Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Image augmentation for machine learning experiments.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

End-to-End Object Detection with Transformers

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Reformer, the efficient Transformer, in Pytorch

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

Simulation of spiking neural networks (SNNs) using PyTorch.

Deep and online learning with spiking neural networks in Python

proof of concept for a transformer-based time series prediction model

Generative Adversarial Transformers

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

Deep Metric Learning

EQTransformer, a python package for earthquake signal detection and phase picking using AI.

Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration

这是一个DETR-pytorch的仓库，可以训练自己的数据集

Offical implementation of "Attention Spiking Neural Networks" (IEEE T-PAMI2023)

A surface electromyographic (sEMG) touch typing dataset with baselines. https://arxiv.org/abs/2410.20081.

Improved sEMG-based gesture recognition

一个deformable-detr的中文注释版本，供大家参考学习（A Chinese annotated version of deformable-detr）

PyTorch and Loihi implementation of the Spiking Neural Network for decoding EEG on Neuromorphic Hardware

A powerful toolbox for the analysis of HD-EMG recordings

Package for decomposing EMG signals into motor unit firings, as used in Formento et al 2021.

multilabel categorical crossentropy

Source code for multiple parameter modelling of synthetic electromyography data.

A deep latent generative model for learning biosystems

Decomposition of Neurophysiological Time Series Signals with a Particle Swarm Optimised Independence Estimator

Second-order information bottleneck for sEMG pattern recognition tasks

The neuromuscular model notebook is an interactive tool for studying the underlying mechanisms of electromyogram (EMG) and force generation. The model, which was based on previous studies (see refe…