4.5 KiB

Raw Blame History

Bags of Tricks and A Strong ReID Baseline

Paper: The codes are expanded on a ReID-baseline , which is open sourced by our co-author Xingyu Liao.

We support

easy dataset preparation
end-to-end training and evaluation
high modular management

Bag of tricks

Warm up learning rate
Random erasing augmentation
Label smoothing
Last stride
BNNeck
Center loss

Get Started

The designed architecture follows this guide PyTorch-Project-Template, you can check each folder's purpose by yourself.

cd to folder where you want to download this repo
Run git clone...
Install dependencies:
- pytorch 1.0
- torchvision
- ignite
- yacs
Prepare dataset

Create a directory to store reid datasets under this repo via
```
cd reid_baseline
mkdir data
```
（1）Market1501
- Download dataset to data/ from http://www.liangzheng.org/Project/project_reid.html
- Extract dataset and rename to market1501. The data structure would like:
```
data
    market1501 # this folder contains 6 files.
        bounding_box_test/
        bounding_box_train/
        ......
```
（2）DukeMTMC-reID
- Download dataset to data/ from https://github.com/layumi/DukeMTMC-reID_evaluation#download-dataset
- Extract dataset and rename to dukemtmc-reid. The data structure would like:
```
data
    dukemtmc-reid
    	DukeMTMC-reID # this folder contains 8 files.
        	bounding_box_test/
        	bounding_box_train/
        	......
```
Prepare pretrained model if you don't have
```
from torchvision import models
models.resnet50(pretrained=True)
```
Then it will automatically download model in ~/.torch/models/, you should set this path in config/defaults.py for all training or set in every single training config file in configs/.
If you want to know the detained configurations and their meaning, please refer to config/defaults.py. If you want to set your own parameters, you can follow our method: create a new yml file, then set your own parameters. Add --config_file='configs/your yml file' int the commands described below, then our code will merge your configuration. automatically.

Train

You can run these commands in .sh files for training different datasets of differernt loss. You can also directly run code sh *.sh to run our demo.

Market1501, cross entropy loss + triplet loss

python3 tools/train.py --config_file='configs/softmax_triplet.yml' MODEL.DEVICE_ID "('your device id')" DATASETS.NAMES "('market1501')" OUTPUT_DIR "('your path to save checkpoints and logs')"

DukeMTMC-reID, cross entropy loss + triplet loss + center loss

python3 tools/train.py --config_file='configs/softmax_triplet_with_center.yml' MODEL.DEVICE_ID "('your device id')" DATASETS.NAMES "('dukemtmc')" OUTPUT_DIR "('your path to save checkpoints and logs')"

Test

You can test your model's performance directly by running these commands in .sh files. You can also change the configuration to determine which feature of BNNeck and whether the feature is normalized (equivalent to use Cosine distance or Euclidean distance) for testing.

Test with Euclidean distance using feature before BN without re-ranking,.

python3 tools/test.py --config_file='configs/softmax_triplet_with_center.yml' MODEL.DEVICE_ID "('your device id')" DATASETS.NAMES "('market1501')" TEST.NECK_FEAT "('before')" TEST.FEAT_NORM "('no')" TEST.WEIGHT "('your path to trained checkpoints')"

Test with Cosine distance using feature after BN without re-ranking,.

python3 tools/test.py --config_file='configs/softmax_triplet_with_center.yml' MODEL.DEVICE_ID "('your device id')" DATASETS.NAMES "('market1501')" TEST.NECK_FEAT "('after')" TEST.FEAT_NORM "('yes')" TEST.WEIGHT "('your path to trained checkpoints')"

Test with Cosine distance using feature after BN with re-ranking

python3 tools/test.py --config_file='configs/softmax_triplet_with_center.yml' MODEL.DEVICE_ID "('your device id')" DATASETS.NAMES "('dukemtmc')" TEST.NECK_FEAT "('after')" TEST.FEAT_NORM "('yes')" TEST.RE_RANKING "('yes')" TEST.WEIGHT "('your path to trained checkpoints')"

Results

Network architecture