search

NVIDIA-AI-IOT / CUDA-PointPillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
Apache License 2.0
502 stars 148 forks source link

onnxruntime evaluation error #75

Open DingZ0115 opened 1 year ago

DingZ0115 commented 1 year ago

Hello, author! I wanted to use onnxruntime to compare the onnx to the pytorch model, but the call got the following error.

sess = onnxruntime.InferenceSession("pointpillar.onnx", None) File "E:\Anaconda3\envs\innovativePractice\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in init self._create_inference_session(providers, provider_options, disabled_optimizers) File "E:\Anaconda3\envs\innovativePractice\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 384, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : Load model from pointpillar.onnx failed:This is an invalid model. In Node, ("ReduceMax_166", ReduceMax, "", -1) : ("onnx::ReduceMax_332": tensor(float),) -> ("onnx::Squeeze_333": tensor(float),) , Error Mismatched attribute type in 'ReduceMax_166 : keepdims'

What is the reason for this? I am a beginner, if it is convenient, can you give me some suggestions for evaluating pointpillar.onnx with onnxruntime.

lxnudt commented 6 months ago

@DingZ0115 Hello，I encountered the same problem. Have you solved it?