Installing tensorrflow with bazel on jetson nano 4gb

AI & Data Science Deep Learning (Training & Inference) TensorRT
,
1

hello
while trying to build tensorflow 2.4.0 on jetson nano I get the following error
ERROR: /home/hm/tensorflow/tensorflow/compiler/tf2tensorrt/BUILD:39:1: C++ compilation of rule ‘//tensorflow/compiler/tf2tensorrt:tensorrt_stub’ failed (Exit 1)
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:58:0:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc: In function ‘void* createInferBuilder_INTERNAL(void*, int)’:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc:5:7: error: declaration of ‘void* createInferBuilder_INTERNAL(void*, int)’ has a different exception specifier
void* createInferBuilder_INTERNAL(void* logger, int version) {
^~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:17:0:
bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInfer.h:8791:30: note: from previous declaration ‘void* createInferBuilder_INTERNAL(void*, int32_t) noexcept’
extern “C” TENSORRTAPI void* createInferBuilder_INTERNAL(void* logger, int32_t version) noexcept;
^~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:58:0:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc: In function ‘void* createInferRefitter_INTERNAL(void*, void*, int)’:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc:12:7: error: declaration of ‘void* createInferRefitter_INTERNAL(void*, void*, int)’ has a different exception specifier
void* createInferRefitter_INTERNAL(void* engine, void* logger, int version) {
^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInfer.h:54:0,
from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:17:
bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInferRuntime.h:2581:30: note: from previous declaration ‘void* createInferRefitter_INTERNAL(void*, void*, int32_t) noexcept’
extern “C” TENSORRTAPI void* createInferRefitter_INTERNAL(void* engine, void* logger, int32_t version) noexcept;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:58:0:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc: In function ‘void* createInferRuntime_INTERNAL(void*, int)’:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc:19:7: error: declaration of ‘void* createInferRuntime_INTERNAL(void*, int)’ has a different exception specifier
void* createInferRuntime_INTERNAL(void* logger, int version) {
^~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInfer.h:54:0,
from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:17:
bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInferRuntime.h:2575:30: note: from previous declaration ‘void* createInferRuntime_INTERNAL(void*, int32_t) noexcept’
extern “C” TENSORRTAPI void* createInferRuntime_INTERNAL(void* logger, int32_t version) noexcept;
^~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:58:0:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc: In function ‘nvinfer1::ILogger* getLogger()’:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc:26:20: error: declaration of ‘nvinfer1::ILogger* getLogger()’ has a different exception specifier
nvinfer1::ILogger* getLogger() {
^~~~~~~~~
In file included from bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInfer.h:54:0,
from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:17:
bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInferRuntime.h:2593:43: note: from previous declaration ‘nvinfer1::ILogger* getLogger() noexcept’
extern “C” TENSORRTAPI nvinfer1::ILogger* getLogger() noexcept;
^~~~~~~~~
In file included from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:58:0:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc: In function ‘nvinfer1::IPluginRegistry* getPluginRegistry()’:
./tensorflow/compiler/tf2tensorrt/stub/NvInfer_5_1.inc:40:28: error: declaration of ‘nvinfer1::IPluginRegistry* getPluginRegistry()’ has a different exception specifier
nvinfer1::IPluginRegistry* getPluginRegistry() {
^~~~~~~~~~~~~~~~~
In file included from bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInfer.h:54:0,
from tensorflow/compiler/tf2tensorrt/stub/nvinfer_stub.cc:17:
bazel-out/aarch64-opt/bin/external/local_config_tensorrt/_virtual_includes/tensorrt_headers/third_party/tensorrt/NvInferRuntime.h:2586:51: note: from previous declaration ‘nvinfer1::IPluginRegistry* getPluginRegistry() noexcept’
extern “C” TENSORRTAPI nvinfer1::IPluginRegistry* getPluginRegistry() noexcept;
^~~~~~~~~~~~~~~~~
Target //tensorflow/tools/pip_package:build_pip_package failed to build
Use --verbose_failures to see the command lines of failed build steps.
INFO: Elapsed time: 5777.909s, Critical Path: 571.98s
INFO: 1598 processes: 1598 local.
FAILED: Build did NOT complete successfully

TensorRT Version: 8
GPU Type:
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version: 8.7
please what is the solution to this
Regards
Abdullah

2

Hi,

This looks like a Jetson issue. Please refer to the below samples in case useful.

For any further assistance, we will move this post to to Jetson related forum.

Thanks!

5

hello Aakanksha
thanks for the response
I would fellow this following again
regards

Abdullah

6

the reference made was made using pytorch but am using tensrflow tensorrt and also I do not want to run it using a docker but I want to build it on jetson nano because I’m working on a custom project

7

Hi Abdullah, I have same issue when using bazel to compile tensorflow 2.4.0. Do you solve your problem?
Appreciate for any suggestion. Thank you for your help.

8

I wasn’t able to compile using bazel, I had to run a tensorflow docker to get the work done