PaddlePaddle / PaddlePaddle/FastDeploy
TrtBackend::LoadTrtCache加载tensorrt模型时报错
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
温馨提示:根据社区不完全统计,按照模板提问,可以加快回复和解决问题的速度
环境
- 【FastDeploy版本】: develop
- 【编译命令】如果您是自行编译的FastDeploy,请说明您的编译方式(参数命令)
- cmake .. -DENABLE_ORT_BACKEND=ON
-DENABLE_PADDLE_BACKEND=OFF
-DENABLE_OPENVINO_BACKEND=OFF
-DENABLE_TRT_BACKEND=ON
-DCMAKE_BUILD_TYPE=DEBUG
-DWITH_GPU=ON
-DCUDA_DIRECTORY=/usr/local/cuda
-DCMAKE_INSTALL_PREFIX=/usr/local/
-DENABLE_VISION=ON
-DENABLE_TEXT=ON
-DBUILD_EXAMPLES=ON
-DTRT_DIRECTORY=${PWD}/../../thirdlibs-x86/tensorrt/TensorRT-8.6.1.6
-DOPENCV_DIRECTORY=/usr/local/share/OpenCV/
-DOPENVINO_DIRECTORY=${PWD}/../../thirdlibs-x86/openvino - 【系统平台】: Linux x64(Ubuntu 18.04)
- 【硬件】:
- nvidia 2060,
- NVIDIA-SMI 530.30.02 Driver Version: 530.30.02 CUDA Version: 11.1
- TensorRT-8.6.1.6
- 【编译语言】: C++ ,python3.7
问题日志及出现问题的操作流程
模型转换参数
~/tensorrt/TensorRT-8.6.1.6/bin/trtexec
--onnx=fusionmodel_final_inNHWC-float32-255_outNHWC-float32-1.onnx
--saveEngine=x86/fusionmodel_final_inNHWC-float32-255_outNHWC-float32-1.trt
--sparsity=enable
--noTF32
--fp16
--int8
--skipInference
--minShapes=img_vis:1x100x100x3,img_ir:1x100x100x1
--optShapes=img_vis:1x480x640x3,img_ir:1x480x640x1
--maxShapes=img_vis:1x480x640x3,img_ir:1x480x640x1
--builderOptimizationLevel=0
加载tensorrt模型时报错:
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.