Error with android vim3 after qat+dis 全量化！

[2050airobert]

Hi，    1）Paddle Lite 版本：release/v2.11    2）android vim3 galcore 6.4.3

• 模型信息    1）tinypose128x96 2）output-from_qat+dis.zip ./image_classification_demo ./assets/models/xc/ 1 ./assets/labels/synset_words.txt ./assets/images/tinypose_input.raw "verisilicon_timvx" NULL NULL NULL NULL 出错log 如下 模型A：log0714tinypose.txt 然后更换模型为，结果正常，输出也正常。 模型B: xc.zip

  模型A是经过qat+dis全量化得到的，我去掉了后缀名而已。 请问下，我该如何处理全量化后的结果，才能获得跟模型B一样正常的结果呢？

BR

[paddle-bot[bot]]

您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网文档、常见问题、历史Issue来寻求解答。祝您生活愉快～

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ and Github Issue to get the answer.Have a nice day!

[hong19860320]

从错误上看，应该是某个算子缺少量化信息，一般缺失了 out_threshold 属性

[2050airobert]

so could you help me with this problem of pplite ?

[2050airobert]

so anyone could help?