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

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

It helps user to learn Pick-up lines and share if he has a better one

Python port of R's Comprehensive Dynamic Time Warp algorithm package

Identifying Stroke Indicators Using Rough Sets

Mixed Neural Likelihood Estimation for models of decision-making

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

Collection of generative models in Tensorflow

Deep Learning Specialization by Andrew Ng, deeplearning.ai.

An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax

DAN: Unfolding the Alternating Optimization for Blind Super Resolution

MLP-Numpy - A simple modular implementation of Multi Layer Perceptron in pure Numpy.

Imaginaire - NVIDIA's Deep Imagination Team's PyTorch Library

Official code for paper "Optimization for Oriented Object Detection via Representation Invariance Loss".

Extracting and filtering paraphrases by bridging natural language inference and paraphrasing

Hypernetwork-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels

Official Tensorflow implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"

Implementation of a Transformer using ReLA (Rectified Linear Attention)