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

Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)

EZ graph is an easy to use AI solution that allows you to make and train your neural networks without a single line of code.

Migration of Edge-based Distributed Federated Learning

Instance-wise Feature Importance in Time (FIT)

paper list in the area of reinforcenment learning for recommendation systems

Official pytorch implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion"

A DCGAN to generate anime faces using custom mined dataset

Bunch of different tools which helps visualizing and annotating images for semantic/instance segmentation tasks

PyTorch DepthNet Training on Still Box dataset

ViDT: An Efficient and Effective Fully Transformer-based Object Detector

Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".

Fuzzing tool (TFuzz): a fuzzing tool based on program transformation

dualPC.R contains the R code for the main functions.

To build a regression model to predict the concrete compressive strength based on the different features in the training data.

Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai

Code to compute permutation and drop-column importances in Python scikit-learn models

Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"

Official code release for "Learned Spatial Representations for Few-shot Talking-Head Synthesis" ICCV 2021

Stochastic gradient descent with model building

Script utilizando OpenCV e modelo Machine Learning para detectar o uso de máscaras.