sdusyj

ContrastiveLearningHAR

Contrastive Learning (SimCLR) for Human Activity Recognition

early-stopping-pytorch

Early stopping for PyTorch

pytorch-image-captioning

Transformer & CNN Image Captioning model in PyTorch.

rezero

Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"

OCR-transformer

OCR seq2seq resnet+transformer

RevTransformerAttentionHAR

Transformer-based deep reverse attention network for multi-sensory human activity recognition published in Engineering Applications of Artificial Intelligence, Elsevier

HAR-Dataset-Preprocess

HAR-Transformer

Transformer for Human Activity Recognition

MCTformer

Code for CVPR 2022 paper "Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation"

Awesome_Human_Activity_Recognition

An up-to-date & curated list of Awesome Human Activity Recognition(Ubiquitous Computing) papers, methods & resources.

replacement-autoencoder

Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis (IoTDI'18)

transformer

Transformer: PyTorch Implementation of "Attention Is All You Need"

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

adapter-bert

byol-pytorch

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

SENet

Squeeze-and-Excitation Networks

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

THAT

Code for AAAI paper "Two-Stream Convolution Augmented Transformer for Human Activity Recognition"

ChatGPT

🔮 ChatGPT Desktop Application (Mac, Windows and Linux)

self-attention-HAR

[ECAI 2020] Tensorflow 2.x Implementation of "Human Activity Recognition from Wearable Sensor Data Using Self-Attention"

Human-activity-recognition

Baseline Classifiers for the Human Activity Recognition with Mobile Sensors Project

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Sensor-Transformer

Transformer Network for Time-Series, Sensor and Wearable Data

Lightweight-Transformer-Models-For-HAR-on-Mobile-Devices

Human Activity Recognition Transformer (HART) is a transformer based architecture that has been specifically adapted for IMU sensing devices. Findings shows that HART uses fewer paremeters, FLOPs and achieves state-of-the-art results.

Activity-recognition-on-MHEALTH

Activity recognition using MHEALTH dataset and CNN or FNN

Human_Activity_Recognition

The MHEALTH (Mobile Health) dataset is devised to benchmark techniques dealing with human behavior analysis based on multimodal body sensing.

Data-Augmentation-For-Wearable-Sensor-Data

A sample code of data augmentation methods for wearable sensor data (time-series data)

CL-HAR

mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.