未验证 提交 bc99a0f0 编写于 作者: C cc 提交者: GitHub

[fix bug] add weight quant for combined model after optimized (#2929)

* add weight quant for combined model after optimized, test=develop
上级 5acf1afa
......@@ -25,6 +25,8 @@ void LightPredictor::Build(const std::string& lite_model_file,
} else {
LoadModelNaiveFromFile(lite_model_file, scope_.get(), &cpp_program_desc_);
}
DequantizeWeight();
BuildRuntimeProgram(cpp_program_desc_);
PrepareFeedFetch();
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册