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

[NeurIPS-2021] Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

Asynchronous Advantage Actor-Critic in PyTorch

Structured Edge Detection Toolbox

State-Relabeling Adversarial Active Learning

MILK: Machine Learning Toolkit

NCVX (NonConVeX): A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning.

Learning Time-Critical Responses for Interactive Character Control

PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

Justmagic - Use a function as a method with this mystic script, like in Nim

The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

Commonsense Ability Tests

[NeurIPS2021] Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

GuideDog is an AI/ML-based mobile app designed to assist the lives of the visually impaired, 100% voice-controlled

Official repository of the paper "GPR1200: A Benchmark for General-PurposeContent-Based Image Retrieval"

The codes of paper 'Active-LATHE: An Active Learning Algorithm for Boosting the Error exponent for Learning Homogeneous Ising Trees'

Framework to build and train RL algorithms

Classify bird species based on their songs using SIamese Networks and 1D dilated convolutions.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

QQ Browser 2021 AI Algorithm Competition Track 1 1st Place Program

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs