Neural Python Packages

neuralprophet

NeuralProphet: A simple forecasting package

neuralpiano

Hi-Fi neural MIDI piano synthesizer and MIDI renderer

torchsample

Lightweight pytorch utilities for neural network featuremap sampling.

neuralnet-visualize

Generate a neural network architecture Image

tempocnn

Framework for estimating temporal properties of music tracks.

atiny

Atiny is a gradient based PyTorch optimizer. Atiny uses half of Adam’s memory to achieve results that are not inferior to Adam.

okrolearn

A machine learning library created by Okerew, which is supposed to be a raw implementation of combining pytorch with scikit-learn

fwu

FWU is a series of PyTorch-based neural network units.It has higher information utilization, prevents neuronal necrosis, and eliminates the need to add additionall activation functions.

neural-tools

Tools made for usage alongside artistic style transfer projects

titans-memory

PyTorch implementation of Titans: Learning to Memorize at Test Time (Behrouz, Zhong & Mirrokni, 2024)

haloblocks

Python library designed to make model experimentation seamless and fast. The goal was simple: treat every component (attention heads, MLPs, MoE layers) as a plug-and-play block so you can focus on the architecture, not the boilerplate.

orientloss

orientLoss is a classification loss function @pytorch. It less prone to overfitting compared to crossEntropy. Compatible with random vector/embeddings with direction-indicating categories、probabilistic、oneHot as target.

promptscan

Detect prompt injections

glassinit

glassInit is a way to initialize the parameters of a neural network layer @PyTorch. It is suitable for shortcut connections where tensor sizes need to be adjusted. The flow of information between forward and backward propagation is maximized while adjusting the tensor size.

deepevolution

A genetic algorithm to evolve tensorflow keras neural networks.

inr-collection

A collection of conditional \ modulatable implicit neural representation implementations and basic building blocks in PyTorch.

jax-dips

JAX-DIPS is a differentiable interfacial PDE solver.

neurokernel

Neurokernel Project

fftloss

The fftLoss @PyTorch is a frequency domain loss function that prevents the problem of weak frequency components being suppressed by strong frequency components when using a regular loss function.

ttscube

Text-to-speech synthesis engine, based on end-to-end GAN training. Features: multilanguage, multispeaker, realtime CPU synthesis