vision
vision copied to clipboard
[WIP] crestereo draft implementation
This is a draft version for the CREStereo model implementation.
It's over-commented for easier readability for those that are unfamiliar with the paper.
It also makes use of ModuleDicts and Dicts to process / access feature pyramid level instead of ModuleLists and Lists for readability purposes.
you also need to add from .crestereo import *
to torchvision/prototype/models/depth/stereo/__init__.py
@TeodorPoncu Oh ya, also please resolve the conflict on the test files