hello! I found some codes are exactly the same. Are they reduplicate?

astra-vision / MonoScene

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

https://astra-vision.github.io/MonoScene/

Apache License 2.0

708 stars 69 forks source link

Closed Yuankus closed 1 year ago

Yuankus commented 1 year ago

here in the self.downsample3 and self.downsample4 in the pic. In MonoScene/monoscene/models/DDR.py line 100

Yuankus commented 1 year ago

Yuankus commented 1 year ago

Sorry that I made some mistake! I can understand it now! Thanks!

anhquancao commented 1 year ago

Hello, @Yuankus! Indeed, a more appropriate approach would involve using a for loop with a ModuleList.