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 implementation of Deep Convolutional Dictionary Learning for Image Denoising.

A parallel framework for population-based multi-agent reinforcement learning.

Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21.

Notebooks em Python para Métodos Eletromagnéticos

Official pytorch code for SSC-GAN: Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation(ICCV 2021)

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

Open Source Light Field Toolbox for Super-Resolution

Long Expressive Memory (LEM)

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.

Applying curriculum to meta-learning for few shot classification

An unreferenced image captioning metric (ACL-21)

R-Drop: Regularized Dropout for Neural Networks

Official implementation of the paper "Lightweight Deep CNN for Natural Image Matting via Similarity Preserving Knowledge Distillation"

MoveNet Single Pose on OpenVINO

SciPy fixes and extensions

PyTorch implementation of "Learn to Dance with AIST++: Music Conditioned 3D Dance Generation."

A list of Machine Learning Art Colabs

Answering Open-Domain Questions of Varying Reasoning Steps from Text

TSIT: A Simple and Versatile Framework for Image-to-Image Translation