NVIDIA-AI-IOT / CUDA-PointPillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

NVIDIA-AI-IOT/CUDA-PointPillars Issues

Could not export onnx.
Closed 2 years ago15
Mismatch in number of Detections with TFRT onnx inference VS pytorch, pth file
Updated 5 months ago5
What should I do if I want more labels?
Updated 5 months ago1
Bug in computation of h_mask_size_
Updated 5 months ago
how to make custom plugin like pillarscatter plugin?
Updated 5 months ago
基于mmdetion3d pointpillar改进
Updated 5 months ago1
onnxruntime evaluation error
Updated 6 months ago1
Changing the grid size resulted in incorrect inference results
Updated 6 months ago5
我发现你们代码的检测结果并不准确，请问是哪里出了问题？
Updated 6 months ago
Where is the model backbone.plan?
Updated 6 months ago1
pointpillar.cpp Cuda failure
Updated 6 months ago
when I cmake .. it return: Could NOT find CUDA (missing: CUDA_INCLUDE_DIRS CUDA_CUDART_LIBRARY) (found version "11.1")
Closed 6 months ago1
when I cmake .. it returns: Could NOT find CUDA (missing: CUDA_INCLUDE_DIRS CUDA_CUDART_LIBRARY) (found version "11.1")
Closed 6 months ago1
inference with Multiple GPU
Updated 6 months ago
Return labels per point instead of bounding boxes
Updated 7 months ago
I use my own model resulted in backbones generating 0 candidate boxes, which resulting in errors in the postprocess module
Updated 7 months ago
The performance specified in github is not reproduced.
Updated 7 months ago4
When using the model trained by myself, the following problems are encountered. Is it due to the process of onnx transfer?What changes should I make to the code when the number of categories changes?
Updated 7 months ago1
question about postprocess_kernal
Updated 8 months ago
cuda pointpillars ROS ; illegal memory access!
Updated 8 months ago3
After adding PCL rendering on top of the inference using `cuda_pointpillar`, the bounding box results for the same frame of point cloud inference vary and exhibit continuous fluctuations.
Updated 8 months ago1
When I run./demo, I get an OutOfMemory and Cudnn (CUDNN_STATUS_EXECUTION_FAILED) error
Updated 8 months ago
When I run ./demo, it encounters an error.
Updated 8 months ago3
Training and evaluation works well when I change MAX_POINTS_PER_VOXEL from 32 to 100, but after converting model to ONNX, TFRT inference results in wrong predictions
Updated 9 months ago5
Two questions:TypeError: forward() missing 1 required positional argument: 'batch_dict' and failed to parse onnx model file, please check the onnx version and trt support op!
Closed 9 months ago2
What should I do if I want more labels？
Updated 10 months ago13
point_cloud_range changed
Updated a year ago
A question about pillarScatter kernel function bank conflict.
Closed a year ago
In the preprocessing module, why calculate the pillar index value twice？
Updated a year ago
Error: No Kernel image is available for exectuion on the device
Updated a year ago
About hard coded const variables in kernel.h
Updated a year ago
how to install Export Tools Pointpillar Onnx Model
Closed a year ago
PostProcessCuda is very slow using my model
Updated a year ago28
demo: malloc.c:2401: sysmalloc: Assertion `(old_top == initial_top (av) && old_size == 0) || ((unsigned long) (old_size) >= MINSIZE && prev_inuse (old_top) && ((unsigned long) old_end & (pagesize - 1)) == 0)' failed.
Updated a year ago5
Failed to convert onnx to trt
Updated a year ago2
Too many false detections with Custom dataset FP16 TFRT inference
Updated a year ago1
How can I print the predict label?
Closed a year ago
Different Results when I do inference on onnx file using TRT engine vs inference using pth file
Updated a year ago2
own model input without internsity,how to modify this code
Updated a year ago1
Found two crashes caused by two defects in preprocess_kernels.cu
Updated a year ago
How can i know about time of scatter processing
Updated 2 years ago
Change ROS's .bag file to kitti's format, But the performance is terrible
Updated 2 years ago5
RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs. Dictionaries and strings are also accepted, but their usage is not recommended. Here, received an input of unsupported type: int
Updated 2 years ago2
how to convert .pt into onnx for pointpillars of mmdetection3d?
Updated 2 years ago
Cant find a pytorch version matched with CUDA11.4
Closed 2 years ago1
vscode cuda debug config
Updated 2 years ago
Core Dumped Error after inference
Updated 2 years ago
build fails: error: initialization with "{...}" is not allowed for object of type "dim3"
Updated 2 years ago
I have this issue with trt_->doinfer(buffers);
Updated 2 years ago
The size of tensor a (12160) must match the size of tensor b (199680) at non-singleton dimension 1
Updated 2 years ago