search

SeanNaren / warp-ctc

Pytorch Bindings for warp-ctc
Apache License 2.0
757 stars 271 forks source link

CUDA 10 support #134

Closed vadimkantorov closed 5 years ago

vadimkantorov commented 5 years ago

CMakeLists.txt needs to be modified. Also suggested in https://github.com/SeanNaren/warp-ctc/issues/116#issuecomment-475145386 .

Otherwise test_gpu does not pass and CTCLoss returns 0.0.

   IF (CUDA_VERSION GREATER 7.6)
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_60,code=sm_60")
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_61,code=sm_61")
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_62,code=sm_62")
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_70,code=sm_70") ## new line
ENDIF()
sdzbft commented 5 years ago

you can use CTC Loss in pytorch 1.0.1 directly without warp_ctc

SeanNaren commented 5 years ago

warp-ctc does support this compute architecture already, the change was made here