tensorflow / tensorflow/models

Produce CIFAR-100 results in the paper

Open
#9,485 0 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Nov 20, 2020.

models:research:odapi type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

Hello,

I am just wondering your steps to produce CIFAR-100 results;

  1. Which policies did you use to produce CIFAR-100 results? While the one in the paper contains 25 policies, there are over 90 policies in this repository.

  2. Did you use the same MEAN and STD for CIFAR-10 and CIFAR-100?

  3. What box size did you use to apply CutOut to CIFAR-100?

Thank you in advance

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.