Tony comments

Repositories
Issues
Comments

Results 3 comments of


                                            Tony

Questions about the keypoint numbers and loss functions on KITTI dataset

UPDATE: with all the setup mentioned above, the best success rate I am able to achieve is 95.13%, with RTE=0.25 and RRE=0.96, which leaves a large margin from the paper....

Seems the implementation of offsets is different from the original paper?

Btw, is that the reason why you put a variable called `deformable_group` to overcome this issue?

Some facts about the runtime speed.

Btw, below is the command line I used for compilation and has been tested to be compatible with TF 1.12, g++ 4.9 and CUDA 9.0 without involving any changes to...