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

Offical code for the paper: "Growing 3D Artefacts and Functional Machines with Neural Cellular Automata" https://arxiv.org/abs/2103.08737

Few-shot Learning of GPT-3

Download from Onlyfans.com.

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

"NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

PyTorch implementation of EfficientNetV2

Deep Learning Models for Causal Inference

Working demo of the Multi-class and Anomaly classification model using the CLIP feature space

Springer Link Download Module for Python

code for `Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation`

Stochastic Extragradient: General Analysis and Improved Rates

PyElecCL - Electron Monte Carlo Second Checks

How to Predict Stock Prices Easily Demo

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021

Medical image analysis framework merging ANTsPy and deep learning

[CVPR 2022 Oral] Versatile Multi-Modal Pre-Training for Human-Centric Perception

Portfolio Optimization and Quantitative Strategic Asset Allocation in Python

Cweqgen - The CW Equation Generator

Kaggle G2Net Gravitational Wave Detection : 2nd place solution

A Bayesian cognition approach for belief updating of correlation judgement through uncertainty visualizations