# 19th place solution with code

Hey guys,
First of all, I'd like to thank the organizers for this awesome challenge. This was not a typical computer vision competition that's for sure and I spent a good amount of time just to understand the problem and the data. I went through multiple papers related to 3d object detection. I chose to go with
[SECOND](https://github.com/traveller59/second.pytorch)
:
![](assets/53c3feccb4426eb05377d98d.png)
I tweaked the SECOND's original source code to get it working for lyft dataset. Added the evaluation metric of the competition for val set evaluation. Modified the default config files according to lyft object dimensions (
anchor_ranges
,
sizes
etc).  Splitted train/val based on scenes (80:20),
[configs/nuscenes/all.pp.lowa.config](https://github.com/pyaf/second.pytorch/blob/master/second/configs/nuscenes/all.pp.lowa.config)
with VoxelNet and PillarFeatureNet worked best for me.
check out my source code:
[https://github.com/pyaf/second.pytorch](https://github.com/pyaf/second.pytorch)