warp-ctc
warp-ctc copied to clipboard
Published
20 hours ago •
SeanNaren
SeanNaren
make[2]: *** [CMakeFiles/warpctc.dir/build.make:72：CMakeFiles/warpctc.dir/src/warpctc_generated_reduce.cu.o] 错误 1
I followed the steps here to make warp-ctc:
git clone https://github.com/SeanNaren/warp-ctc.git
cd warp-ctc
git checkout ac045b6072b9bc3454fb9f9f17674f0d59373789
mkdir build; cd build
cmake ..
make
I failed at the step of make and get:
/home/x/ææ¡£/Deep_Learning/NLP/Chinese_OCR/Lets_OCR/recognizer/warp-ctc/src/reduce.cu(44): error: identifier "__shfl_down" is undefined
detected during:
instantiation of "T CTAReduce<NT, T, Rop>::reduce(int, T, CTAReduce<NT, T, Rop>::Storage &, int, Rop) [with NT=128, T=float, Rop=ctc_helper::add<float, float>]"
(76): here
instantiation of "void reduce_rows<NT,Iop,Rop,T>(Iop, Rop, const T *, T *, int, int) [with NT=128, Iop=ctc_helper::negate<float, float>, Rop=ctc_helper::add<float, float>, T=float]"
(124): here
instantiation of "void ReduceHelper::impl(Iof, Rof, const T *, T *, int, int, __nv_bool, cudaStream_t) [with T=float, Iof=ctc_helper::negate<float, float>, Rof=ctc_helper::add<float, float>]"
(139): here
instantiation of "ctcStatus_t reduce(Iof, Rof, const T *, T *, int, int, __nv_bool, cudaStream_t) [with T=float, Iof=ctc_helper::negate<float, float>, Rof=ctc_helper::add<float, float>]"
(149): here
/home/x/ææ¡£/Deep_Learning/NLP/Chinese_OCR/Lets_OCR/recognizer/warp-ctc/src/reduce.cu(44): error: identifier "__shfl_down" is undefined
detected during:
instantiation of "T CTAReduce<NT, T, Rop>::reduce(int, T, CTAReduce<NT, T, Rop>::Storage &, int, Rop) [with NT=128, T=float, Rop=ctc_helper::maximum<float, float>]"
(76): here
instantiation of "void reduce_rows<NT,Iop,Rop,T>(Iop, Rop, const T *, T *, int, int) [with NT=128, Iop=ctc_helper::identity<float, float>, Rop=ctc_helper::maximum<float, float>, T=float]"
(124): here
instantiation of "void ReduceHelper::impl(Iof, Rof, const T *, T *, int, int, __nv_bool, cudaStream_t) [with T=float, Iof=ctc_helper::identity<float, float>, Rof=ctc_helper::maximum<float, float>]"
(139): here
instantiation of "ctcStatus_t reduce(Iof, Rof, const T *, T *, int, int, __nv_bool, cudaStream_t) [with T=float, Iof=ctc_helper::identity<float, float>, Rof=ctc_helper::maximum<float, float>]"
(157): here
2 errors detected in the compilation of "/tmp/tmpxft_00005cf8_00000000-13_reduce.compute_70.cpp1.ii".
CMake Error at warpctc_generated_reduce.cu.o.cmake:279 (message):
Error generating file
/home/x/文档/Deep_Learning/NLP/Chinese_OCR/Lets_OCR/recognizer/warp-ctc/build/CMakeFiles/warpctc.dir/src/./warpctc_generated_reduce.cu.o
make[2]: *** [CMakeFiles/warpctc.dir/build.make:72：CMakeFiles/warpctc.dir/src/warpctc_generated_reduce.cu.o] 错误 1
make[1]: *** [CMakeFiles/Makefile2:72：CMakeFiles/warpctc.dir/all] 错误 2
make: *** [Makefile:130：all] 错误 2
Anyone could help? Thanks at advance.
可以先用https://github.com/baidu-research/warp-ctc 的源码安装warp-ctc，成功后，返回到本项目的源码目录，cd ../pytorch_binding，修改setup.py中的warp_ctc_path = "../build"，改为baidu的build目录，然后再执行python setup.py install，但是libwarpctc.dylib这个文件没有找到，不过Example代码执行没问题。 有没有其他大神把这个问题解决了的？
