search

Tream733 / centerpoint-livox

CenterPoint model trained on livox dataset, and deployed with TensorRT on ros2
24 stars 1 forks source link

Why are there multiple bounding boxes in the final visualization? #3

Open 1806610292 opened 1 year ago

1806610292 commented 1 year ago

First of all, thank you very much for your work! When I was trying to replicate your work and converting ONNX to TensorRT, I encountered a warning: "onnx2trt_utils.cpp:365: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32." I ignored this warning, and in the end, there were multiple bounding boxes in the visualization. Upon reflection, I believe that I may need to convert your ONNX model to INT32 type . However, during the conversion, I encountered an error: "onnx.onnx_cpp2py_export.checker.ValidationError: Nodes in a graph must be topologically sorted, however input '/head/Mod_output_0' of node: name: '/head/Div OpType: Div is not the output of any previous nodes." Do you have any suggestions?

zjg1210 commented 11 months ago

Hello, I have the same problem, but I do not have any test object output, may I ask if you have solved this problem?