STAR

Official implementation of Sparse Transformer-based Action Recognition

Dataset

download NTU RGB+D 60 action recognition of 2D/3D skeleton from http://rose1.ntu.edu.sg/datasets/actionRecognition.asp

or use google drive

NTU60 NTU120

uzip data as the following file structure: $(project_folder)/raw/.\*skeleton or $(project_folder)/dataset/raw/.\*skeleton (create "raw" folder under $(project_folder) or $(project_folder)/dataset then put raw skeleton files under "raw" folder)

run the code below to generate dataset:

python datagen.py

Training

git fetch and checkout to "distributed" branch

python train_dist.py -#distributed training

Configuration

parser.set_defaults(gpu=True,
                    batch_size=128,
                    dataset_name='NTU',
                    dataset_root=osp.join(os.getcwd()),  # or dataset_root=osp.join(os.getcwd(), 'dataset')
                    load_model=False,
                    in_channels=9,
                    num_enc_layers=5,
                    num_conv_layers=2,
                    weight_decay=4e-5,
                    drop_rate=[0.4, 0.4, 0.4, 0.4],  # linear_attention, sparse_attention, add_norm, ffn
                    hid_channels=64,
                    out_channels=64,
                    heads=8,
                    data_parallel=False,
                    cross_k=5,
                    mlp_head_hidden=128)

parser.set_defaults(gpu=True,
                    batch_size=128,
                    dataset_name='NTU',
                    dataset_root=osp.join(os.getcwd()),
                    load_model=False,
                    in_channels=9,
                    num_enc_layers=5,
                    num_conv_layers=2,
                    weight_decay=4e-5,
                    drop_rate=[0.4, 0.4, 0.4, 0.4],  # linear_attention, sparse_attention, add_norm, ffn
                    hid_channels=128,
                    out_channels=128,
                    heads=8,
                    data_parallel=False,
                    cross_k=5,
                    mlp_head_hidden=128)

Official implementation of Sparse Transformer-based Action Recognition

Related tags

Overview

STAR

Dataset

Training

Configuration

Owner

Chonghan_Lee

Facial detection, landmark tracking and expression transfer library for Windows, Linux and Mac

4th place solution to datafactory challenge by Intermarché.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Subnet Replacement Attack: Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

Official code for "Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer. ICCV2021".

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

PyTorch DepthNet Training on Still Box dataset

League of Legends Reinforcement Learning Environment (LoLRLE) multiple training scenarios using PPO.

A small library for doing fluid simulation with neural networks.

Determined: Deep Learning Training Platform

Angular & Electron desktop UI framework. Angular components for native looking and behaving macOS desktop UI (Electron/Web)

Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder

SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022

Python TFLite scripts for detecting objects of any class in an image without knowing their label.

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

Point Cloud Denoising input segmentation output raw point-cloud valid/clear fog rain de-noised Abstract Lidar sensors are frequently used in environme

PaddleBoBo是基于PaddlePaddle和PaddleSpeech、PaddleGAN等开发套件的虚拟主播快速生成项目

Complete system for facial identity system. Include one-shot model, database operation, features visualization, monitoring

Source code for Task-Aware Variational Adversarial Active Learning

Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.