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

To SMOTE, or not to SMOTE?

SGoLAM - Simultaneous Goal Localization and Mapping

Faune proche - Retrieval of Faune-France data near a google maps location

A developer interface for creating Chat AIs for the Chai app.

TorchX is a library containing standard DSLs for authoring and running PyTorch related components for an E2E production ML pipeline.

Pose estimation with MoveNet Lightning

Implementation of "Semi-supervised Domain Adaptive Structure Learning"

[NeurIPS-2021] Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

PyTorch implementation of the wavelet analysis from Torrence & Compo

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

AI grand challenge 2020 Repo (Speech Recognition Track)

REGTR: End-to-end Point Cloud Correspondences with Transformers

Go from graph data to a secure and interactive visual graph app in 15 minutes. Batteries-included self-hosting of graph data apps with Streamlit, Graphistry, RAPIDS, and more!

Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.

Use .csv files to record, play and evaluate motion capture data.

PyTorch implementation of DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images

Python implementation of cover trees, near-drop-in replacement for scipy.spatial.kdtree

Implementation of SiameseXML (ICML 2021)

Code for the paper "Adapting Monolingual Models: Data can be Scarce when Language Similarity is High"

Tiny Object Detection in Aerial Images.