https://github.com/google-research/deep_representation_one_class

https://github.com/google-research/deep_representation_one_class

Last synced: 3 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/google-research/deep_representation_one_class
• Owner: google-research
• License: apache-2.0
• Created: 2021-03-17T15:38:14.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2024-05-03T20:05:22.000Z (6 months ago)
• Last Synced: 2024-10-30T06:33:53.089Z (15 days ago)
• Language: Python
• Size: 43.9 KB
• Stars: 156
• Watchers: 7
• Forks: 27
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Deep Representation One-class Classification (DROC).

**This is not an officially supported Google product.**

Tensorflow 2 implementation of the paper: 

[Learning and Evaluating Representations for Deep One-class Classification](https://openreview.net/forum?id=HCSgyPUfeDj) 

published at [ICLR 2021](https://iclr.cc/) as a conference paper

by Kihyuk Sohn, Chun-Liang Li, Jinsung Yoon, Minho Jin, and Tomas Pfister.

This directory contains a two-stage framework for deep one-class classification

example, which includes the self-supervised deep representation learning from

one-class data, and a classifier using generative or discriminative models.

## Install

The `requirements.txt` includes all the dependencies for this project, and an

example of install and run the project is given in run.sh.

```bash

$sh deep_representation_one_class/run.sh

```

## Download datasets

`script/prepare_data.sh` includes an instruction how to prepare data for

CatVsDog and CelebA datasets. For CatVsDog dataset, the data needs to be

downloaded manually. Please uncomment line 2 to set `DATA_DIR` to download

datasets before starting it.

## Run

The options for the experiments are specified thru the command line arguments.

The detailed explanation can be found in `train_and_eval_loop.py`. Scripts for

running experiments can be found

-   Rotation prediction: `script/run_rotation.sh`

-   Contrastive learning: `script/run_contrastive.sh`

-   Contrastive learning with distribution augmentation:

    `script/run_contrastive_da.sh`

## Evaluation

After running `train_and_eval_loop.py`, the evaluation results can be found in

`$MODEL_DIR/stats/summary.json`, where `MODEL_DIR` is specified as model_dir of

`train_and_eval_loop.py`.

## Contacts

[email protected], [email protected], [email protected],

[email protected], [email protected]