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

Official Pytorch implementation of the paper: "Locally Shifted Attention With Early Global Integration"

Caffe: a fast open framework for deep learning.

Anderson Acceleration for Deep Learning

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

一个多语言支持、易使用的 OCR 项目。An easy-to-use OCR project with multilingual support.

Source code for Fixed-Point GAN for Cloud Detection

Array Camera Ptychography

Detail-Preserving Transformer for Light Field Image Super-Resolution

Pure python implementations of popular ML algorithms.

[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation

Breast Cancer Classification Model is applied on a different dataset

[CVPR 2021] MiVOS - Scribble to Mask module

A simple implementation of Kalman filter in Multi Object Tracking

Learning Tracking Representations via Dual-Branch Fully Transformer Networks

Convex optimization for fun and profit.

Manifold-Mixup implementation for fastai V2

Visualizer for neural network, deep learning, and machine learning models

OpenIPDM is a MATLAB open-source platform that stands for infrastructures probabilistic deterioration model

A quantum game modeling of pandemic (QHack 2022)

PyTorch and Tensorflow functional model definitions