Skip to content

  • 体验新版
    • 正在加载...
  • 登录
  • PaddlePaddle
  • Paddle
  • Issue
  • #21492

P
Paddle
  • 项目概览

PaddlePaddle / Paddle
大约 2 年 前同步成功

通知 2325
Star 20933
Fork 5424
  • 代码
    • 文件
    • 提交
    • 分支
    • Tags
    • 贡献者
    • 分支图
    • Diff
  • Issue 1423
    • 列表
    • 看板
    • 标记
    • 里程碑
  • 合并请求 543
  • Wiki 0
    • Wiki
  • 分析
    • 仓库
    • DevOps
  • 项目成员
  • Pages
P
Paddle
  • 项目概览
    • 项目概览
    • 详情
    • 发布
  • 仓库
    • 仓库
    • 文件
    • 提交
    • 分支
    • 标签
    • 贡献者
    • 分支图
    • 比较
  • Issue 1,423
    • Issue 1,423
    • 列表
    • 看板
    • 标记
    • 里程碑
  • 合并请求 543
    • 合并请求 543
  • Pages
  • 分析
    • 分析
    • 仓库分析
    • DevOps
  • Wiki 0
    • Wiki
  • 成员
    • 成员
  • 收起侧边栏
  • 动态
  • 分支图
  • 创建新Issue
  • 提交
  • Issue看板
已关闭
开放中
Opened 12月 02, 2019 by saxon_zh@saxon_zhGuest

Malformed graph of ernie when ran with benchmark application

Created by: Sand3r-

Current behaviour

The error has been discovered thanks to level 3 logging enabled by GLOG_v environmental variable. GLOG has reported, that:

Some operators use the same variables for reading/writing output. For example, when the fp32_model has been ran, one could observe that scale_op as well transpose2_op accept transpose_4.tmp_0 as their input to the operator (while according to the original graph they do not) Subpart of a GLOG error documenting this:

operator.cc:172 CPUPlace Op(scale), inputs:{X[transpose_4.tmp_0:float[1, 12, 128, 64]({})]}, outputs:{Out[scale_12.tmp_0:float[1, 12, 128, 64]({})]}.
(...several ops later...)
operator.cc:172 CPUPlace Op(transpose2), inputs:{X[transpose_4.tmp_0:float[1, 12, 128, 64]({})]}, outputs:{Out[fc_66.tmp_0:float[1, 128, 12, 64]({})], XShape[transpose_47.tmp_1:[0, 1, 12, 128, 64]({})]}.

As far as I understand that, this is a bug, since variable names should be unique (as long as they are enclosed in the same scope).

To illustrate the problem, please see the following figure depicting a different model (ernie_quant) which suffers from the same problem: image

This is a blocking issue for INT8 Ernie quantization task, since our quantization system associates scales with variable names. And if the variable repeats in several places, we have end up with the same scales where we didn't mean to.

Reproduction

  • based on 8da0cd53 -CPU: including MKLDNN version v.20 -OS Platform Ubuntu 16.04 -Cmake orders -DCMAKE_BUILD_TYPE=RelWithDebInfo -DWITH_GPU=OFF -DON_INFER=ON -DWITH_MKLDNN=ON -DWITH_TESTING=ON -DWITH_PROFILER=ON -DWITH_STYLE_CHECK=OFF -DWITH_INFERENCE_API_TEST=ON -API information To Reproduce
  1. Build paddle
  2. Build benchmark Inference application for ernie https://github.com/PaddlePaddle/benchmark/tree/master/Inference/c%2B%2B/ernie Run any 4-input ernie model.

@luotao1 Could you please assign someone to help solving this issue?

指派人
分配到
无
里程碑
无
分配里程碑
工时统计
无
截止日期
无
标识: paddlepaddle/Paddle#21492
渝ICP备2023009037号

京公网安备11010502055752号

网络110报警服务 Powered by GitLab CE v13.7
开源知识
Git 入门 Pro Git 电子书 在线学 Git
Markdown 基础入门 IT 技术知识开源图谱
帮助
使用手册 反馈建议 博客
《GitCode 隐私声明》 《GitCode 服务条款》 关于GitCode
Powered by GitLab CE v13.7