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 needed to reproduce the examples found in "The Temporal Robustness of Stochastic Signals"

Official respository for "Modeling Defocus-Disparity in Dual-Pixel Sensors", ICCP 2020

Code for "OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021)"

PolyGlot, a fuzzing framework for language processors

Public Code for NIPS submission SimiGrad: Fine-Grained Adaptive Batching for Large ScaleTraining using Gradient Similarity Measurement

Python library for analysis of time series data including dimensionality reduction, clustering, and Markov model estimation

[TOG 2021] PyTorch implementation for the paper: SofGAN: A Portrait Image Generator with Dynamic Styling.

Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.

TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning

This repository contains the scripts for downloading and validating scripts for the documents

Recursive Bayesian Networks

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

A unet implementation for Image semantic segmentation

Your interactive network visualizing dashboard

Turi Create simplifies the development of custom machine learning models.

A 10000+ hours dataset for Chinese speech recognition

Bayes-Newton—A Gaussian process library in JAX, with a unifying view of approximate Bayesian inference as variants of Newton's algorithm.

Decorator for PyMC3

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"