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

The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"

a practicable framework used in Deep Learning. So far UDL only provide DCFNet implementation for the ICCV paper (Dynamic Cross Feature Fusion for Remote Sensing Pansharpening)

Python script that analyses the given datasets and comes up with the best polynomial regression representation with the smallest polynomial degree possible

[ICLR2021oral] Rethinking Architecture Selection in Differentiable NAS

Causal Imitative Model for Autonomous Driving

Code for visualizing the loss landscape of neural nets

Code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search.

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

Mesh TensorFlow: Model Parallelism Made Easier

PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

The Pytorch implementation for "Video-Text Pre-training with Learned Regions"

Simple and ready-to-use tutorials for TensorFlow

Sequence modeling benchmarks and temporal convolutional networks

Implementation of StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation in PyTorch

Tensorflow 2.x implementation of Vision-Transformer model

天勤量化开发包, 期货量化, 实时行情/历史数据/实盘交易

PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility

Automatic caption evaluation metric based on typicality analysis.

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

Fortuitous Forgetting in Connectionist Networks