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

Gems & Holiday Package Prediction

Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"

DI-HPC is an acceleration operator component for general algorithm modules in reinforcement learning algorithms

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

MVSDF - Learning Signed Distance Field for Multi-view Surface Reconstruction

Exemplo de implementação do padrão circuit breaker em python

Projecting interval uncertainty through the discrete Fourier transform

[Link]deep_portfolo - Use Reforcemet earg ad Supervsed learg to Optmze portfolo allocato []

(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

Tensorflow Repo for "DeepGCNs: Can GCNs Go as Deep as CNNs?"

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

An implementation of the 1. Parallel, 2. Streaming, 3. Randomized SVD using MPI4Py

AFLFast (extends AFL with Power Schedules)

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning, NeurIPS 2021 (Spotlight)

Rename Images with Auto Generated Neural Image Captions

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

In this work, we will implement some basic but important algorithm of machine learning step by step.

Classification of EEG data using Deep Learning

An end-to-end PyTorch framework for image and video classification

Character Controllers using Motion VAEs