daijifeng001 / caffe-rfcn Goto Github PK
View Code? Open in Web Editor NEWCaffe branch for R-FCN
License: Other
Caffe branch for R-FCN
License: Other
How could i use it to train my own dataset? Is there a demo available? Thanks
When I build caffe-rfcn,I get errors:
错误 382 error : argument of type "int" is incompatible with parameter of type "cudnnNanPropagation_t" C:\Users\dell\Downloads\caffe-rfcn\include\caffe\util\cudnn.hpp 128 1 libcaffe
错误 383 error : too few arguments in function call C:\Users\dell\Downloads\caffe-rfcn\include\caffe\util\cudnn.hpp 128 1 libcaffe
错误 384 error : argument of type "int" is incompatible with parameter of type "cudnnNanPropagation_t" C:\Users\dell\Downloads\caffe-rfcn\include\caffe\util\cudnn.hpp 128 1 libcaffe
错误 385 error : too few arguments in function call C:\Users\dell\Downloads\caffe-rfcn\include\caffe\util\cudnn.hpp 128 1 libcaffe
错误 402 error MSB3721: 命令“"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\bin\nvcc.exe" -gencode=arch=compute_35,code=\"sm_35,compute_35\" -gencode=arch=compute_52,code=\"sm_52,compute_52\" -gencode=arch=compute_61,code=\"sm_61,compute_61\" --use-local-env --cl-version 2013 -ccbin "C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\bin\x86_amd64" -I"C:\Users\dell\Downloads\NugetPackages\lmdb-v120-clean.0.9.14.0\build\native\..\..\lib\native\include" -I"C:\Users\dell\Downloads\NugetPackages\LevelDB-vc120.1.2.0.0\build\native\../..//build/native/include/" -I"C:\Users\dell\Downloads\NugetPackages\protobuf-v120.2.6.1\build\native\../..//build/native/include/" -IC:\Users\dell\Downloads\NugetPackages\glog.0.3.3.0\build\native\../..//build/native/include/ -IC:\Users\dell\Downloads\NugetPackages\gflags.2.1.2.1\build\native\../..///build/native/include/ -IC:\Users\dell\Downloads\NugetPackages\boost.1.59.0.0\build\native\..\..\lib\native\include\ -I"C:\Users\dell\Downloads\NugetPackages\hdf5-v120-complete.1.8.15.2\build\native\..\..\lib\native\include" -IC:\Users\dell\Downloads\NugetPackages\OpenBLAS.0.2.14.1\build\native\..\..\lib\native\include -IC:\Users\dell\Downloads\NugetPackages\OpenCV.2.4.10\build\native\../../build/native/include/ -I"C:\Users\dell\Downloads\caffe-rfcn\windows\libcaffe\\..\..\src\\" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\include" -G -lineinfo --keep-dir C:\Users\dell\Downloads\caffe-rfcn\windows\..\Build\Int\libcaffe\x64\Debug -maxrregcount=0 --machine 64 --compile -cudart static -Xcudafe "--diag_suppress=exception_spec_override_incompat --diag_suppress=useless_using_declaration --diag_suppress=field_without_dll_interface" -D_SCL_SECURE_NO_WARNINGS -DGFLAGS_DLL_DECL= -g -DHAS_LMDB -DHAS_HDF5 -DHAS_OPENBLAS -DHAS_OPENCV -D_DEBUG -D_SCL_SECURE_NO_WARNINGS -DUSE_OPENCV -DUSE_LEVELDB -DUSE_LMDB -DMATLAB_MEX_FILE -DWITH_PYTHON_LAYER -DBOOST_PYTHON_STATIC_LIB -DUSE_CUDNN -D_UNICODE -DUNICODE -Xcompiler "/EHsc /W1 /nologo /Od /FS /Zi /RTC1 /MDd " -o C:\Users\dell\Downloads\caffe-rfcn\windows\..\Build\Int\libcaffe\x64\Debug\base_data_layer.cu.obj "C:\Users\dell\Downloads\caffe-rfcn\src\caffe\layers\base_data_layer.cu"”已退出,返回代码为 2。 C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V120\BuildCustomizations\CUDA 8.0.targets 687 9 libcaffe
My build environment is Windows 7+CUDA 8.0+CUDNN 5.1.
Is caffe-rfcn not support CUDA8.0+CUDNN 5.1?
Do you have any idea with the problem?
Thank you.
这个必须用MATLAB 吗?
Hi, I find two extra lines in softmax_loss_layer.cpp
// Fix a bug which occurs with more than one output
softmax_param.clear_loss_weight();
And I'm not sure why you add these or what will happen if I delete these two lines.
Thanks for devoting this project ! there is no demo_rfcn.py in tools file of my project? how should i train my own datasets? thank you !
I met a problem during compiling caffe, I post the screenshot image as below. The problem is "box_annotator_ohem_layer.cu(50): error: a template argument may not reference a local type"; I add "-std=C++11" in makefile of caffe, however , the problem is still there. So have you met the problem during compiling caffe?
i want build caffe-rfcn on windows 10. i build caffeproto and caffe successfully but cant build caffe.bin.
when i try build caffe.bin this error occur:
1>------ Build started: Project: caffe.bin, Configuration: Release x64 ------
1>LINK : fatal error LNK1149: output filename matches input filename 'D:\Artificial Intelligence\Deep Learning\Src\Caffe Branch\caffe-rfcn-r-fcn\caffe-rfcn-r-fcn\Build\lib\Release\caffe.lib'
========== Build: 0 succeeded, 1 failed, 3 up-to-date, 0 skipped ==========
my property command line :
/OUT:"D:\Artificial Intelligence\Deep Learning\Src\Caffe Branch\caffe-rfcn-r-fcn\caffe-rfcn-r-fcn\Build\tools\Release\caffe_rfcn.exe"
/IMPLIB:"D:/Artificial Intelligence/Deep Learning/Src/Caffe Branch/caffe-rfcn-r-fcn/caffe-rfcn-r-fcn/Build/lib/Release/caffe.lib"
why this error happen?
Hi,
I have used caffe framework for training text detection model using GPU mode. There are 4 such models are running simultaneously for 4 different use-cases. Running more than 2 models giving me CUDA memory error, so i increased compute power of my AWS EC2 instance to g4dn.12xlarge which costing me much higher and it is going beyond my budget.
So i am trying to inferencing this GPU trained caffe model to run in CPU mode and throw output so that my cost will be minimum. Please note training the model in GPU mode is done, i just wanted to use this model to run in CPU mode or CPU EC2 instance and get the output.
I tried below option:
Step 1:
Made changes in file "psroi_pooling_layer.cpp" as mentioned in below link and saved it.
https://github.com/daijifeng001/caffe-rfcn/pull/10/files
Step 2:
Set "caffe.set_mode_cpu()" and ran the script and getting error like "check failure stack trace"
Changes in code:
Please let me know where I am doing wrong or do I need to perform some additional steps?
Your quick response and help will be much appreciated.
Thank you,
Amar
How to fine tune your model? I don't have sufficient data to retrain your model from scratch.I want to fine tune your model on my data which has only two classes ?
In line 98 of softmax_loss_layer.cpp
, the function SoftmaxWithLossLayer::Forward_cpu leaves a macro NOT_IMPLEMENTED, and the runtest
fails. Could you explain why you remove it ?
thanks a lot for your great contribution, could we use it without matlab and cuda?
Does this caffe-rfcn only support cuDNN v3&v4??? Mine is cuDNN v6 and it doesn't work well.
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.