-
@YangZhang4065 @edwardzhou130 Thanks for open sourcing the work , its of great work . I am having few queries
Q1. You have tested on the semattic kitti dataset , how will the output differ when we r…
-
Dear authors,
Thanks a lot for your open source code and SemanticKITTI dataset! After reading your ICCV'19 paper, I have some questions related to the statistics reported in Table 3.
- What is t…
-
Dear HuQingyong,
I have trained the network with my data. It works perfectly. But I have some problem with the inference. with --mode test. my data have 5 classes and I have set class 0 as ignore in …
-
Hi,thanks for your great work!when i want to train your model,i meet this problem,can you help me ?looking forward to your reply.
InternalError (see above for traceback): Blas xGEMM launch failed : a…
-
Hi !
Thanks for this great dataset, and labeling tool.
We are trying to use the labeler to annotate data of our own, and are encountering weird issues.
We have created the .bin files, .label…
-
hello @QingyongHu
what the value of ```batch-size``` and ```N``` when training SemanticKITTI ?
in the ```3.4. Implementation``` of your paper, it said used the fixed ```N ~= 1e6```, but the nu…
-
For the multiple scan experiment in the SemanticKITTI paper, was the Darknet53Seg network also trained over the combined dataset (5-scans combined), or was it only evaluated over the 5-scan combined d…
-
Hi,
Thanks for making this state of the art algorithm readily available!
When experimenting with your code, I noticed that you provide in your config file image mean and standard deviation param…
-
We are currently running our competition of the DFC 2020 on your platform.
Here is the link to our competition: https://competitions.codalab.org/competitions/22289
The status of several submission…
-
In the squeezesegV2.py class, I can see that the binary mask has not been used as an input channel. However, in the squeezesegV2 paper, the authors have claimed that using this binary mask to indicate…