Guan Jie

Failure in compiling examples/calibration/main.cpp

6

Hi. Thanks in advance for spending time reading my issue. Could anyone help me on this error? The OS system using is Ubuntu 16, and the SDK is built from...

Hi. May I know has anyone try to train any CNN-based segmentation model using the dataset SA-1B? I am curious what will be its performance in particular the zero-shot generalization.

Wrong depth map

9

Hi. I retrained the model and try to visualize the depth map predicted and find that it doesn't make sense. However, the performance of the model is about the same...

SECOND format

1

Anyone know the position and orientation of the coordinate system used by SECOND format? Thank you.

Incorrect Visualization

2

 I think the order of overlapped patch merging is wrong. Is my comment correct?

Solving #73 by adding .contiguous() after transpose and permutation.

Speed of Webserver degrade after a while

2

Hi Naurril. May I know did you encounter this situation where the loading of pcd file and images just get super slow after a while (random, it could be one...

CUDA-BEVFusion: difference in the result of onnx and pytorch model

5

Hi. I have converted BEVFusion model from torch to onnx but it fails np.testing.allclose ``` Mismatched elements: 17068436 / 100663296 (17%) Max absolute difference: 0.00343999 Max relative difference: 17035.555 x:...

### Motivation Hi. I have tried to follow the template to prompt the model ``` \nPlease provide the bounding box coordinate of the region this sentence describes: ... ``` My...

I am using CUDA-BEVFusion. May I know how to get 80? https://github.com/NVIDIA-AI-IOT/Lidar_AI_Solution/blob/8a1b2962a35e4dadec07ceadbd5a90662881ff1f/CUDA-BEVFusion/src/main.cpp#L196 I can understand that 360 = (54+54) / 0.3.