy way to concatenate along batch_size for all properties of traced paths?
The idea is to precompute traced_paths for a large number of UE's sampled on a scene, but by breaking up the compute into runs where traced paths are computed batch by batch. The final combined traced paths object is fed into a train function and reused for calibration of the ray tracer.
Beta Was this translation helpful? Give feedback.
All reactions