CUDA error 400: invalid resource handle

[dangnh0611]

Error encounting when working on Decord + TensorRT for inference time.

Reproduce

Code:

def _test2():
    # for tensorrt stuff
    import pycuda.autoinit
    import decord
    VIDEO_PATH = 'data/test_video.mp4'
    
    vr = decord.VideoReader(VIDEO_PATH, ctx=decord.gpu(0))
    frames = vr.get_batch([0,1,2])
    print(frames.shape)


if __name__ == '__main__':
    _test2()

Output with error:

CUDA error 400 at line 34 in file /workspace/libs/decord/src/video/nvcodec/cuda_mapped_frame.cc: invalid resource handle
Terminated

Remove the line import pycuda.autoinit, code exec normally without any error.

def _test2():
    # for tensorrt stuff
    # import pycuda.autoinit
    import decord
    VIDEO_PATH = 'data/test_video.mp4'
    
    vr = decord.VideoReader(VIDEO_PATH, ctx=decord.gpu(0))
    frames = vr.get_batch([0,1,2])
    print(frames.shape)


if __name__ == '__main__':
    _test2()

This may relate to this issue

Keywords: TensorRT, PyCUDA