NVIDIA-AI-IOT/CUDA-PointPillars
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
PythonApache-2.0
Issues
- 3
the problem of point cloud height?
#120 opened by fffyyy111 - 1
Bug in computation of h_mask_size_
#118 opened by ClementLeBihan - 4
cuda pointpillars ROS ; illegal memory access!
#87 opened by zzt007 - 3
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!
#97 opened by JonathanFK981 - 4
Where is the model backbone.plan?
#108 opened by warren-lei - 0
Regarding the issue of inconsistent inference results between the openpcdet model and the generated plan model
#123 opened by hehualin-tut - 0
A lot of false positive on demo data result
#122 opened by zhu2900000 - 15
Could not export onnx.
#72 opened by Domwis-IR - 1
I use my own model resulted in backbones generating 0 candidate boxes, which resulting in errors in the postprocess module
#106 opened by ACFIRSTONE - 29
- 0
- 1
- 3
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
#73 opened by darrenearl - 5
Mismatch in number of Detections with TFRT onnx inference VS pytorch, pth file
#83 opened by Allamrahul - 1
What should I do if I want more labels?
#115 opened by brillint - 0
- 1
基于mmdetion3d pointpillar改进
#116 opened by fpeanut - 1
onnxruntime evaluation error
#75 opened by DingZ0115 - 5
- 0
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？
#114 opened by fpeanut - 0
pointpillar.cpp Cuda failure
#113 opened by lishanxiuxiu - 1
when I cmake .. it return: Could NOT find CUDA (missing: CUDA_INCLUDE_DIRS CUDA_CUDART_LIBRARY) (found version "11.1")
#111 opened by brillint - 1
when I cmake .. it returns: Could NOT find CUDA (missing: CUDA_INCLUDE_DIRS CUDA_CUDART_LIBRARY) (found version "11.1")
#112 opened by brillint - 0
inference with Multiple GPU
#109 opened by xiaoxifuhongse - 0
Return labels per point instead of bounding boxes
#107 opened by tiesus - 4
- 1
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?
#88 opened by NukaCC - 0
question about postprocess_kernal
#104 opened by jinz2014 - 1
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.
#96 opened by yrbqy2013 - 0
When I run./demo, I get an OutOfMemory and Cudnn (CUDNN_STATUS_EXECUTION_FAILED) error
#101 opened by windlinsherlock - 3
When I run ./demo, it encounters an error.
#93 opened by gitctrlx - 5
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
#86 opened by Allamrahul - 0
point_cloud_range changed
#95 opened by The-wind-rises-2023 - 0
- 0
- 0
- 0
About hard coded const variables in kernel.h
#90 opened by Acuno41 - 0
- 5
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.
#66 opened by christmas-ww - 2
Failed to convert onnx to trt
#81 opened by Derrick1994 - 1
- 0
How can I print the predict label?
#84 opened by JiyuanWANG12138 - 2
Different Results when I do inference on onnx file using TRT engine vs inference using pth file
#82 opened by Allamrahul - 0
- 0
- 5
- 0
- 1
Cant find a pytorch version matched with CUDA11.4
#69 opened by Aracher - 0
vscode cuda debug config
#68 opened by zyxcambridge - 0
build fails: error: initialization with "{...}" is not allowed for object of type "dim3"
#65 opened by serser