1.问题现象：
两种写法都是更新tobj，为什么方法1（gather_nd+scatter_nd_add）耗时约8ms, 方法2（切片赋值）耗时约35ms。

2.问题示例代码如下：

import paddle
import datetime

tobj = paddle.load("test_tobj")
mask = paddle.load("test_mask")
score_iou = paddle.load("test_score_iou")
t_indices = paddle.load("test_t_indices")
gr = 1.0

print("tobj shape: {}, mask shape: {}".format(tobj.shape, mask.shape))

#方法1
def fun1(tobj, mask, score_iou,gr):
    start_time = datetime.datetime.now()
    with paddle.no_grad():
        x = paddle.gather_nd(tobj, mask)
        tobj = paddle.scatter_nd_add(
            tobj, mask, (1.0 - gr) + gr * score_iou - x)
    end_time = datetime.datetime.now()
    elapsed_time = end_time - start_time
    print("gather_nd + scatter_nd Elapsed time: ", elapsed_time.microseconds/1000, "ms")
    return tobj

#方法2
def fun2(tobj,score_iou, t_indices,gr):
    b, a, gj, gi = t_indices  # image, anchor, gridy, gridx
    start_time = datetime.datetime.now()
    with paddle.no_grad():
            tobj[b, a, gj, gi] = (1.0 - gr) + gr * score_iou  # iou ratio
    end_time = datetime.datetime.now()
    elapsed_time = end_time - start_time
    print("set_value Elapsed time: ", elapsed_time.microseconds/1000, "ms")
    return tobj

tobj1 = fun1(tobj, mask, score_iou,gr)
tobj2 = fun2(tobj,score_iou, t_indices,gr)

测试结果：