WenjiaR comments

Repositories
Issues
Comments

Results 4 comments of


                                            WenjiaR

finetune in the secend batch, loss is nan.

> @jim88481 I solved it by using the pytorch implementation https://github.com/ibaiGorordo/CREStereo-Pytorch. Hi, may I ask whether the pytorch implementation has the same performance compared with MegEngine implementation?

nan

Hi, have you solved this issue? I encountered this problem when training on Sceneflow.

nan

> > Hi, have you solved this issue? I encountered this problem when training on Sceneflow. > > yes，I solved it by https://github.com/ibaiGorordo/CREStereo-Pytorch and,there is not much difference in their...

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

Is the code of this paper still unavailable?