AI Rank
中文
← Open Source
PengBoXiangShang

SiamRPN_plus_plus_PyTorch

SiamRPN, SiamRPN++, unofficial implementation of "SiamRPN++" (CVPR2019), multi-GPUs, LMDB.

ModelsVision modelsPython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
503
Stars
89
Forks
+0
This week
1
Contributors
Created 2019-04-12 · Updated 2026-07-21 · #18253 today
Top developers
PengBoXiangShang

PengBoXiangShang/SiamRPN_plus_plus_PyTorch is ranked 18,253 with 503 stars.

Same-category comparison

PengBoXiangShang/SiamRPN_plus_plus_PyTorch is ranked 18,253 among these 8 peers; GuyTevet/MotionCLIP is ranked 18,250.

Same-category comparison
NameRankMetrics
frank-xwang/UnSAM18,233
Language:
Jupyter Notebook
Stars:
504
Forks:
27
Description:
[NeurIPS 2024] Code release for "Segment Anything without Supervision".
rosinality/alias-free-gan-pytorch18,242
Language:
Python
Stars:
504
Forks:
43
Description:
Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch.
sail-sg/metaformer18,243
Language:
Python
Stars:
504
Forks:
31
Description:
MetaFormer Baselines for Vision (TPAMI 2024).
GuyTevet/MotionCLIP18,250
Language:
Python
Stars:
503
Forks:
45
Description:
Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space".
lumina37/rotate-captcha-crack18,262
Language:
Python
Stars:
503
Forks:
118
MarcoForte/FBA_Matting18,277
Language:
Jupyter Notebook
Stars:
502
Forks:
95
Description:
Official repository for the paper F, B, Alpha Matting.
facebookresearch/jepa-wms18,288
Language:
Python
Stars:
502
Forks:
64
Description:
Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models.
mikeferguson/robot_calibration18,293
Language:
C++
Stars:
502
Forks:
130
Description:
Generic calibration for robots.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModels
SubcategoryVision models
KeywordsDatasets, Distributed training, Model architecture, Object detection
Stars503
Forks89
Contributors1
Created date2019-04-12
Updated date2026-07-21
Stars in 1 day0
Stars in 7 days0
Rank18,253
Previous rank18,005
Rank change-248
7-day stars rank16,556
Previous 7-day stars rank16,573
7-day stars rank change17
Total stars rank19,275
Previous total stars rank19,249
Total stars rank change-26
CountryChina
README summary

SiamRPN++_PyTorch This is an unofficial PyTorch implementation of SiamRPN++ (CVPR2019), implemented by **Peng Xu** and **Jin Feng**. Our **training** can be conducted on **multi-GPUs**, and use **LMDB** data format to speed up the data loading. This project is designed with these goals: [x] Training on ILSVRC2015_VID dataset. [ ] Training on YouTube-BoundingBoxes dataset. [ ] Evaluate the performance on tracking benchmarks. Details of SiamRPN++ Network As stated in the original paper, SiamRPN++ network has three parts, including Backbone Networks, SiamRPN

Blocks, and Weighted Fusion Layers. Backbone Network (modified ResNet-50)** As stated in the original paper, SiamRPN++ uses ResNet-50 as backbone by modifying the strides and adding dilated convolutions for *conv4* and *conv5* blocks. Here, we present the detailed comparison between original ResNet-50 and SiamRPN++ ResNet-50 backbone in following table. SiamRPN Block** Based on our understanding to the original paper, we plot a architecture illustration to describe the *Siamese RPN* block as shown in following. We also

present the detailed configurations of each layer of RPN block in following table. Weighted Fusion Layer** We implemente the *weighted fusion layer* via **group convolution operations**. 0 Other main requirements can be installed by: Training Instructions Acknowledgement Many thanks to Sisi who helps us to download the huge ILSVRC2015_VID dataset.

Frequently asked questions

How many stars and forks are recorded?

PengBoXiangShang/SiamRPN_plus_plus_PyTorch has 503 stars and 89 forks.

What is the repository rank?

PengBoXiangShang/SiamRPN_plus_plus_PyTorch is ranked 18,253.

What language and category are recorded?

PengBoXiangShang/SiamRPN_plus_plus_PyTorch has 503 stars, uses Python and belongs to Models.

Which repository is closest in rank?

PengBoXiangShang/SiamRPN_plus_plus_PyTorch is compared with GuyTevet/MotionCLIP, ranked 18,250 with 503 stars.

README

SiamRPN++_PyTorch

This is an unofficial PyTorch implementation of SiamRPN++ (CVPR2019), implemented by Peng Xu and Jin Feng. Our training can be conducted on multi-GPUs, and use LMDB data format to speed up the data loading.

This project is designed with these goals:

  • [x] Training on ILSVRC2015_VID dataset.
  • [ ] Training on GOT-10k dataset.
  • [ ] Training on YouTube-BoundingBoxes dataset.
  • [ ] Evaluate the performance on tracking benchmarks.

Details of SiamRPN++ Network

As stated in the original paper, SiamRPN++ network has three parts, including Backbone Networks, SiamRPN Blocks, and Weighted Fusion Layers.

1. Backbone Network (modified ResNet-50)

As stated in the original paper, SiamRPN++ uses ResNet-50 as backbone by modifying the strides and adding dilated convolutions for conv4 and conv5 blocks. Here, we present the detailed comparison between original ResNet-50 and SiamRPN++ ResNet-50 backbone in following table.

bottleneck in conv4

bottleneck in conv5

conv1x1

conv3x3

conv1x1

conv1x1

conv3x3

conv1x1

original ResNet-50

stride

1

2

1

1

2

1

padding

0

1

0

0

1

0

dilation

1

1

1

1

1

1

ResNet-50 in SiamRPN++

stride

1

1

1

1

1

1

padding

0

2

0

0

4

0

dilation

1

2

1

1

4

1

2. SiamRPN Block

Based on our understanding to the original paper, we plot a architecture illustration to describe the Siamese RPN block as shown in following.

We also present the detailed configurations of each layer of RPN block in following table. Please see more details in ./network/RPN.py.

component configuration
adj_1 / adj_2 / adj_3 / adj_4 conv2d(256, 256, ksize=3, pad=1, stride=1), BN2d(256)
fusion_module_1 / fusion_module_2 conv2d(256, 256, ksize=1, pad=0, stride=1), BN2d(256), ReLU
box head conv2d(256, 4*5, ksize=1, pad=0, stride=1)
cls head conv2d(256, 2*5, ksize=1, pad=0, stride=1)

3. Weighted Fusion Layer

We implemente the weighted fusion layer via group convolution operations. Please see details in ./network/SiamRPN.py.

Requirements

Ubuntu 14.04

Python 2.7

PyTorch 0.4.0

Other main requirements can be installed by:

# 1. Install cv2 package.
conda install opencv

# 2. Install LMDB package.
conda install lmdb

# 3. Install fire package.
pip install fire -c conda-forge

Training Instructions

# 1. Clone this repository to your disk.
git clone https://github.com/PengBoXiangShang/SiamRPN_plus_plus_PyTorch.git

# 2. Change working directory.
cd SiamRPN_plus_plus_PyTorch

# 3. Download training data. In this project, we provide the downloading and preprocessing scripts for ILSVRC2015_VID dataset. Please download ILSVRC2015_VID dataset (86GB). The cripts for other tracking datasets are coming soon.
cd data
wget -c http://bvisionweb1.cs.unc.edu/ilsvrc2015/ILSVRC2015_VID.tar.gz
tar -xvf ILSVRC2015_VID.tar.gz
rm ILSVRC2015_VID.tar.gz
cd ..

# 4. Preprocess data.
chmod u+x ./preprocessing/create_dataset.sh
./preprocessing/create_dataset.sh

# 5. Pack the preprocessed data into LMDB format to accelerate data loading.
chmod u+x ./preprocessing/create_lmdb.sh
./preprocessing/create_lmdb.sh

# 6. Start the training.
chmod u+x ./train.sh
./train.sh

Acknowledgement

Many thanks to Sisi who helps us to download the huge ILSVRC2015_VID dataset.

Nearby in the ranking
Similar items