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

Notebooks, slides and dataset of the CorrelAid Machine Learning Winter School

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

SEJE Pytorch implementation

[CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution

mmfewshot is an open source few shot learning toolbox based on PyTorch

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

a simple, efficient, and intuitive text editor

BlueFog Tutorials

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image

A3C LSTM Atari with Pytorch plus A3G design

The first machine learning framework that encourages learning ML concepts instead of memorizing class functions.

An Artificial Intelligence trying to drive a car by itself on a user created map

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

Dados coletados e programas desenvolvidos no processo de iniciação científica

Pytorch implementation for M^3L

Invertible conditional GANs for image editing

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Distributed Deep learning with Keras & Spark

[ICCV2021] Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving

Code base for the paper "Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation"