Comments (13)
Hi,
Do you know how to download the dataset and unzip it from the link below?
https://drive.google.com/open?id=131dH36qXCabym1JjSmEpSQZg4dmZVQid
from pixel2mesh.
You can rename tf_nndistance_so.so to cd_dist.so and replace original cd_dist.so with that
from pixel2mesh.
I do replacement, but still get the following error. Compile PointSetGeneration with make good enough? Any changes in PointSetGeneration? Thanks.
/Pixel2Mesh/pixel2mesh# python demo.py --image utils/examples/
Traceback (most recent call last):
File "demo.py", line 3, in
from models import GCN
File "/Pixel2Mesh/pixel2mesh/models.py", line 3, in
from losses import *
File "/Pixel2Mesh/pixel2mesh/losses.py", line 2, in
from cd_dist import *
ImportError: dynamic module does not define init function (initcd_dist)
from pixel2mesh.
after replacement, when I run the demo, I find these problem: "undefined symbol: _ZTIN10tensorflow8OpKernelE", This is because when compiling code with g++, it is not used by the tensorflow_framework.so dynamic library. But I don't know how to use it. Have you encountered this problem?
from pixel2mesh.
I do replacement, but still get the following error. Compile PointSetGeneration with make good enough? Any changes in PointSetGeneration? Thanks.
/Pixel2Mesh/pixel2mesh# python demo.py --image utils/examples/
Traceback (most recent call last):
File "demo.py", line 3, in
from models import GCN
File "/Pixel2Mesh/pixel2mesh/models.py", line 3, in
from losses import *
File "/Pixel2Mesh/pixel2mesh/losses.py", line 2, in
from cd_dist import *
ImportError: dynamic module does not define init function (initcd_dist)
I also meet this problem. have you figured it out?
from pixel2mesh.
I have encountered this problem before, and I have solved it now.
If your cuda‘s version is not 8.0, You must recompile in the PointSetGeneration project.
But the ’makefile‘ could not be used directly.
My revised makefile file is as follows :
cudalib = /usr/local/cuda-9.0/lib64/
tensorflow = /usr/local/lib/python2.7/dist-packages/tensorflow/include
TF_INC=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_include())')
all: depthestimate/tf_nndistance_so.so depthestimate/render_balls_so.so
.PHONY : all
depthestimate/tf_nndistance_so.so: depthestimate/tf_nndistance_g.cu.o depthestimate/tf_nndistance.cpp
g++ -std=c++11 -shared depthestimate/tf_nndistance.cpp depthestimate/tf_nndistance_g.cu.o -o depthestimate/tf_nndistance_so.so -fPIC -I $TF_INC -O2
depthestimate/tf_nndistance_g.cu.o: depthestimate/tf_nndistance_g.cu
$(nvcc) -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 -c -o depthestimate/tf_nndistance_g.cu.o depthestimate/tf_nndistance_g.cu -I $(tensorflow) -DGOOGLE_CUDA=1 -x cu -Xcompiler -fPIC -O2
depthestimate/render_balls_so.so: depthestimate/render_balls_so.cpp
g++ -std=c++11 depthestimate/render_balls_so.cpp -o depthestimate/render_balls_so.so -shared -fPIC -O2 -D_GLIBCXX_USE_CXX11_ABI=0
For reference only, thanks again for sharing.
from pixel2mesh.
I have encountered this problem before, and I have solved it now.
If your cuda‘s version is not 8.0, You must recompile in the PointSetGeneration project.
But the ’makefile‘ could not be used directly.
My revised makefile file is as follows :cudalib = /usr/local/cuda-9.0/lib64/ tensorflow = /usr/local/lib/python2.7/dist-packages/tensorflow/include TF_INC=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_include())') all: depthestimate/tf_nndistance_so.so depthestimate/render_balls_so.so .PHONY : all depthestimate/tf_nndistance_so.so: depthestimate/tf_nndistance_g.cu.o depthestimate/tf_nndistance.cpp g++ -std=c++11 -shared depthestimate/tf_nndistance.cpp depthestimate/tf_nndistance_g.cu.o -o depthestimate/tf_nndistance_so.so -fPIC -I $TF_INC -O2 depthestimate/tf_nndistance_g.cu.o: depthestimate/tf_nndistance_g.cu $(nvcc) -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 -c -o depthestimate/tf_nndistance_g.cu.o depthestimate/tf_nndistance_g.cu -I $(tensorflow) -DGOOGLE_CUDA=1 -x cu -Xcompiler -fPIC -O2 depthestimate/render_balls_so.so: depthestimate/render_balls_so.cpp g++ -std=c++11 depthestimate/render_balls_so.cpp -o depthestimate/render_balls_so.so -shared -fPIC -O2 -D_GLIBCXX_USE_CXX11_ABI=0
For reference only, thanks again for sharing.
Hi @jinglunYang I recompiled, but encounter the following issue. Do you have any ideas? Thanks!
$ sudo python demo.py --image utils/examples/plane.png
Traceback (most recent call last):
File "demo.py", line 3, in
from pixel2mesh.models import GCN
File "build/bdist.linux-x86_64/egg/pixel2mesh/models.py", line 3, in
from pixel2mesh.losses import *
File "build/bdist.linux-x86_64/egg/pixel2mesh/losses.py", line 2, in
from pixel2mesh.cd_dist import *
File "build/bdist.linux-x86_64/egg/pixel2mesh/cd_dist.py", line 3, in
nn_distance_module=tf.load_op_library('./cd_dist.so')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/load_library.py", line 60, in load_op_library
lib_handle = py_tf.TF_LoadLibrary(library_filename)
tensorflow.python.framework.errors_impl.NotFoundError: ./cd_dist.so: undefined symbol: _ZTIN10tensorflow8OpKernelE
Maybe you should execute 'python setup.py. install' again.I think your program used the old cd_dist.so
from pixel2mesh.
@XuXianbing I met the same problem, have you solved it ? Can you help me, thanks!
from pixel2mesh.
@XuXianbing I met the same problem, have you solved it ? Can you help me, thanks!
when I change the TF1.4 to TF1.3, the problem was solved! Maybe your TF version is 1.4+, you can try TF1.3.
from pixel2mesh.
@XuXianbing Yes, my TF is 1.9. Do you just change the TF version? Have you recomplie the .so file in the PointSetGeneration project? Or you compile your .so file in the external folder directly? Thx!
from pixel2mesh.
@XuXianbing Yes, my TF is 1.9. Do you just change the TF version? Have you recomplie the .so file in the PointSetGeneration project? Or you compile your .so file in the external folder directly? Thx!
Yes, first you should compile the .so file in the PointSetGeneration project, rename tf_nndistance_so.so to cd_dist.so and replace original cd_dist.so. If your TF version is 1.3, you won't encounter this problem!
from pixel2mesh.
@XuXianbing OK, I will try, thanks
from pixel2mesh.
If there is no further discussion, I will temporarily close this issue, and if there is any problem, please feel free to open again.
from pixel2mesh.
Related Issues (20)
- Train on dataset of images
- How do you train this on a own dataset of 3d models? HOT 3
- tensorflow.python.framework.errors_impl.InvalidArgumentError
- How to create our own datasets? HOT 1
- The passed save_path is not a valid checkpoint: Data/checkpoint/gcc.ckpt
- Question about GenerateData HOT 1
- Is 4_make_auxiliary_dat_file.ipynb supposed to generate the same formatted dat files as the ones in the gdrive of shapenet? HOT 2
- One problem about some trick things
- Pixel2Mesh commercial use inquiry
- How does converting the .xyz file to a .dat file work ? HOT 5
- How to get texture?
- No module named 'layers' HOT 2
- Is the support constant in all shapes(airplane, car, ellipsoid)?
- Intrinsic camera parameters for rendered views
- Ellipsoidal data generation
- Error running Pixel2Mesh in Google Colab: "python2: command not found" HOT 2
- Cannot interpret feed_dict error
- tf_nndistance_so.so not found HOT 2
- training problem
- Weighted chamfer loss and Weighted Edge Length Regularization
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pixel2mesh.