如何提取更多GPU进行图像拼接OpenCV-Python

如何解决如何提取更多GPU进行图像拼接OpenCV-Python

我有什么选择？如何为我的功能实现更多的GPU计算？

def composePanorama(self):
    # dst_sz,warper,cameras,corners,masks_warped = cached
    self.blender.prepare(self.dst_sz)
    for idx,name in enumerate(self.img_names):
        corner,image_warped = self.warper.warp(name,self.cameras[idx].K().astype(np.float32),self.cameras[idx].R,cv2.INTER_LINEAR,cv2.BORDER_REFLECT)
        p,mask_warped = self.warper.warp(255 * np.ones((name.shape[0],name.shape[1]),np.uint8),cv2.INTER_NEAREST,cv2.BORDER_CONSTANT)
        self.compensator.apply(idx,self.corners[idx],image_warped,mask_warped)
        mask_warped = cv2.bitwise_and(cv2.resize(cv2.dilate(self.masks_warped[idx],None),(mask_warped.shape[1],mask_warped.shape[0]),cv2.INTER_LINEAR_EXACT),mask_warped)
        self.blender.Feed(cv2.UMat(image_warped.astype(np.int16)),mask_warped,self.corners[idx])
    result,result_mask = self.blender.blend(None,None)
    dst = cv2.normalize(src=result,dst=None,alpha=255.,norm_type=cv2.norM_MINMAX,dtype=cv2.CV_8U)
    return dst

这是我的完整代码示例； https://gist.github.com/Tony363/62aa16d30a1fcbe5115ffa316d6727e1