Out-of-distribution detection using the pNML regret. NeurIPS2021

Last update: Dec 02, 2022

Overview

OOD Detection

Load conda environment

conda env create -f environment.yml

or install requirements:

while read requirement; do conda install --yes $requirement || pip install $requirement; done < requirements.txt

# Download OOD data
cd bash_scripts
chmod 777 ./download_data.sh
./download_data.sh

# Download pretrained models
chmod 777 ./download_models.sh
./download_models.sh

Download imagenet30

Follow https://github.com/alinlab/CSI

Imagenet30 training set: https://drive.google.com/file/d/1B5c39Fc3haOPzlehzmpTLz6xLtGyKEy4/view

Imagenet30 testing set: https://drive.google.com/file/d/13xzVuQMEhSnBRZr-YaaO08coLU2dxAUq/view

Put and untar under ./data/Imagenet30

.
├── README.md
├── data
│   ├── Imagenet30
│   │   ├── one_class_test
│   │   ├── one_class_test.tar
│   │   ├── one_class_train
│   │   └── one_class_train.tar

Execute methods

Using the pretrained models, score ood detection

cd bash_scripts
chmod 777 ./execute_methods.sh
./execute_methods.sh

Create paper's tables

cd src
python main main_create_tables.py

Out-of-distribution detection using the pNML regret. NeurIPS2021

Related tags

Overview

OOD Detection

Download imagenet30

Execute methods

Owner

Koby Bibas

This is the source code for: Context-aware Entity Typing in Knowledge Graphs.

KITTI-360 Annotation Tool is a framework that developed based on python(cherrypy + jinja2 + sqlite3) as the server end and javascript + WebGL as the front end.

Few-NERD: Not Only a Few-shot NER Dataset

OCR Streamlit App is used to extract text from images using python's easyocr, pytorch and streamlit packages

Unofficial PyTorch implementation of Google AI's VoiceFilter system

Efficient Deep Learning Systems course

The tl;dr on a few notable transformer/language model papers + other papers (alignment, memorization, etc).

One line to host them all. Bootstrap your image search case in minutes.

A model which classifies reviews as positive or negative.

Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

Toward Spatially Unbiased Generative Models (ICCV 2021)

Picasso: a methods for embedding points in 2D in a way that respects distances while fitting a user-specified shape.

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

HyperaPy: An automatic hyperparameter optimization framework ⚡🚀

PINN(s): Physics-Informed Neural Network(s) for von Karman vortex street

Using deep learning model to detect breast cancer.

Code accompanying the paper "How Tight Can PAC-Bayes be in the Small Data Regime?"

GitHub repository for "Improving Video Generation for Multi-functional Applications"

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

A Simplied Framework of GAN Inversion