Official Python library for the DeepL language translation API.

Shared repository for open-sourced projects from the Google AI Language team.

Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).

Keras implementation of GradCAM.

A PyTorch implementation of D-RISE

A game theoretic approach to explain the output of any machine learning model.

Tools to Design or Visualize Architecture of Neural Network

A collection of infrastructure and tools for research in neural network interpretability.

Python Development Workflow for Humans.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Efficient Image Captioning code in Torch, runs on GPU

A curated list of awesome responsible machine learning resources.

[ICCV 2017] Torch code for Grad-CAM

Applied Deep Learning Course

Riemann-Stieltjes Integrated Gradient-weighted Class Activation Map (RSI-Grad-CAM) - (https://arxiv.org/abs/2205.10900)

Streamlit — A faster way to build and share data apps.

Code and slides of my YouTube series called "Audio Signal Proessing for Machine Learning"

👋 Xplique is a Neural Networks Explainability Toolbox

Visualkeras is a Python package to help visualize Keras (either standalone or included in TensorFlow) neural network architectures. It allows easy styling to fit most needs. This module supports la…

Using temporal convolution to detect Audio Deepfakes

Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…

Groundtruth images of tampering dataset CASIA 2.0

DeepMind's Tacotron-2 Tensorflow implementation

Robust Speech Recognition via Large-Scale Weak Supervision

scikit-learn: machine learning in Python

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Python library and CLI tool to interface with Google Translate's text-to-speech API

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

Contains colab files for making audio and video with deep fakes

This repository contains code for the method proposed in the paper: Two-stream Encoder-Decoder Network for Localizing Image Forgeries