gylee1103 / saliencyeld Goto Github PK
View Code? Open in Web Editor NEWSource code for Deep Saliency with Encoded Low Level Distance Map and High Level Features, CVPR 2016.
Source code for Deep Saliency with Encoded Low Level Distance Map and High Level Features, CVPR 2016.
This work is really great! It will be really helpful for my future research!
Hi gylee1103,
Thank you so much for sharing the codes!
I git clone your source code and everything goes fine with building caffe and your code, but when I tried to start to test the model, I got stuck.
like:
$ ./SaliencyELD ../test_images
bash: ./SaliencyELD: Permission denied
then
$ sudo ./SaliencyELD ../test_images
sudo: ./SaliencyELD: command not found
and type 'ls -l' in /SaliencyELD/build/ directory
$ ls -l
total 140
-rw------- 1 archer archer 20846 9月 30 18:04 CMakeCache.txt
drwx------ 1 archer archer 488 9月 30 18:04 CMakeFiles
-rw------- 1 archer archer 1678 9月 30 18:04 cmake_install.cmake
-rw------- 1 archer archer 7688 9月 30 18:04 Makefile
-rw------- 1 archer archer 104534 9月 30 18:04 SaliencyELD
Could you please help me?
Thank you very much!
Because of the 'great wall' in china, 'www.dropbox.com' is blocked.
Could you please upload it to some other cloud disks, or send it to my email([email protected]).
I'll appreciate your help.
如何用matlab使用其中的代码
Could you please specify in the README which CUDA and CUDNN versions you used ?
I am unable to compile the provided caffe code with CUDA 8.0 and CUDNN 4 or 5.
I get errors relative to cudnn
-- Generating /data/TREC/TMPTMP/SaliencyELD/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_cudnn_conv_layer.cu.o
/usr/local/cuda/bin/nvcc /data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu -c -o /data/TREC/TMPTMP/SaliencyELD/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_cudnn_conv_layer.cu.o -ccbin /usr/bin/gcc -m64 -DUSE_LMDB -DUSE_LEVELDB -DUSE_CUDNN -DUSE_OPENCV -DWITH_PYTHON_LAYER -DGTEST_USE_OWN_TR1_TUPLE -Xcompiler ,\"-fPIC\",\"-Wall\",\"-Wno-sign-compare\",\"-Wno-uninitialized\",\"-O3\",\"-DNDEBUG\" -I/net/Tools/CUDNN4/cuda/include -Xcompiler -I/net/Tools/CUDNN4/cuda/include -gencode arch=compute_35,code=sm_35 -Xcudafe --diag_suppress=cc_clobber_ignored -Xcudafe --diag_suppress=integer_sign_change -Xcudafe --diag_suppress=useless_using_declaration -Xcudafe --diag_suppress=set_but_not_used -Xcompiler -fPIC -DNVCC -I/usr/local/cuda/include -I/data/TREC/TMPTMP/SaliencyELD/caffe/src -I/usr/include -I/data/TREC/TMPTMP/SaliencyELD/caffe/build/include -I/net/Tools/CUDNN4/cuda/include -I/usr/local/cuda/include -I/net/Tools/include -I/net/Tools/include/opencv -I/usr/include/python2.7 -I/usr/labri/mansenca/.local/lib/python2.7/site-packages/numpy/core/include -I/data/TREC/TMPTMP/SaliencyELD/caffe/include -I/data/TREC/TMPTMP/SaliencyELD/caffe/build
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "cudnnAddMode_t" is incompatible with parameter of type "const void *"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "const void *" is incompatible with parameter of type "cudnnTensorDescriptor_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "const void *" is incompatible with parameter of type "cudnnTensorDescriptor_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: too many arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: argument of type "const void *" is incompatible with parameter of type "cudnnConvolutionBwdFilterAlgo_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: argument of type "float *" is incompatible with parameter of type "size_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: too few arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: argument of type "const void *" is incompatible with parameter of type "cudnnConvolutionBwdDataAlgo_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: argument of type "float *" is incompatible with parameter of type "size_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: too few arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=float]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "cudnnAddMode_t" is incompatible with parameter of type "const void *"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "const void *" is incompatible with parameter of type "cudnnTensorDescriptor_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: argument of type "const void *" is incompatible with parameter of type "cudnnTensorDescriptor_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(81): error: too many arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: argument of type "const void *" is incompatible with parameter of type "cudnnConvolutionBwdFilterAlgo_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: argument of type "double *" is incompatible with parameter of type "size_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(125): error: too few arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: argument of type "const void *" is incompatible with parameter of type "cudnnConvolutionBwdDataAlgo_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: argument of type "double *" is incompatible with parameter of type "size_t"
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
/data/TREC/TMPTMP/SaliencyELD/caffe/src/caffe/layers/cudnn_conv_layer.cu(140): error: too few arguments in function call
detected during instantiation of "void caffe::CuDNNConvolutionLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &, const std::vector<__nv_bool, std::allocator<__nv_bool>> &, const std::vector<caffe::Blob<Dtype> *, std::allocator<caffe::Blob<Dtype> *>> &) [with Dtype=double]"
(157): here
20 errors detected in the compilation of "/tmp/tmpxft_00010075_00000000-7_cudnn_conv_layer.cpp1.ii".
-- Removing /data/TREC/TMPTMP/SaliencyELD/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_cudnn_conv_layer.cu.o
/usr/bin/cmake -E remove /data/TREC/TMPTMP/SaliencyELD/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_cudnn_conv_layer.cu.o
CMake Error at cuda_compile_generated_cudnn_conv_layer.cu.o.cmake:266 (message):
Error generating file
/data/TREC/TMPTMP/SaliencyELD/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_cudnn_conv_layer.cu.o
It seems that we need to use CUDNN 3 and thus CUDA 7.0.
Could you confirm this ?
I have a question. When i operate 'make -j4', i cannot pass and have the error:
SaliencyELD-master/caffe/src/caffe/layers/cudnn_relu_layer.cu(20): error: argument of type "cudnnActivationMode_t" is incompatible with parameter of type "cudnnActivationDescriptor_t"
detected during instantiation of "void caffe::CuDNNReLULayer::Forward_gpu(const std::vector<caffe::Blob *, std::allocator<caffe::Blob *>> &, const std::vector<caffe::Blob *, std::allocator<caffe::Blob *>> &) [with Dtype=float]"
(54): here
We publish our journal codes ( https://github.com/gylee1103/ELDNet ) which are able to train easily.
The codes include modified caffe that contains gslic algorithm. Please use the modified caffe and refer $(PROJECT_ROOT)/training directory for your training.
*NOTE : You may need to disable CUDNN setting when build this repo (because of the impcompatibility between caffe and new version of CUDNN)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.