-

-

Collection of Functions useful for testing various packages in the Lux Ecosystem

This is a package for automated landmarking of images and volumes

An adapter package that implements Lighthouse's framework interface for Flux

-

Radial Basis Function Surrogates

-

Plots.jl recipes for the GeoStats.jl framework

[WIP] Wrapper package for simulation and bayesian inference of behavioral models

-

Plotting Radiotherapy Beam-Limiting Devices using Plots.jl

Package for generating masks and line lists for use in stellar radial velocity measurements

Gaussian simulation solvers for the GeoStats.jl framework

Draw simple Flux neural networks using TikZ

Additional layers and functions for Flux.jl.

Valid Discrete-Time Methods for Relaxing pODEs

SMLMBoxer.jl is a Julia package that provides a fast and efficient method for detecting particles or blobs in a multidimensional image stack and cutting out sub-regions around local maxima.

A small package for differentiable discontinuities in Julia.

A Julia package for plotting sequential sampling models

Automatically Differentiate the backward Euler method

-

Bosons/Fermions Superfluid problem with morden tools.

Generalized linear models for cell-cell communication

-

Small package to extract coordinates of countries border

Makie visualization module for TopOpt.jl

Julia implementation of our multi-operation blank localization method

Transliterate Beta Code Greek to Unicode Greek

A package for discretizing trajectory data into a transition probability matrix using Ulam's method.

Deep Unfolded Convolutional Dictionary Learning for motif discovery.

Advanced exports management for AutomationLabs.jl

Make recurrent layers in Flux much faster

DeepForest Impletmentation in Julia

Julia implementation of AlphaFold 2's Invariant Point Attention

Parameter estimation under uncertainty.

Julia code of CycleGAN based on pytorch implementation

Multi-start optimization in Nonconvex.jl

Jet transform operators that depend on FFTW.jl, and Wavelets.jl. Part of the COFII framework.

Deep-learning sliding window attention with circular boundary conditions. No tokenization, no patchify-ing.