OpenPCDet

OpenPCDet copied to clipboard

APH is all equal to 0

3

why the recall is not 0, but APH and AP is all equal to 0. I expend the Voxel-RCNN based from center head to dense head in waymo 2024-01-04 10:03:12,810...

SiHengHeHSH

is the results of Voxel-RCNN orPV-RCNN same on Waymo v1.3 and v1.2？

1

SiHengHeHSH

Do the PV-RCNN use the dense-head in Waymo Open Datasets?

1

SiHengHeHSH

Hello, could you please provide us with a MPPnet model that can be used?

1

Hello, could you please provide us with a MPPnet model that can be used?

L00qqq

Hello, when I reproduce the pvrcnn algorithm, there is not much difference in the accuracy of the validation set, but the accuracy of the test set submitted to the official website is very different from the accuracy you published, why is this?

1

Hello, when I reproduce the pvrcnn algorithm, there is not much difference in the accuracy of the validation set, but the accuracy of the test set submitted to the official...

y1216942674

substantial difference between the test set and the validation set

2

bqcs

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 12, 1])

1

Always reporting errors on different samples, Has anyone encountered the same problem before？ with 2 RTX 3090 Ti GPUs , python3.8, spconv2.3,  

HuangLLL123

After turning the learning to Custom Datasets and turning the last epoch, the following error comes out. The classes I learned are Car, Bus, and Truck. May I know how...

Parkeunseok

Some question about evaluation

1

hello, when i run test or train function , i will also meet this question in eval. It is some issue aboud tensorflow ? ` Traceback (most recent call last):...

YuRui-Learning

How to add and show the reading (the length of each side of the bounding box) in visualization?

1

I wish to add and show the reading (the length of each side of the bounding box) in visualization but i have no idea how to do it. Please help...

nicholas053