When I run ./demo, it encounters an error.

Question

When I run ./demo, it encounters an error.

gitctrlx opened this issue a year ago · comments

GPU has cuda devices: 1
----device id: 0 info----
GPU : NVIDIA GeForce RTX 2080 Ti
Capbility: 7.5
Global memory: 11017MB
Const memory: 64KB
SM in a block: 48KB
warp size: 32
threads in a block: 1024
block dim: (1024,1024,64)
grid dim: (2147483647,65535,65535)

Building TRT engine.
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 1:9: Message type "onnx2trt_onnx.ModelProto" has no field named "version".
trt_infer: ModelImporter.cpp:733: Failed to parse ONNX model from file: /project/CUDA-PointPillars/model/pointpillar.onnx
: failed to parse onnx model file, please check the onnx version and trt support op!

JonathanFK981 · Answer 1 · Sat Sep 02 2023 00:46:48 GMT+0800 (China Standard Time)

I have also encountered the same problem. Plz tell me how to solve it

warrenwlei · Answer 2 · Wed Oct 11 2023 14:31:58 GMT+0800 (China Standard Time)

I have also encountered the same problem. Plz tell me how to solve it

Check model size of pointpillar.onnx. The model may be incomplete or incorret while using git clone. Correct size should be 18.4 MB.

warrenwlei · Answer 3 · Wed Oct 11 2023 14:38:58 GMT+0800 (China Standard Time)

I have also encountered the same problem. Plz tell me how to solve it

There are two ways to solve this problem.

Use Git LFS (Large File Storage) to clone this repo.
Download pointpillar.onnx from web page.
https://github.com/NVIDIA-AI-IOT/CUDA-PointPillars/raw/main/model/pointpillar.onnx
eg:

wget https://github.com/NVIDIA-AI-IOT/CUDA-PointPillars/raw/main/model/pointpillar.onnx