PyTorch implementation 3D U-Net and its variants.
The code allows for training the U-Net for both: semantic segmentation (binary and multi-class) and regression problems (e.g. …
Keywords: Unet, U-net, 3D U-net, semantic segmentation, computer vision, PyTorch, de-noising, deep learning, neural networks
Reference implementation for the paper Adversarial Latent Autoencoders by S. Pidhorskyi, D. A. Adjeroh, and G. Doretto, CVPR 2020.
Keywords: ALAE, StyleALAE, adversarial latent autoencoders, computer vision, image processing, deep learning, autoencoder, unsupervised learning
A general toolbox for adversarial robustness in machine learning. Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that …
Keywords: adversarial robustness, adversarial attacks, machine learning, security, poisoning attacks, trusted AI, Python, PyTorch, TensorFlow, MXNet
The open source implementation of DeepMind's AlphaFold v2 award winning protein folding algorithm.
Keywords: protein folding, machine learning, neural networks, deep learning, CASP14, structure prediction, DeepMind, JAX, TensorFlow
This is the Open source of the paper "AnimeGAN: a novel lightweight GAN for photo animation", which uses the GAN framwork to transform real-world photos …
Keywords: AnimeGAN, Tensorflow, generative adversarial networks, deep learning, computer vision, anime, photo animation
The reference implementation for the ANYCSP algorithm that learns search heuristics for SAT problems using graph neural networks (GNNs).
Keywords: constraint satisfaction problem, CSP, search heuristics, graph neural networks, GNN, machine learning, Python, PyTorch
Asteroid is a Pytorch-based audio source separation toolkit that enables fast experimentation on common datasets. It comes with a source code that supports a large …
Keywords: Asteroid, Pytorch, audio source separation, toolkit, audio, sound processing, ConvTasnet, Tasnet, Deep clustering, DualPathRNN, Chimera++, Wavesplit
The official implementation of a method for multiple instance learning using deep neural networks and attention mechanism.
Keywords: multiple instance learning, deep learning, attention, PyTorch, weak classification
The reference implementation for the attri2vec algorithm.
Keywords: Attri2vec, representation learning, graph machine learning, node classification, link prediction
AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations. Each modality’s augmentations are contained …
Keywords: data augmentation, machine learning, Python, PyTorch