-
hi,
Congrats on this good work.
I am recently checking NuScene Lidarseg benchmark, according to its official instructions, we are allowed to used up to 10 past sweeps to density the point cloud…
-
@xinge008
Do you have Inference code to evaluate model on pointcloud files?
-
Thank you for your wonderful work!
I'm trying to reuse the training code for SemanticKITTI for Panoptic-PolarNet to train the network on NuScenes (https://github.com/edwardzhou130/Panoptic-PolarNet…
-
Hello, thank you very much for your great work ! I have a question: when we test the pre-trained model on a new database, should we modify the axes of the point cloud such that they are the same as th…
-
I train the net from scratch as the redeme said. However, after 5 epoch, the loss is always nan, acc is 0, iou is 0.
```text
Lr: 9.611e-03 | Update: nan mean,nan std | Epoch: [4][990/1047] | Time 1…
-
@morpheus1820 @Yang7879 @QingyongHu Hi thanks for opensourcing the source code , i have following queries
1. Can you share the pre-trained model for semantic kitti dataset i want to check the outpu…
-
I tried to train Randla-Net on the Toronto3D, but training does not seem to work. It is stuck on this for 10 hours now:
`training: 0%| | 0/50 [00:00
-
I built a neural network and trained successfully on other data sets, but I encountered the following problems when I wanted to use your data set for training.
Step 00000050 L_out= nan Acc= nan ---…
-
Great work on the Point Tubes. I am particularly interested in the 4D semantic segmentation applications.
I was wondering if you tried the PSTNet on benchmark datasets like Semantic Kitti or nuScenes…
-
嗨,@HuguesTHOMAS,
I am trying to use your library in the SemanticKitti dataset.
I tried to modify the `batch_num` parameter from` 8` to `160` to make full use of computing resources.
Unfortunately, …