Speedup by using Numba CUDA

[bmabir17-asj]

For my use case(Large image size) the current processing takes a lot of time. I found that get_dark_channel and get_transmission functions takes a lot of time to process. Thus i decided to change the numba to use cuda by doing the below changes following this reference

@cuda.jit
    def get_dark_channel(self, radius=7):

@cuda.jit
    def get_transmission(self, radius=7, omega=0.95):

and called those as

    import sys
    hr = HazeRemoval()
    hr.open_image(sys.argv[1])
    #################### For CUDA
    # Set the number of threads in a block
    threadsperblock = 32 
    # Calculate the number of thread blocks in the grid
    blockspergrid = (hr.src.size + (threadsperblock - 1)) // threadsperblock
    ####################
    hr.get_dark_channel[blockspergrid, threadsperblock]()
    hr.get_air_light()
    hr.get_transmission[blockspergrid, threadsperblock]()
    hr.guided_filter()
    hr.recover()
    hr.show()

But i am getting the fllowing error

TypeError: Failed in nopython mode pipeline (step: fix up args)
Signature mismatch: 0 argument types given, but function takes 2 arguments

Has anyone tried to do this?