TF-TRT Error on Jetson Nano

SunilJB · August 26, 2021, 7:18am

Hi @skilic
Please refer to below topic as well in case it helps:

Tensorflow TensorRT: Could not load dynamic library 'libnvinfer.so.5'

opened 10:53PM - 15 Nov 19 UTC

closed 12:05AM - 16 Nov 19 UTC

<em>Please make sure that this is a bug. As per our [GitHub Policy](https://gith…ub.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template</em> **System information** - Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04.3 LTS - TensorFlow installed from (source or binary): Binary - TensorFlow version (use command below): Tensorflow 2.0 - Python version: 3.7.4 - CUDA/cuDNN version: 10.0 - GPU model and memory: V100 **Describe the current behavior** _(Note - also posted to NVIDIA developer forums)_ I'm following the Tensorflow 2.0 [instructions](https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html#usage-example) for optimizing a SavedModel file with TensorRT. I have my Tensorflow model saved to models/mymodel. When I run the following: ``` from tensorflow.python.compiler.tensorrt import trt_convert as trt converter = trt.TrtGraphConverterV2(input_saved_model_dir='models/mymodel') converter.convert() converter.save('models/mymodel_tensorrt') ``` I get the error (from second line): > 2019-11-14 17:29:07.427738: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer.so.5'; dlerror: libnvinfer.so.5: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib64/openmpi/lib/:/usr/local/cuda/lib64:/usr/local/lib:/usr/lib:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/mpi/lib:/lib/:/home/ubuntu/src/cntk/bindings/python/cntk/libs:/usr/local/cuda/lib64:/usr/local/lib:/usr/lib:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/mpi/lib:/usr/lib64/openmpi/lib/:/usr/local/cuda/lib64:/usr/local/lib:/usr/lib:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/mpi/lib:/lib/: 2019-11-14 17:29:07.427783: F tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:49] getInferLibVersion symbol not found. Aborted (core dumped) Looking at the thread [here](https://devtalk.nvidia.com/default/topic/1036527/tensorrt/importerror-libnvinfer-so-4-cannot-open-shared-object-file-no-such-file-or-directory/), it seems like it may be an issue with needing to set LD_LIBRARY_PATH. However, when I google setting the LD_LIBRARY_PATH, it seems only necessary when manually installing TensorRT from tar. I have not built/installed TensorRT separately and am just using what's bundled in with Tensorflow 2.0. **Describe the expected behavior** The converter should run and save optimized model to 'models/mymodel_tensorrt'

Thanks

Topic		Replies	Views
TF-TRT Converter Error on Jetson Nano Jetson Nano tensorrt , tensorflow	2	483	October 15, 2021
TF-TRT optimization TensorRT tensorrt , tensorflow , jetson-inference	4	4945	June 2, 2021
TF-TRT on Jetson Nano Jetson Nano tensorrt , tensorflow , ubuntu	4	3098	June 25, 2021
Converting Tensorflow .pb models to TensorRT Models to run on the Nano Jetson Nano tensorrt , tensorflow	9	910	October 18, 2021
TF-TRT issue Jetson TX2	26	3827	October 18, 2021
Cannot Convert Custom Model To TensorRT TensorRT	10	1757	October 12, 2021
Jetson Nano: Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory TensorRT	4	8082	August 3, 2022
TF-TRT Errors fetching dynamic library TensorRT tensorrt , cuda , tensorflow , ubuntu , tf-trt	5	1385	October 27, 2021
Jetson Orin Nano Developer Kit, Jetpack, Cuda, Tensorflow with GPU and TensorRT Jetson Orin Nano tensorflow	16	3427	September 28, 2023
TF-TRT conversion is broken on 32.7.1 Jetson AGX Xavier tensorflow , docker	11	1582	April 6, 2022

TF-TRT Error on Jetson Nano

Related topics