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

Code & Data for the Paper "Time Masking for Temporal Language Models", WSDM 2022

Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

Paaster is a secure by default end-to-end encrypted pastebin built with the objective of simplicity.

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

OMLT: Optimization and Machine Learning Toolkit

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.

This is the code of using DQN to play Sekiro .

PyTorch implementation of the ideas presented in the paper Interaction Grounded Learning (IGL)

LightLog is an open source deep learning based lightweight log analysis tool for log anomaly detection.

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies

Spatially-Adaptive Pixelwise Networks for Fast Image Translation, CVPR 2021

ObjectDetNet is an easy, flexible, open-source object detection framework

PyTorch implementation of MulMON

Code for the paper Learning the Predictability of the Future

Romanian Automatic Speech Recognition from the ROBIN project

Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set

PIXIE: Collaborative Regression of Expressive Bodies

"Exploring Vision Transformers for Fine-grained Classification" at CVPRW FGVC8