Tony

Questions about the keypoint numbers and loss functions on KITTI dataset

1

Hi, thanks for the great work. I came across a problem when trying to reproduce the performance on KITTI dataset. I tried different combinations of keypoint numbers (from 64 to...

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

1

Hi, I'm trying to reimplement the deform conv in Tensorflow. I found in the original paper, the number of filters for the offsets is 2 * c, where c is...

The calculation of padding size seems to be conflicted in the kernel registration and execution. In [kernel registration](https://github.com/Zardinality/TF-deformable-conv/blob/8e3c7136aa08d99a86de2d78e99654bcfefcd896/lib/deform_conv.cc#L153), the padding size is calculated based on the effective kernel size (taking...

Some facts about the runtime speed.

1

Hi I tried to reimplement the similar operation as yours in Tensorflow and found two facts w.r.t the runtime speed performance: 1. The gpu kernel which adds the filter gradients...

Questions about inference time

2

Hi, thanks for sharing the work. I tried to run inference with `./tools/dist_test.sh ./projects/configs/surroundocc/surroundocc.py ./path/to/ckpts.pth 8` with the pickle file you provided. However, the inference speed is super slow. It...