AI Rank
EN
← 开源
HonglinChu

SiamTrackers

(2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on deep learning

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.66k
Star
310
Fork
+2
本周
2
贡献者
创建于 2020-04-07 · 更新于 2026-10-13 · 今日第 9748 名
主要开发者
HonglinChuzihaomu

HonglinChu/SiamTrackers 排名第 9,748，有 1,660 个星标。

同类别比较

HonglinChu/SiamTrackers 排名第 9,748，此处有 8 个同类条目；Data-Centric-AI-Community/fg-data-synthetic 排名第 9,747。

同类别比较
名称排名指标
uber-research/deep-neuroevolution9,734
语言:
Python
星标数:
1,669
分叉数:
297
简介:
Deep Neuroevolution
datamllab/tods9,737
语言:
Python
星标数:
1,667
分叉数:
206
简介:
TODS: An Automated Time-series Outlier Detection System
tencent-ailab/persona-hub9,738
语言:
Python
星标数:
1,666
分叉数:
134
简介:
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
Data-Centric-AI-Community/fg-data-synthetic9,747
语言:
Jupyter Notebook
星标数:
1,660
分叉数:
257
简介:
Synthetic data generators for tabular and time-series data
hfawaz/dl-4-tsc9,749
语言:
Python
星标数:
1,660
分叉数:
592
简介:
Deep Learning for Time Series Classification
mhamilton723/FeatUp9,766
语言:
Jupyter Notebook
星标数:
1,655
分叉数:
96
简介:
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
openai/neural-mmo9,767
语言:
Python
星标数:
1,655
分叉数:
272
简介:
Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"
opendilab/LightZero9,774
语言:
Python
星标数:
1,652
分叉数:
201
简介:
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数1,660
分叉数310
贡献者2
创建日期2020-04-07
更新日期2026-10-13
1 天星标数0
7 天星标数2
排名9,748
上次排名9,789
排名变化41
7 天星标排名7,963
上次 7 天星标排名8,006
7 天星标排名变化43
总星标排名7,439
上次总星标排名7,432
总星标排名变化-7
国家China
README 摘录

SiamTrackers NanoTrackV1 Experiment NanoTrack is a lightweight and high speed tracking network which mainly referring to SiamBAN and LightTrack. It is suitable for deployment on embedded or mobile devices. In fact, V1 and V2 can run at **> 200FPS** on Apple M1 CPU. 4K | Experiments show that NanoTrack has good performance on tracking datasets. 815 | | CVPR2021 LightTrack | MobileNetV3 | 7. 766 | | WACV2022 SiamTPN | ShuffleNetV2 | 62. 728 | | ICRA2021 SiamAPN | AlexNet | 118. 786 | | IROS2021 SiamAPN++ | AlexNet | 187MB | 0. 791 | For NanoTrackV1, we provide Android

demo and MacOS demo based on ncnn inference framework. It is friendly for training with much lower GPU memory cost than other models. NanoTrackV1 only uses GOT-10k dataset to train, which only takes two hours on RTX3090. OpenCV API Dataset **All json files** BaiduYun parrword: xm5w (The json files are provided by pysot) Test **OTB2015** BaiduYun password: t5i1 **VOT2016** BaiduYun password: v7vq **VOT2018** BaiduYun password: e5eh **VOT2019** BaiduYun password: p4fi **VOT2020** BaiduYun password: x93i **UAV123** BaiduYun password: 2iq4 **DTB70

** BaiduYun password: e7qm **UAVDT** BaiduYun password: keva **VisDrone2019** BaiduYun password: yxb6 **TColor128** BaiduYun password: 26d4 **NFS** BaiduYun password: vng1 Train **GOT10k** BaiduYun password: uxds **LaSOT** BaiduYun password: ygtx **ILSVRC2015 VID** BaiDuYun password: uqzj **ILSVRC2015 DET** BaiDuYun password: 6fu7 **YTB-Crop511** BaiduYun password: ebq1 **COCO** BaiduYun password: ggya **TrackingNet** BaiduYun password: nkb9 (Note that this link is provided by SiamFCpp author) Mask **YTB-VOS** BaiduYun password: sf1m **DAVIS2017** BaiduYun password: c9qp Toolkit Matlab version **OTB2013/2015** Github **UAVDT** BaiduYun password: ehit

**VOT2016-toolkit** BaiduYun password: 272e **VOT2018-toolkit** BaiduYun password: xpkb Python version **pysot-toolkit**： OTB, VOT, UAV, NfS, LaSOT are supported. BaiduYun password: 2t2q **got10k-toolkit**：GOT-10k, OTB, VOT, UAV, TColor, DTB, NfS, LaSOT and TrackingNet are supported. BaiduYun password: vsar Papers BaiduYun password: fukj Reference

常见问题

记录了多少星标和分叉？

HonglinChu/SiamTrackers 有 1,660 个星标和 310 个分叉。

仓库排名是多少？

HonglinChu/SiamTrackers 排名第 9,748。

记录的语言和类别是什么？

HonglinChu/SiamTrackers 有 1,660 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

HonglinChu/SiamTrackers 与 Data-Centric-AI-Community/fg-data-synthetic 比较，后者排名第 9,747，有 1,660 个星标。

README

SiamTrackers

Experiment

  • NanoTrack is a lightweight and high speed tracking network which mainly referring to SiamBAN and LightTrack. It is suitable for deployment on embedded or mobile devices. In fact, V1 and V2 can run at > 200FPS on Apple M1 CPU.
Trackers Backbone Size(*.onnx) Head Size (*.onnx) FLOPs Parameters
NanoTrackV1 752K 384K 75.6M 287.9K
NanoTrackV2 1.0M 712K 84.6M 334.1K
NanoTrackV3 1.4M 1.1M 115.6M 541.4K
  • Experiments show that NanoTrack has good performance on tracking datasets.
Trackers Backbone Model Size(*.pth) VOT2018 EAO VOT2019 EAO GOT-10k-Val AO GOT-10k-Val SR DTB70 Success DTB70 Precision
NanoTrackV1 MobileNetV3 2.4MB 0.311 0.247 0.604 0.724 0.532 0.727
NanoTrackV2 MobileNetV3 2.0MB 0.352 0.270 0.680 0.817 0.584 0.753
NanoTrackV3 MobileNetV3 3.4MB 0.449 0.296 0.719 0.848 0.628 0.815
CVPR2021 LightTrack MobileNetV3 7.7MB 0.418 0.328 0.75 0.877 0.591 0.766
WACV2022 SiamTPN ShuffleNetV2 62.2MB 0.191 0.209 0.728 0.865 0.572 0.728
ICRA2021 SiamAPN AlexNet 118.7MB 0.248 0.235 0.622 0.708 0.585 0.786
IROS2021 SiamAPN++ AlexNet 187MB 0.268 0.234 0.635 0.73 0.594 0.791

  • For NanoTrackV1, we provide Android demo and MacOS demo based on ncnn inference framework.

  • We also provide PyTorch code. It is friendly for training with much lower GPU memory cost than other models. NanoTrackV1 only uses GOT-10k dataset to train, which only takes two hours on RTX3090.

OpenCV API

Dataset

  • All json files BaiduYun parrword: xm5w (The json files are provided by pysot)

Test

Train

  • GOT10k BaiduYun password: uxds

  • LaSOT BaiduYun password: ygtx

  • ILSVRC2015 VID BaiDuYun password: uqzj

  • ILSVRC2015 DET BaiDuYun password: 6fu7

  • YTB-Crop511 BaiduYun password: ebq1

  • COCO BaiduYun password: ggya

  • TrackingNet BaiduYun password: nkb9 (Note that this link is provided by SiamFCpp author)

Mask

Toolkit

Matlab version

Python version

  • pysot-toolkit： OTB, VOT, UAV, NfS, LaSOT are supported.BaiduYun password: 2t2q

  • got10k-toolkit：GOT-10k, OTB, VOT, UAV, TColor, DTB, NfS, LaSOT and TrackingNet are supported.BaiduYun password: vsar

Papers

BaiduYun password: fukj

Reference

[1] SiamFC

Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking.European conference on computer vision. Springer, Cham, 2016: 850-865.
   
[2] SiamRPN

Li B, Yan J, Wu W, et al. High performance visual tracking with siamese region proposal network.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8971-8980.

[3] DaSiamRPN

Zhu Z, Wang Q, Li B, et al. Distractor-aware siamese networks for visual object tracking.Proceedings of the European Conference on Computer Vision (ECCV). 2018: 101-117.

[4] UpdateNet

Zhang L, Gonzalez-Garcia A, Weijer J, et al. Learning the Model Update for Siamese Trackers. Proceedings of the IEEE International Conference on Computer Vision. 2019: 4010-4019.
   
[5] SiamDW

Zhang Z, Peng H. Deeper and wider siamese networks for real-time visual tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 4591-4600.

[6] SiamRPNpp

Li B, Wu W, Wang Q, et al. SiamRPNpp: Evolution of siamese visual tracking with very deep networks.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 4282-4291.

[7] SiamMask

Wang Q, Zhang L, Bertinetto L, et al. Fast online object tracking and segmentation: A unifying approach. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 1328-1338.
   
[8] SiamFCpp

Xu Y, Wang Z, Li Z, et al. SiamFCpp: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines. AAAI, 2020.

[9] SiamCAR
Guo D ,  Wang J ,  Cui Y , et al. SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2020.

[10] SiamBAN
Chen Z, Zhong B, Li G, et al. Siamese box adaptive network for visual tracking[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6668-6677.

[11] TrTr 
Zhao M, Okada K, Inaba M. TrTr: Visual Tracking with Transformer[J]. arXiv preprint arXiv:2105.03817, 2021.

[12] LightTrack 
Yan B, Peng H, Wu K, et al. Lighttrack: Finding lightweight neural networks for object tracking via one-shot architecture search[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 15180-15189.
排名相邻
同类项目