PascalVOC-AUG pseudo labels

未关闭
#986 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
8/100
Issue 类型
文档
描述清晰度
基本清楚
活跃度
停滞
技术栈
tensorflow

调研方向

This is a question about how the PascalVOC-AUG pseudo labels were produced, not a code change, and no files or entry points are named in the payload. Start by checking the repository's README or model docs for any pseudo-label release, then the paper's self-training section for the teacher model and the argmax-versus-threshold choice. Done would be a maintainer answer, which the thread has not yet received.

由索引模型根据 Issue 内容生成。

描述

Hi thanks for your work.
Is the PascalVOC-AUG pseudo labels used in the paper, "Rethinking Pre-training and Self-training", publicity available?
If not, are there any instructions on how to create those? Couldn't find some details in the paper about which model was used to predict the labels? Does the pseudo label is defined by argmax of the predictions or by a fixed threshold?

主要语言
Jupyter Notebook
星标
5.3k
派生
1.7k
PR 合并指标
30 天内没有已合并 PR

环境准备

这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

tensorflow/tpu 的其他 Issue

查看 tensorflow/tpu 的全部 Issue

相似的 Issue

更多 Machine Learning Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。