Neural Python Packages

neuralprophet

NeuralProphet: A simple forecasting package

neuralpiano

[WIP] Hi-Fi neural MIDI piano synthesizer and MIDI renderer

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 in python by Okerew

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.

neuralnet-visualize

Give architecture get the image

ttscube

End-2-end speech synthesis with recurrent neural networks

neural-tools

Tools made for usage alongside artistic style transfer projects

kerze

A pure-Python, zero-dependency tensor and autograd library, a mini NumPy + PyTorch built from scratch.

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.

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.

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.

neurokernel

Neurokernel Project

inr-collection

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

titans-memory

Titans in PyTorch: Infinite Context models that learn to remember. Faster than Transformers, smarter than RNNs, and fully HuggingFace compatible.

promptscan

Detect prompt injections

jax-dips

JAX-DIPS is a differentiable interfacial PDE solver.

torchsample

Lightweight pytorch utilities for neural network featuremap sampling.

deepevolution

Deepevolution is a PIP package for evolving tensorflow keras models with a genetic algorithm towards fitting a fitness function.

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.