tensorflow API: tf.unsorted_segment_sum

unsorted_segment_sum(    data,    segment_ids,    num_segments,    name=None)

Computes a tensor such that (output[i] = sum_{j…} data[j…] where the sum is over tuples j… such that segment_ids[j…] == i.
计算一个tensor的输出output[i]等于咱们给的segment_ids[j….]里面所有填i的位置对应到data[j….]的和，意思就是我想对data的j,k,l位置求和放在输出a[0]上，那segment_ids再[j,k,l]上都是0
Unlike SegmentSum, segment_ids need not be sorted and need not cover all values in the full range of valid values.
给出的segment_ids不用像tf.segment_sum一样有序，对data的求和位置可以跨越
If the sum is empty for a given segment ID i, output[i] = 0.
去和为空，那么output[i]为0
num_segments should equal the number of distinct segment IDs
num_segments等于segment_ids里面的划分数，就是分解出来的结果数组的大小。

例子：

a = np.arange(1,10).reshape(3,3)print(a)print('----------')print((sess.run(tf.unsorted_segment_max(data=a,segment_ids=[0,1,0],num_segments=2))))

输出:

Out[20]:array([[1, 2, 3],       [4, 5, 6],       [7, 8, 9]])----------[[7 8 9] [4 5 6]]