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

Pytorch implementation of PTNet for high-resolution and longitudinal infant MRI synthesis

Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer

Object Depth via Motion and Detection Dataset

Open-sourcing the Slates Dataset for recommender systems research

Improving Object Detection by Label Assignment Distillation

CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

A data-driven maritime port simulator

TorchFlare is a simple, beginner-friendly, and easy-to-use PyTorch Framework train your models effortlessly.

This is the pytorch implementation for the paper: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation, which is accepted to ICCV2021.

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces (ICCV 2021)

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs

Block-wisely Supervised Neural Architecture Search with Knowledge Distillation (CVPR 2020)

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Pytorch implementation for "Implicit Semantic Response Alignment for Partial Domain Adaptation"

Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

A package related to building quasi-fibration symmetries

Code for the paper "Improved Techniques for Training GANs"

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Powerful unsupervised domain adaptation method for dense retrieval.

Code for technical report "An Improved Baseline for Sentence-level Relation Extraction".