-
Thanks for your great work!!!.
After reading two papers(RTM3D, KM3D), it seems that you only make the code of KM3D open-source, isn't it ? I wonder to compare the performance of core part of KM3D and…
-
For the actual images, The results of RTM3D are better than those of RTS3D. why?
-
**Hello** @Banconxuan
**I got an error when I ran your code**：python ./src/main.py --data_dir ./kitti_format --exp_id KM3D_res18 --arch res_18 --batch_size 32 --master_batch_size 16 --lr 1.25e-4 --g…
-
Inference on own data with different perspective, camera and resolution:
![rtm3d_on_providentia_first_result_no_calibration_no_crop](https://user-images.githubusercontent.com/22540236/107159259-34a…
-
Dear authors,
Thank you very much for sharing us the excellent code for the 'KM3D' paper .
I would like to reproduce your results on the KITTI dataset and then apply your method to a customed da…
-
Hi, Banconxuan and everyone. if can get your help, I will very greatful for you. That will help me very much!
1. I want to train the kitti dataset and run the demo command below as provided by the…
-
I try to compile DCNv2 in my project use CenterNet. But i got this error. My environment use torch 1.7.0 and torchvision 0.8.1
I have checked python version. I realized with python3.6, DCN compile su…
-
i can not find that.
-
My self data set **image resolution is too high to train the model** --- "cuda out of memory".....So I want to **resize images**,I modify kitti.py to resize image,but when train datas, it will come th…
-
I have a question for PGD (Probabilistic and Geometric Depth: Detecting
Objects in Perspective).
In paper you mentioned that the inference on 1080TI, the latency is 28ms (or 36 Hz), is quicker tha…