def _call_nms_kernel(bbox, thresh):
n_bbox = bbox.shape[0]
threads_per_block = 64
col_blocks = np.ceil(n_bbox / threads_per_block).astype(np.int32)
blocks = (col_blocks, col_blocks, 1)
threads = (threads_per_block, 1, 1)
mask_dev = cp.zeros((n_bbox * col_blocks, ), dtype=np.uint64)
bbox = cp.ascontiguousarray(bbox, dtype=np.float32)
kern = _load_kernel('nms_kernel', _nms_gpu_code)
kern(blocks, threads, args=(n_bbox, cp.float32(thresh), bbox, mask_dev))
mask_host = mask_dev.get()
selection, n_selec = _nms_gpu_post(mask_host, n_bbox, threads_per_block,
col_blocks)
return selection, n_selec
def _call_nms_kernel(bbox, thresh):
n_bbox = bbox.shape[0]
threads_per_block = 64
col_blocks = np.ceil(n_bbox / threads_per_block).astype(np.int32)
blocks = (col_blocks, col_blocks, 1)
threads = (threads_per_block, 1, 1)
mask_dev = cp.zeros((n_bbox * col_blocks,), dtype=np.uint64)
bbox = cp.ascontiguousarray(bbox, dtype=np.float32)
kern = _load_kernel('nms_kernel', _nms_gpu_code)
kern(blocks, threads, args=(cp.int32(n_bbox), cp.float32(thresh),
bbox, mask_dev))
mask_host = mask_dev.get()
selection, n_selec = _nms_gpu_post(
mask_host, n_bbox, threads_per_block, col_blocks)
return selection, n_selec