想请问一下pp-liteseg导出onnx后转trt模型问题

[David-dotcom666]

问题确认 Search before asking

• 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

目前的环境是paddle2.4.2,tensorrt 8.5.1.7,cuda11.7, cudnn8.4，paddle2onnx1.0.5, onnx转tensorrt会报错

[Paddle2ONNX] Start to parse PaddlePaddle model...
[Paddle2ONNX] Model file path: inference_model/model.pdmodel
[Paddle2ONNX] Paramters file path: inference_model/model.pdiparams
[Paddle2ONNX] Start to parsing Paddle model...
[Paddle2ONNX] Use opset_version = 11 for ONNX export.
[Paddle2ONNX] PaddlePaddle model is exported as ONNX format now.
[08/29/2024-17:43:34] [TRT] [W] onnx2trt_utils.cpp:377: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[08/29/2024-17:43:34] [TRT] [W] Tensor DataType is determined at build time for tensors not marked as input or output.
[08/29/2024-17:43:35] [TRT] [W] TensorRT was linked against cuDNN 8.6.0 but loaded cuDNN 8.4.1
[08/29/2024-17:44:53] [TRT] [W] TensorRT was linked against cuDNN 8.6.0 but loaded cuDNN 8.4.1
[08/29/2024-17:44:55] [TRT] [E] 1: [resizingAllocator.cpp::nvinfer1::internal::ResizingAllocator::deallocate::105] Error Code 1: Cuda Runtime (invalid argument)
[08/29/2024-17:44:55] [TRT] [E] 1: [resizingAllocator.cpp::nvinfer1::internal::ResizingAllocator::deallocate::105] Error Code 1: Cuda Runtime (invalid argument)
[08/29/2024-17:44:55] [TRT] [E] 1: [resizingAllocator.cpp::nvinfer1::internal::ResizingAllocator::deallocate::105] Error Code 1: Cuda Runtime (invalid argument)
[08/29/2024-17:44:55] [TRT] [E] 1: [resizingAllocator.cpp::nvinfer1::internal::ResizingAllocator::deallocate::105] Error Code 1: Cuda Runtime (invalid argument)

我看pplite-seg推荐的是tensorrt7的，但是我环境要兼顾到其他的模型，想请问下有没有什么建议？

[David-dotcom666]

在这里有一个连接，目前已经能转换trt模型了
NVIDIA/TensorRT#2052