MLU270 V1.7.0开发包  框架：Tensorflow

模型输入：1*1000*22 

模型输出：1*4

生成离线模型时日志显示：

W tensorflow/stream_executor/mlu/mlu_api/fusion_op/fusion_op.cc:215][26383] Only one offline model is supported, but now there are multiple fusion segments. So only the offline model generated by the last fusion segment is saved.

offline_model.cambricon_twins文件里信息：Shape(dim): 1 256

This is the Twins File of "offline_model.cambricon".
Function number: 1
---------------kernel graph--------------------

Function #0 {
Kernel num:1
Cache mode:0
Name: subnet0
Input number: 1
    Input #0.
        Mask: 338036233
        Shape(dim): 1 256
        Name:
        Id: 216
        Data type: CNRT_FLOAT32        Dim Order: CNRT_NHWC
        Quantize position: 1886413614
        Quantize scale: -0.000000
Output number: 1
    Output #0.
        Mask: 338036233
        Shape(dim): 1 4
        Name:
        Id: 223
        Data type: CNRT_FLOAT32        Dim Order: CNRT_NHWC
        Quantize position: 32700

问题：

Shape(dim): 1 256为什么是1*256？ 应该是1*1000*22才对；

请问这种情况应该如何处理？