roi_pooling.so Makefile

[symechar]

Hello, i get the following error: tensorflow.python.framework.errors_impl.NotFoundError: ~/nms_net/roi_pooling_layer/roi_pooling.so: undefined symbol: _ZN10tensorflow7strings6StrCatB5cxx11ERKNS0_8AlphaNumE Is there any advice solving it?

[SchroeterJulien]

Hi,

While this will certainly be too late for the original author of the question, here is what worked for me (Tensorflow 1.14). Disclaimer: I mostly don't know what I am doing, so if you are a real and rigorous programmer apologies in advance. But at least the following worked for me, thus it might help others out:

1. In Makefile, add -D_GLIBCXX_USE_CXX11_ABI=0 to each g++ command. This might already fix it for some. [1] [2]

2. In Makefile, add -L$TF_LIB -ltensorflow_framework to each g++ command, where TF_LIB=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_lib())') (this need to be added in the first lines). [3] [4] [5]. Depending on how you set things up on your computer, you might need to replace python with python3.

3. Check manually that you have a file called libtensorflow_framework.so in $TF_LIB (see point 2. on how to obtain that path). If not, you should have a file that is almost called like it (e.g., libtensorflow_framework.so.1). In that case, you need to create a symbolic link [6]:

$ cd [$TF_LIB]
$ ln -s libtensorflow_framework.so.1 libtensorflow_framework.so

4. In Makefile, add -lcudart -L $CUDA_PATH/lib64 to each g++ command, where CUDA_PATH=/usr/local/cuda/ (this need to be added in the first lines). To locate where cuda was installed on your machine (e.g., it might be /usr/local/cuda-10.0/) check [6]

At that point, it should be working. But if for some reason it is not, you might still try one last trick while you are at it: replace every variable containing a path (e.g., "L$TF_LIB") with a "fixed text" (e.g., -L/home/julien/.local/lib/python3.6/site-packages/tensorflow). In the end here is the version that worked for me (it is not pretty, but does the job):

TF_INC="/home/julien/.local/lib/python3.6/site-packages/tensorflow/include/" #$(python3 -c 'import tensorflow as tf; print(tf.sysconfig.get_include())')
TF_LIB="/home/julien/.local/lib/python3.6/site-packages/tensorflow" #$(python3 -c 'import tensorflow as tf; print(tf.sysconfig.get_lib())')

.PHONY: all

all: nms_net/matching_module/det_matching.so nms_net/roi_pooling_layer/roi_pooling.so imdb/file_formats/AnnoList_pb2.py

nms_net/roi_pooling_layer/roi_pooling.so: nms_net/roi_pooling_layer/roi_pooling_op.o nms_net/roi_pooling_layer/roi_pooling_op_gpu.o
	g++ -std=c++11 -shared $^ -o $@ -fPIC -O2 -lcudart -L/usr/local/cuda-10.0/lib64 -D_GLIBCXX_USE_CXX11_ABI=0 -L/home/julien/.local/lib/python3.6/site-packages/tensorflow -ltensorflow_framework

%.o: %.cc
	g++ -std=c++11 -c $< -o $@ -fPIC -I ${TF_INC} -O2 -lcudart -L/usr/local/cuda-10.0/lib64 -D_GLIBCXX_USE_CXX11_ABI=0 -L/home/julien/.local/lib/python3.6/site-packages/tensorflow -ltensorflow_framework

%.o: %.cu
	nvcc -std=c++11 -c $< -o $@ -I ${TF_INC} -O2 -x cu -arch=sm_35 -D GOOGLE_CUDA=1 -Xcompiler -fPIC

%.so: %.cc
	g++ -std=c++11 -shared $< -o $@ -fPIC -I ${TF_INC} -O2 -lcudart -L/usr/local/cuda-10.0/lib64 -D_GLIBCXX_USE_CXX11_ABI=0 -L/home/julien/.local/lib/python3.6/site-packages/tensorflow -ltensorflow_framework

%_pb2.py: %.proto
	protoc --python_out=. $<

Hope that these loose instructions will help someone.