No description, website, or topics provided.
Switch branches/tags
Nothing to show
Clone or download
Pull request Compare This branch is 6 commits ahead, 12 commits behind liu-xb:master.
Latest commit 0196f1a Jun 28, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
caffe f Jun 6, 2018
features Create readme.txt Jun 6, 2018
model/veri Create readme.txt Jun 6, 2018
prototxt Add files via upload Jun 26, 2018
snapshot Add files via upload Jun 25, 2018
README.md Add files via upload Jun 28, 2018
compute_AP.m f Jun 6, 2018
evaluate.m Add files via upload Jun 28, 2018
ex-mod-col-fc6.prototxt Add files via upload Jun 6, 2018
ex.txt Add files via upload Jun 6, 2018
gt_index.txt Add files via upload Jun 6, 2018
jk_index.txt Add files via upload Jun 6, 2018
norm_code.m Add files via upload Jun 6, 2018
read_code.m Add files via upload Jun 6, 2018
train-id-col-mod.txt Add files via upload Jun 6, 2018
train_veri.sh Add files via upload Jun 25, 2018

README.md

RAM (ICME2018)

This is the code of our ICME 2018 paper, "RAM: A Region-Aware Deep Model for Vehicle Re-Identification".
If you find this help, please kindly cite our paper:

@inproceedings{cime-ram-liu,
  Author = {Liu, Xiaobin and Zhang, Shiliang and Huang, Qingming and Gao, Wen},<br>
  Booktitle = {ICME},
  Title = {RAM: A Region-Aware Deep Model for Vehicle Re-Identification},
  Year = {2018}
}

Train the model

You can simply train a RAM on VeRi by running:

sh train_veri.sh

The final model is saved as "snapshot/veri-RAM-finetune_iter_60000.caffemodel". Our models and extracted features on VeRi can be downloaded from here.

We provide a new caffe layer to sample mini-batch. Please refer to "prototxt/train_RAM.prototxt" for an example of usage.

Evaluate the performance

We provide an evaluate script, "evaluate.m", on VeRi following https://github.com/VehicleReId/VeRidataset

We provide a tools in caffe to extract features and write features to binary files. We also provide a tools to read features from binary file, "read_code.m", and a tools to normalize features, "norm_code.m". An example of the usage of these tools can be found in "evaluate.m".

Contact me

Email: xbliu.vmc@pku.edu.cn
Homepage: https://liu-xb.github.io
Please feel free to contact me if you have any question.