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

Code of paper: "DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks"

Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Implementation of the paper Scalable Intervention Target Estimation in Linear Models (NeurIPS 2021), and the code to generate simulation results.

Simple torch.nn.module implementation of Alias-Free-GAN style filter and resample

a general-purpose Transformer based vision backbone

[ICCV 2021] Target Adaptive Context Aggregation for Video Scene Graph Generation

GazeScroller - Using Facial Movements to perform Hands-free Gesture on the system

Supplemental learning materials for "Fourier Feature Networks and Neural Volume Rendering"

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Official PyTorch implementation of Learning Intra-Batch Connections for Deep Metric Learning (ICML 2021) published at International Conference on Machine Learning

Source codes of CenterTrack++ in 2021 ICME Workshop on Big Surveillance Data Processing and Analysis

Small-bets - Ergodic Experiment With Python

The official repository for paper ''Domain Generalization for Vision-based Driving Trajectory Generation'' submitted to ICRA 2022

[SDM 2022] Towards Similarity-Aware Time-Series Classification

Show-attend-and-tell - TensorFlow Implementation of "Show, Attend and Tell"

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects (CVPR 2021)

TransferNet: Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Official PyTorch Implementation of Unsupervised Learning of Scene Flow Estimation Fusing with Local Rigidity