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

Continuous Diffusion Graph Neural Network

A PyTorch Implementation of SphereFace.

Le dataset des images du projet d'IA de 2021

Implementation of [Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes].

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption

Udacity's CS101: Intro to Computer Science - Building a Search Engine

Winning solution of the Indoor Location & Navigation Kaggle competition

Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding

A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech

End-to-end beat and downbeat tracking in the time domain.

This is an official repository of CLGo: Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints

My personal Home Assistant configuration.

python library for invisible image watermark (blind image watermark)

Evaluating Cross-lingual Sentence Representations

Transformer model implemented with Pytorch

A parallel framework for population-based multi-agent reinforcement learning.

Implementation of the Swin Transformer in PyTorch.