Yiming Mao

> Hi, I am also very confused about this problem, but I successfully converted the coordinates of Pandaset to the standard coordinates of openpcdet using this ego coordinate system, which...

> Hi,there I am trying to test kitti trained models like pv_rcnn on pandaset. it looks like there is no standard evaluation metric yet. > > can you tell me...

Do you have wechat?, I am stuck int this place too I want to talk with you~ my wechat: MegaloAiming

> According to the pandaset paper, they are using kitti evaluation metric. > > But I don't know how to convert to Kitti format, and the paper doesn't give a...

> @Joeless Sorry for the late reply, you can contact me by email. I tried converting pandas to kitti's bin format, but I didn't get any results (AP=0), and then...

@Xharlie Hi I want to get "Pedestrians" and "Cyclist" configs Thank you very much~

@Anirbanbhk88 hi~ Can you share your config about car ? I modify the car config using README.md But I get a lower AP than this paper

> @Joeless I have attached the config car file in zip. [car.fhd.zip](https://github.com/pangsu0613/CLOCs/files/8388540/car.fhd.zip) Thanks for your config I checked the config and found that we are the same Are you get...

Thank you for your attention to our work. To align all the 3D sizes in the track, you can simply use the strategy of selecting the size of the highest...

Hi~ @pangsu0613 I evaluate it by your "CLOCs_SecCas_pretrained/fusion_layer-11136.tckpt" , and get a lower AP than you can you tell why? **My result:** Predict_test: False sparse_shape: [ 41 1600 1408] num_class...