tensorflow implementation
esgnn opened this issue · comments
Hi,
Would you mind sharing how to implement in tensorflow in more detail?
Thanks
We have updated README.md to include more details.
dear,
The same question about that.
dear,
Would you mind sharing how to implement in tensorflow such as Window or Ubuntu, Python 2 or Python 3, .... from installing the beginning.
The same question for Matlab, C++.
THANK YOU.
Hello, we just implement part of the whole model in Tensorflow using Python2. Others of this model are implemented by Caffe using C++. If you have an interest in this project, we expect you to transfer whole model into Tensorflow or MXNET.
dear @chanyn ,
Did You implement Project in Ubuntu or Window? I want to rebuild them.
This project is implemented in Ubuntu.
Dear Chanyn,
I am interested in porting this into TensorFlow. My initial question in this regard is how do I identify without digging much into the code, which parts are already implemented in tensorflow and which is in Caffe. Please bear my ignorance, as I don't have any experience with Caffe. Especially which folders in the caffe should I look into carefully.
dear @chanyn,
I have plan to change into tensorflow but I currently have not experience to build caffe. I have the problem to install.
dear @chanyn,
I still have issues in make caffe.
Can you help me?
(OpenSSL) binh@binh:~/3Dpose_ssl/caffe-3dssl$ make all
CXX src/caffe/solver.cpp
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
from ./include/caffe/common.hpp:19,
from ./include/caffe/blob.hpp:8,
from ./include/caffe/net.hpp:10,
from ./include/caffe/solver.hpp:7,
from src/caffe/solver.cpp:6:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
switch (status) {
^
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:113:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
cudnnStatus_t status = condition;
^
In file included from ./include/caffe/util/cudnn.hpp:5:0,
from ./include/caffe/util/device_alternate.hpp:40,
from ./include/caffe/common.hpp:19,
from ./include/caffe/blob.hpp:8,
from ./include/caffe/net.hpp:10,
from ./include/caffe/solver.hpp:7,
from src/caffe/solver.cpp:6:
/home/binh/anaconda2/envs/OpenSSL/include/cudnn.h:500:27: note: declared here
cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
^
Makefile:575: recipe for target '.build_release/src/caffe/solver.o' failed
make: *** [.build_release/src/caffe/solver.o] Error 1
dear @chanyn,
I still have issues in make caffe.
Can you help me?
(OpenSSL) binh@binh:~/3Dpose_ssl/caffe-3dssl$ make all
CXX src/caffe/solver.cpp
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
from ./include/caffe/common.hpp:19,
from ./include/caffe/blob.hpp:8,
from ./include/caffe/net.hpp:10,
from ./include/caffe/solver.hpp:7,
from src/caffe/solver.cpp:6:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
switch (status) {
^
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:113:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
cudnnStatus_t status = condition;
^
In file included from ./include/caffe/util/cudnn.hpp:5:0,
from ./include/caffe/util/device_alternate.hpp:40,
from ./include/caffe/common.hpp:19,
from ./include/caffe/blob.hpp:8,
from ./include/caffe/net.hpp:10,
from ./include/caffe/solver.hpp:7,
from src/caffe/solver.cpp:6:
/home/binh/anaconda2/envs/OpenSSL/include/cudnn.h:500:27: note: declared here
cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
^
Makefile:575: recipe for target '.build_release/src/caffe/solver.o' failed
make: *** [.build_release/src/caffe/solver.o] Error 1
Please try cudnn 5.1 instead.
dear @kezewang,
Can you give me a moment though temviewer?
dear @kezewang ,
can you help me?
Dear @NguyenDangBinh,
do you address your issue?