Syne Tune is a Python library that provides state-of-the-art algorithms for hyperparameter optimization (HPO) with platform flexibility and minimal dependencies. It supports 20+ HPO methods, …
Keywords: hyper-parameter optimization, hyper-parameter tuning, neural architecture search, machine leaning, Bayesian optimization, Python
The official implementation of TabNet neural network algorithm for tabular data.
Keywords: neural networks, tabular data, attention, interpretability, Python, PyTorch
Implementation of TabR retrieval-augmented tabular deep learning algorithm.
Keywords: deep learning, tabular data, PyTorch, Python
TAGNet is an efficient Knowledge Graph Completion (KGC) method that efficiently propagates information by aggregating paths within a fixed window, reducing the number of propagated …
Keywords: knowledge graph, graph machine learning, machine learning, Python, PyTorch
TensorFlow GNN is a Google library to build Graph Neural Networks on the TensorFlow platform.
Keywords: graph neural networks, GNN, machine learning, geometric deep learning, TensorFlow, Python
The TensorFlow Model Garden is a repository with a number of different implementations of state-of-the-art (SOTA) models and modeling solutions for TensorFlow users. We aim …
Keywords: Tensorflow, models, model garder, examples
We present Temporal Interlacing Network(TIN), a simple interlacing operator. TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with …
Keywords: TIN, Temporal Interlacing Network, PyTorch, computer vision, video analysis
TorchDrug is a machine learning platform designed for drug discovery, covering techniques from graph machine learning (graph neural networks, geometric deep learning & knowledge graphs), …
Keywords: graph representation learning, drug discovery, machine learning, Python, PyTorch
TorchGeo is a PyTorch domain library, similar to torchvision, providing datasets, samplers, transforms, and pre-trained models specific to geospatial data. The goal of this library …
Keywords: geospatial, remote sensing, earth observation, benchmark datasets, deep learning, PyTorch, Python
torchlayers is a library based on PyTorch providing automatic shape and dimensionality inference of torch.nn layers + additional building blocks featured in current SOTA architectures …
Keywords: PyTorch, layers, torchlayer, shape inference