jkam1211 / ibn-net Goto Github PK

Xingang Pan, Ping Luo, Jianping Shi, Xiaoou Tang. "Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net", ECCV2018.

• IBN-Net is a CNN model with domain/appearance invariance. It carefully unifies instance normalization and batch normalization in a single deep network.
• It provides a simple way to increase both modeling and generalization capacity without adding model complexity.
• IBN-Net is especially suitable for cross domain or person/vehicle re-identification tasks, see michuanhaohao/reid-strong-baseline and strong baseline for ReID for more details.

• Pytorch 0.4.1 or higher

Top1/Top5 error on the ImageNet validation set are reported. You may get different results when training your models with different random seed.

The rank1/mAP on two Re-ID benchmarks Market1501 and DukeMTMC-reID (from michuanhaohao/reid-strong-baseline):

import torch
model = torch.hub.load('XingangPan/IBN-Net', 'resnet50_ibn_a', pretrained=True)

1. Clone the repository

   git clone https://github.com/XingangPan/IBN-Net.git

2. Download ImageNet dataset (if you need to test or train on ImageNet). You may follow the instruction at fb.resnet.torch to process the validation set.

1. Edit test.sh. Modify model and data_path to yours.
   Options for model: resnet50_ibn_a, resnet50_ibn_b, resnet101_ibn_a, resnext101_ibn_a, se_resnet101_ibn_a, densenet121_ibn_a, densenet169_ibn_a.

2. Run test script

   sh test.sh

1. Edit train.sh. Modify model and data_path to yours.
2. Run train script

   sh train.sh

This code is developed based on bearpaw/pytorch-classification.

https://github.com/bruinxiong/IBN-Net.mxnet

@inproceedings{pan2018IBN-Net,  
  author = {Xingang Pan, Ping Luo, Jianping Shi, and Xiaoou Tang},  
  title = {Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net},  
  booktitle = {ECCV},  
  year = {2018}  
}