Person_reID_baseline_pytorch

A tiny, friendly, strong baseline code for Person-reID (based on pytorch).

• Strong. It is consistent with the new baseline result in several top-conference works, e.g., Beyond Part Models: Person Retrieval with Refined Part Pooling(ECCV18) and Camera Style Adaptation for Person Re-identification(CVPR18). We arrived Rank@1=88.24%, mAP=70.68% only with softmax loss.

• Small. With fp16, our baseline could be trained with only 2GB GPU memory.

• Friendly. You may use the off-the-shelf options to apply many state-of-the-art tricks in one line. Besides, if you are new to person re-ID, you may check out our Tutorial first (8 min read) 👍 .

Table of contents

• Features
• Some News
• Trained Model
• Prerequisites
• Getting Started
  • Installation
  • Dataset Preparation
  • Train
  • Test
  • Evaluation
• Tips for training with other datasets
• Citation
• Related Repos

Features

Now we have supported:

• Float16 to save GPU memory based on apex
• Part-based Convolutional Baseline(PCB)
• Multiple Query Evaluation
• Re-Ranking
• Random Erasing
• ResNet/DenseNet
• Visualize Training Curves
• Visualize Ranking Result

Here we provide hyperparameters and architectures, that were used to generate the result. Some of them (i.e. learning rate) are far from optimal. Do not hesitate to change them and see the effect.

P.S. With similar structure, we arrived Rank@1=87.74% mAP=69.46% with Matconvnet. (batchsize=8, dropout=0.75) You may refer to Here. Different framework need to be tuned in a different way.

Some News

What's new: FP16 has been added. It can be used by simply added --fp16. You need to install apex and update your pytorch to 1.0.

Float16 could save about 50% GPU memory usage without accuracy drop. Our baseline could be trained with only 2GB GPU memory.

python train.py --fp16

What's new: Visualizing ranking result is added.

python prepare.py
python train.py
python test.py
python demo.py --query_index 777

What's new: Multiple-query Evaluation is added. The multiple-query result is about Rank@1=91.95% mAP=78.06%.

python prepare.py
python train.py
python test.py --multi
python evaluate_gpu.py

What's new:  PCB is added. You may use '--PCB' to use this model. It can achieve around Rank@1=92.73% mAP=78.16%. I used a GPU (P40) with 24GB Memory. You may try apply smaller batchsize and choose the smaller learning rate (for stability) to run. (For example, --batchsize 32 --lr 0.01 --PCB)

python train.py --PCB --batchsize 64 --name PCB-64
python test.py --PCB --name PCB-64

What's new: You may try evaluate_gpu.py to conduct a faster evaluation with GPU.

What's new: You may apply '--use_dense' to use DenseNet-121. It can arrive around Rank@1=89.91% mAP=73.58%.

What's new: Re-ranking is added to evaluation. The re-ranked result is about Rank@1=90.20% mAP=84.76%.

What's new: Random Erasing is added to train.

What's new: I add some code to generate training curves. The figure will be saved into the model folder when training.

Trained Model

I re-trained several models, and the results may be different with the original one. Just for a quick reference, you may directly use these models. The download link is Here.

Methods	Rank@1	mAP	Reference
[ResNet-50]	88.84%	71.59%	python train.py --train_all
[DenseNet-121]	90.17%	74.02%	python train.py --name ft_net_dense --use_dense --train_all
[PCB]	92.64%	77.47%	python train.py --name PCB --PCB --train_all --lr 0.02
[ResNet-50 (fp16)]	88.03%	71.40%	python train.py --name fp16 --fp16 --train_all

Model Structure

You may learn more from model.py. We add one linear layer(bottleneck), one batchnorm layer and relu.

Prerequisites

• Python 3.6
• GPU Memory >= 6G
• Numpy
• Pytorch 0.3+
• [Optional] apex (for float16)
• [Optional] pretrainedmodels

(Some reports found that updating numpy can arrive the right accuracy. If you only get 50~80 Top1 Accuracy, just try it.) We have successfully run the code based on numpy 1.12.1 and 1.13.1 .

Getting started

Installation

• Install Pytorch from http://pytorch.org/
• Install Torchvision from the source

git clone https://github.com/pytorch/vision
cd vision
python setup.py install

• [Optinal] You may skip it. Install apex from the source

git clone https://github.com/NVIDIA/apex.git
cd apex
python setup.py install --cuda_ext --cpp_ext

Because pytorch and torchvision are ongoing projects.

Here we noted that our code is tested based on Pytorch 0.3.0/0.4.0/0.5.0/1.0.0 and Torchvision 0.2.0/0.2.1 .

Dataset & Preparation

Download Market1501 Dataset

Preparation: Put the images with the same id in one folder. You may use

python prepare.py

Remember to change the dataset path to your own path.

Futhermore, you also can test our code on DukeMTMC-reID Dataset. Our baseline code is not such high on DukeMTMC-reID Rank@1=64.23%, mAP=43.92%. Hyperparameters are need to be tuned.

Train

Train a model by

python train.py --gpu_ids 0 --name ft_ResNet50 --train_all --batchsize 32  --data_dir your_data_path

--gpu_ids which gpu to run.

--name the name of model.

--data_dir the path of the training data.

--train_all using all images to train.

--batchsize batch size.

--erasing_p random erasing probability.

Train a model with random erasing by

python train.py --gpu_ids 0 --name ft_ResNet50 --train_all --batchsize 32  --data_dir your_data_path --erasing_p 0.5

Test

Use trained model to extract feature by

python test.py --gpu_ids 0 --name ft_ResNet50 --test_dir your_data_path  --batchsize 32 --which_epoch 59

--gpu_ids which gpu to run.

--batchsize batch size.

--name the dir name of trained model.

--which_epoch select the i-th model.

--data_dir the path of the testing data.

Evaluation

python evaluate.py

It will output Rank@1, Rank@5, Rank@10 and mAP results. You may also try evaluate_gpu.py to conduct a faster evaluation with GPU.

For mAP calculation, you also can refer to the C++ code for Oxford Building. We use the triangle mAP calculation (consistent with the Market1501 original code).

re-ranking

python evaluate_rerank.py

It may take more than 10G Memory to run. So run it on a powerful machine if possible.

It will output Rank@1, Rank@5, Rank@10 and mAP results.

Tips

Notes the format of the camera id and the number of cameras.

For some dataset, e.g., MSMT17, there are more than 10 cameras. You need to modify the prepare.py and test.py to read the double-digit camera ID.

For some vehicle re-ID datasets. e.g. VeRi, you also need to modify the prepare.py and test.py. It has different naming rules. layumi/Person_reID_baseline_pytorch#107 (Sorry. It is in Chinese)

Citation

As far as I know, the following papers may be the first two to use the bottleneck baseline. You may cite them in your paper.

@article{DBLP:journals/corr/SunZDW17,
  author    = {Yifan Sun and
               Liang Zheng and
               Weijian Deng and
               Shengjin Wang},
  title     = {SVDNet for Pedestrian Retrieval},
  booktitle   = {ICCV},
  year      = {2017},
}

@article{hermans2017defense,
  title={In Defense of the Triplet Loss for Person Re-Identification},
  author={Hermans, Alexander and Beyer, Lucas and Leibe, Bastian},
  journal={arXiv preprint arXiv:1703.07737},
  year={2017}
}

Related Repos

1. Pedestrian Alignment Network
2. 2stream Person re-ID
3. Pedestrian GAN
4. Language Person Search