models/.github/README_TEMPLATE.md

:memo: A README.md template for releasing a paper code implementation to a GitHub repository.

• Template version: 1.0.2020.170
• Please modify sections depending on needs.

Model name, Paper title, or Project Name

:memo: Add a badge for the ArXiv identifier of your paper (arXiv:YYMM.NNNNN)

This repository is the official or unofficial implementation of the following paper.

• Paper title: Paper Title

Description

:memo: Provide description of the model.

• Provide brief information of the algorithms used.
• Provide links for demos, blog posts, etc.

History

:memo: Provide a changelog.

Authors or Maintainers

:memo: Provide maintainer information.

• Full name (@GitHub username)
• Full name (@GitHub username)

Table of Contents

:memo: Provide a table of contents to help readers navigate a lengthy README document.

Requirements

:memo: Provide details of the software required.

• Add a requirements.txt file to the root directory for installing the necessary dependencies.
  • Describe how to install requirements using pip.
• Alternatively, create INSTALL.md.

To install requirements:

pip install -r requirements.txt

Results

:memo: Provide a table with results. (e.g., accuracy, latency)

• Provide links to the pre-trained models (checkpoint, SavedModel files).
  • Publish TensorFlow SavedModel files on TensorFlow Hub (tfhub.dev) if possible.
• Add links to TensorBoard.dev for visualizing metrics.

An example table for image classification results

Image Classification

Model name	Download	Top 1 Accuracy	Top 5 Accuracy
Model name	Checkpoint, SavedModel	xx%	xx%

Dataset

:memo: Provide information of the dataset used.

Training

:memo: Provide training information.

• Provide details for preprocessing, hyperparameters, random seeds, and environment.
• Provide a command line example for training.

Please run this command line for training.

python3 ...

Evaluation

:memo: Provide an evaluation script with details of how to reproduce results.

• Describe data preprocessing / postprocessing steps.
• Provide a command line example for evaluation.

Please run this command line for evaluation.

python3 ...

References

:memo: Provide links to references.

License

:memo: Place your license text in a file named LICENSE in the root of the repository.

• Include information about your license.
• Reference: Adding a license to a repository

This project is licensed under the terms of the Apache License 2.0.

Citation

:memo: Make your repository citable.

• Reference: Making Your Code Citable

If you want to cite this repository in your research paper, please use the following information.