Jigsaw Rate Severity of Toxic Comments

Last update: Nov 30, 2022

Overview

Jigsaw-Rate-Severity-of-Toxic-Comments

Link to method description: https://www.kaggle.com/c/jigsaw-toxic-severity-rating/discussion/306274

Software Requirement: torch==1.10 transformers==4.15.0 geneticalgorithm

Hardware Requirement: 3 x RTX A6000

Please download and extract the competition data and all external data into the corresponding locations of the input folder. this competition data: https://www.kaggle.com/c/jigsaw-toxic-severity-rating/data jigsaw18 data: https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge/data jigsaw19 data: https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification/data ruddit data: https://www.kaggle.com/rajkumarl/ruddit-jigsaw-dataset

For training, please go to jigsaw18/, jigsaw19, ruddit/ and sh run.sh

Owner

Guanshuo Xu

GitHub Repository

Training DiffWave using variational method from Variational Diffusion Models.

Variational DiffWave Training DiffWave using variational method from Variational Diffusion Models. Quick Start python train_distributed.py discrete_10

26 Dec 13, 2022

Implementation of average- and worst-case robust flatness measures for adversarial training.

Relating Adversarially Robust Generalization to Flat Minima This repository contains code corresponding to the MLSys'21 paper: D. Stutz, M. Hein, B. S

13 Nov 27, 2022

This is an official implementation for "Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation".

Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation This repo is the official implementation of Exploiting Temporal Con

241 Jan 07, 2023

When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset of 53,000+ Legal Holdings

When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset of 53,000+ Legal Holdings This is the repository for t

39 Jan 07, 2023

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

Deep Illuminator Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide

52 Nov 29, 2022

Jigsaw Rate Severity of Toxic Comments

Related tags

Overview

Jigsaw-Rate-Severity-of-Toxic-Comments

Owner

Guanshuo Xu

Training DiffWave using variational method from Variational Diffusion Models.

Implementation of average- and worst-case robust flatness measures for adversarial training.

This is an official implementation for "Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation".

When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset of 53,000+ Legal Holdings

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

GLANet - The code for Global and Local Alignment Networks for Unpaired Image-to-Image Translation arxiv

DiAne is a smart fuzzer for IoT devices

Self-Supervised CNN-GCN Autoencoder

This repository is for DSA and CP scripts for reference.

Anomaly detection related books, papers, videos, and toolboxes

It helps user to learn Pick-up lines and share if he has a better one

Cards Against Humanity AI

Web-interface + rest API for classification and regression (https://jeff1evesque.github.io/machine-learning.docs)

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Language Models Can See: Plugging Visual Controls in Text Generation

All course materials for the Zero to Mastery Machine Learning and Data Science course.

EM-POSE 3D Human Pose Estimation from Sparse Electromagnetic Trackers.

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition

Semantic Segmentation of images using PixelLib with help of Pascalvoc dataset trained with Deeplabv3+ framework.