Xianshun Wang

https://github.com/sampepose/flownet2-tf/blob/18f87081db44939414fc4a48834f9e0da3e69f4c/src/dataset_configs.py#L95 does this mean that excepting geometric augmentation, only Gaussian noise is applied to the first image? And are the Gaussian noise of the two images exactly the same?

Could you give more information about `make_bilinear_weights`?

2

https://github.com/meteorshowers/RCF-pytorch/blob/5efe8046f92f271142fcc3b9f0b8f4303cc4066a/models.py#L209 Nice work! Function `make_bilinear_weights` makes me confused, could you give us more information or references about this function? Thanks a lot!

Thanks for your excellent work. But I have some doubts about the shape of the jaobian of the exponential map. Let's take the $SE3$ for example. Its exponential function map...

How many epochs are required to converge?

2

Hi. Thanks for your contribution. These days I am training your network. The total loss fluctuates between 1.5 and 3 after 10 epochs while the edge_loss is fixed at 0.00244~....

Problem when I compile with -O0 parameter

1

I want to debug this project and get some implementation details, so I modified the CMakeList.txt: ``` -SET(CMAKE_BUILD_TYPE "Release") -SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O3 -mtune=native -mavx") +SET(CMAKE_BUILD_TYPE "Debug") +SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O0 -mtune=native...

Training code?

9

Excellent work! Thanks for your contribution! Will the training code be available later? How many computing resources are needed to reproduce your reported results?

what does `grounding_hash ` mean?

1

Hello everyone, I’m relatively new to the field of Referential Segmentation (RefSeg) and am trying to enhance my understanding of the code and concepts. I came across the term `grounding_hash...