ByteTrack(Multi-Object Tracking by Associating Every Detection Box)のPythonでのONNX推論サンプル

Overview

ByteTrack-ONNX-Sample

ByteTrack(Multi-Object Tracking by Associating Every Detection Box)のPythonでのONNX推論サンプルです。
ONNXに変換したモデルも同梱しています。
変換自体を試したい方はByteTrack_Convert2ONNX.ipynbを使用ください。
ByteTrack_Convert2ONNX.ipynbはColaboratory上での実行を想定しています。
書き動画はWindowsでの実行例です。

sample_.mp4

Requirement

opencv-python 4.5.3.56 or later
onnx 1.9.0 or later
onnxruntime-gpu 1.9.0 or later
Cython 0.29.24 or later
torch 1.8.1 or later
torchvision 0.9.1 or later
pycocotools 2.0.2 or later
scipy 1.6.3 or later
loguru 0.5.3 or later
thop 0.0.31.post2005241907 or later
lap 0.4.0 or later
cython_bbox 0.1.3 or later

※onnxruntime-gpuはonnxruntimeでも動作しますが、推論時間がかかるためGPUを推奨します
※Windowsでcython_bbox のインストールが失敗する場合は、GitHubからのインストールをお試しください(2021/11/19時点)
pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox

Demo

デモの実行方法は以下です。

動画:動画に対しByteTrackで追跡した結果を動画出力します

python demo_video_onnx.py
実行時オプション
  • --use_debug_window
    動画書き込み時に書き込みフレームをGUI表示するか否か
    デフォルト:指定なし
  • --model
    ByteTrackのONNXモデル格納パス
    デフォルト:byte_tracker/model/bytetrack_s.onnx
  • --video
    入力動画の格納パス
    デフォルト:sample.mp4
  • --output_dir
    動画出力パス
    デフォルト:output
  • --score_th
    人検出のスコア閾値
    デフォルト:0.1
  • --score_th
    人検出のNMS閾値
    デフォルト:0.7
  • --input_shape
    推論時入力サイズ
    デフォルト:608,1088
  • --with_p6
    YOLOXモデルのFPN/PANでp6を含むか否か
    デフォルト:指定なし
  • --track_thresh
    追跡時のスコア閾値
    デフォルト:0.5
  • --track_buffer
    見失い時に何フレームの間、追跡対象を保持するか
    デフォルト:30
  • --match_thresh
    追跡時のマッチングスコア閾値
    デフォルト:0.8
  • --min-box-area
    最小のバウンディングボックスのサイズ閾値
    デフォルト:10
  • --mot20
    MOT20を使用しているか否か
    デフォルト:指定なし

Webカメラ:Webカメラ画像に対しByteTrackで追跡した結果をGUI表示します

python demo_webcam_onnx.py
実行時オプション
  • --model
    ByteTrackのONNXモデル格納パス
    デフォルト:byte_tracker/model/bytetrack_s.onnx
  • --device
    カメラデバイス番号の指定
    デフォルト:0
  • --width
    カメラキャプチャ時の横幅
    デフォルト:960
  • --height
    カメラキャプチャ時の縦幅
    デフォルト:540
  • --score_th
    人検出のスコア閾値
    デフォルト:0.1
  • --score_th
    人検出のNMS閾値
    デフォルト:0.7
  • --input_shape
    推論時入力サイズ
    デフォルト:608,1088
  • --with_p6
    YOLOXモデルのFPN/PANでp6を含むか否か
    デフォルト:指定なし
  • --track_thresh
    追跡時のスコア閾値
    デフォルト:0.5
  • --track_buffer
    見失い時に何フレームの間、追跡対象を保持するか
    デフォルト:30
  • --match_thresh
    追跡時のマッチングスコア閾値
    デフォルト:0.8
  • --min-box-area
    最小のバウンディングボックスのサイズ閾値
    デフォルト:10
  • --mot20
    MOT20を使用しているか否か
    デフォルト:指定なし

Reference

Author

高橋かずひと(https://twitter.com/KzhtTkhs)

License

ByteTrack-ONNX-Sample is under MIT License.

License(Movie)

サンプル動画はNHKクリエイティブ・ライブラリーイギリス ウースターのエルガー像を使用しています。

Owner
KazuhitoTakahashi
KazuhitoTakahashi
an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

This work has now been superseded by: https://github.com/sniklaus/revisiting-sepconv sepconv-slomo This is a reference implementation of Video Frame I

Simon Niklaus 985 Jan 08, 2023
Official Pytorch implementation of "DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network" (CVPR'21)

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network Pytorch implementation for our DivCo. We propose a simple ye

64 Nov 22, 2022
Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.

Conceptual 12M We introduce the Conceptual 12M (CC12M), a dataset with ~12 million image-text pairs meant to be used for vision-and-language pre-train

Google Research Datasets 226 Dec 07, 2022
The Official Implementation of Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose [NIPS 2021].

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Release Notes The offical PyTorch implementation of Neural View Sy

Angtian Wang 20 Oct 09, 2022
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Exposure: A White-Box Photo Post-Processing Framework ACM Transactions on Graphics (presented at SIGGRAPH 2018) Yuanming Hu1,2, Hao He1,2, Chenxi Xu1,

Yuanming Hu 719 Dec 29, 2022
A implemetation of the LRCN in mxnet

A implemetation of the LRCN in mxnet ##Abstract LRCN is a combination of CNN and RNN ##Installation Download UCF101 dataset ./avi2jpg.sh to split the

44 Aug 25, 2022
Einshape: DSL-based reshaping library for JAX and other frameworks.

Einshape: DSL-based reshaping library for JAX and other frameworks. The jnp.einsum op provides a DSL-based unified interface to matmul and tensordot o

DeepMind 62 Nov 30, 2022
Implementation of Sequence Generative Adversarial Nets with Policy Gradient

SeqGAN Requirements: Tensorflow r1.0.1 Python 2.7 CUDA 7.5+ (For GPU) Introduction Apply Generative Adversarial Nets to generating sequences of discre

Lantao Yu 2k Dec 29, 2022
A new play-and-plug method of controlling an existing generative model with conditioning attributes and their compositions.

Viz-It Data Visualizer Web-Application If I ask you where most of the data wrangler looses their time ? It is Data Overview and EDA. Presenting "Viz-I

NVIDIA Research Projects 66 Jan 01, 2023
A Pytorch implementation of CVPR 2021 paper "RSG: A Simple but Effective Module for Learning Imbalanced Datasets"

RSG: A Simple but Effective Module for Learning Imbalanced Datasets (CVPR 2021) A Pytorch implementation of our CVPR 2021 paper "RSG: A Simple but Eff

120 Dec 12, 2022
Towards Representation Learning for Atmospheric Dynamics (AtmoDist)

Towards Representation Learning for Atmospheric Dynamics (AtmoDist) The prediction of future climate scenarios under anthropogenic forcing is critical

Sebastian Hoffmann 4 Dec 15, 2022
Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images"

Reverse_Engineering_GMs Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Gener

100 Dec 18, 2022
On-device speech-to-index engine powered by deep learning.

On-device speech-to-index engine powered by deep learning.

Picovoice 30 Nov 24, 2022
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Learning Pixel-level Semantic Affinity with Image-level Supervision This code is deprecated. Please see https://github.com/jiwoon-ahn/irn instead. Int

Jiwoon Ahn 337 Dec 15, 2022
Data augmentation for NLP, accepted at EMNLP 2021 Findings

AEDA: An Easier Data Augmentation Technique for Text Classification This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Techni

Akbar Karimi 81 Dec 09, 2022
AI Based Smart Exam Proctoring Package

AI Based Smart Exam Proctoring Package It takes image (base64) as input: Provide Output as: Detection of Mobile phone. Detection of More than 1 person

NARENDER KESWANI 3 Sep 09, 2022
Code for CVPR2019 paper《Unequal Training for Deep Face Recognition with Long Tailed Noisy Data》

Unequal-Training-for-Deep-Face-Recognition-with-Long-Tailed-Noisy-Data. This is the code of CVPR 2019 paper《Unequal Training for Deep Face Recognition

Zhong Yaoyao 68 Jan 07, 2023
Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

NeuralTextures This is repository with inference code for paper "StylePeople: A Generative Model of Fullbody Human Avatars" (CVPR21). This code is for

Visual Understanding Lab @ Samsung AI Center Moscow 18 Oct 06, 2022
PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

Image Super-Resolution with Non-Local Sparse Attention This repository is for NLSN introduced in the following paper "Image Super-Resolution with Non-

143 Dec 28, 2022
A TensorFlow implementation of FCN-8s

FCN-8s implementation in TensorFlow Contents Overview Examples and demo video Dependencies How to use it Download pre-trained VGG-16 Overview This is

Pierluigi Ferrari 50 Aug 08, 2022