zhunzhong07 / Ide Baseline Market 1501
ID-discriminative Embedding (IDE) for Person Re-identification
Stars: ✭ 220
Programming Languages
matlab
3953 projects
Labels
Projects that are alternatives of or similar to Ide Baseline Market 1501
Caffe Oneclick
Use caffe to train your own data in just one click
Stars: ✭ 187 (-15%)
Mutual labels: caffe
Up Down Captioner
Automatic image captioning model based on Caffe, using features from bottom-up attention.
Stars: ✭ 195 (-11.36%)
Mutual labels: caffe
Caffe Deepbinarycode
Supervised Semantics-preserving Deep Hashing (TPAMI18)
Stars: ✭ 206 (-6.36%)
Mutual labels: caffe
Light Field Video
Light field video applications (e.g. video refocusing, focus tracking, changing aperture and view)
Stars: ✭ 190 (-13.64%)
Mutual labels: caffe
Pixelnet
The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.
Stars: ✭ 194 (-11.82%)
Mutual labels: caffe
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (-18.64%)
Mutual labels: caffe
Dl inference
通用深度学习推理服务，可在生产环境中快速上线由TensorFlow、PyTorch、Caffe框架训练出的深度学习模型。
Stars: ✭ 209 (-5%)
Mutual labels: caffe
Liteflownet2
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (-11.36%)
Mutual labels: caffe
Dsrg
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR 2018).
Stars: ✭ 206 (-6.36%)
Mutual labels: caffe
Ck Caffe
Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):
Stars: ✭ 192 (-12.73%)
Mutual labels: caffe
Raspberrypi Facedetection Mtcnn Caffe With Motion
MTCNN with Motion Detection, on Raspberry Pi with Love
Stars: ✭ 204 (-7.27%)
Mutual labels: caffe
Snn toolbox
Toolbox for converting analog to spiking neural networks (ANN to SNN), and running them in a spiking neuron simulator.
Stars: ✭ 187 (-15%)
Mutual labels: caffe
Auto Reid And Others
Auto-ReID and Other Person Re-Identification Projects
Stars: ✭ 198 (-10%)
Mutual labels: caffe
Caffe Yolov3 Windows
A windows caffe implementation of YOLO detection network
Stars: ✭ 210 (-4.55%)
Mutual labels: caffe
Interactive Deep Colorization
Deep learning software for colorizing black and white images with a few clicks.
Stars: ✭ 2,465 (+1020.45%)
Mutual labels: caffe
Netron
Visualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+7715%)
Mutual labels: caffe
Code for IDE baseline on Market-1501
============= This code was used for experiments with ID-discriminative Embedding (IDE) for Market-1501 dataset.
Thanks Liboyue, give us suggestions for improvement.
If you find this code useful in your research, please consider citing:
@article{zheng2016person,
title={Person Re-identification: Past, Present and Future},
author={Zheng, Liang and Yang, Yi and Hauptmann, Alexander G},
journal={arXiv preprint arXiv:1610.02984},
year={2016}
}
@inproceedings{zheng2015scalable,
title={Scalable Person Re-identification: A Benchmark},
author={Zheng, Liang and Shen, Liyue and Tian, Lu and Wang, Shengjin and Wang, Jingdong and Tian, Qi},
booktitle={Computer Vision, IEEE International Conference on},
year={2015}
}
Requirements: Caffe
Requirements for Caffe and matcaffe (see: Caffe installation instructions)
Installation
- Clone the IDE repository
# Make sure to clone with --recursive
git clone --recursive https://github.com/zhunzhong07/IDE-baseline-Market-1501
-
Build Caffe and matcaffe
cd $IDE_ROOT/caffe # Now follow the Caffe installation instructions here: # http://caffe.berkeleyvision.org/installation.html make -j8 && make matcaffe -
Download pre-computed models and Market-1501 dataset
Please download the pre-trained imagenet models and put it in the "data/imagenet_models" folder.
Please download Market-1501 dataset and unzip it in the "market_evaluation/dataset" folder.
Training and testing IDE model
- Training
cd $IDE_ROOT
# train IDE on CaffeNet
./experiments/market/train_IDE_CaffeNet.sh
# train IDE ResNet_50
./experiments/market/train_IDE_ResNet_50.sh
# The IDE models are saved under: "out/market_train"
# If you encounter this problem: bash: ./experiments/market/train_IDE_CaffeNet.sh: Permission denied
# Please execute: chmod 777 -R experiments/
- Feature Extraction
cd $IDE_ROOT/market_evaluation
Run Matlab: extract_feature.m
# The IDE features are saved under: "market_evaluation/feat"
- Evaluation
Run Matlab: baseline_evaluation_IDE.m
Results
You can download our pre-trained IDE models and IDE features, and put them in the "out_put/market_train" and "market_evaluation/feat" folder, respectively.
Using the models and features above, you can reproduce the results as follows:
| Methods | [email protected] | mAP |
|---|---|---|
| IDE_CaffeNet + Euclidean | 59.53% | 32.85% |
| IDE_CaffeNet + XQDA | 62.00% | 37.55% |
| IDE_CaffeNet + KISSME | 61.02% | 36.72% |
| IDE_ResNet_50 + Euclidean | 75.62% | 50.68% |
| IDE_ResNet_50 + XQDA | 76.01% | 52.98% |
| IDE_ResNet_50 + KISSME | 77.52% | 53.88% |
If you add a dropout = 0.5 layer after pool5, you will get a better performance for ResNet_50:
| Methods | [email protected] | mAP |
|---|---|---|
| IDE_ResNet_50 + dropout(0.5) + Euclidean | 78.92% | 55.03% |
| IDE_ResNet_50 + dropout(0.5) + XQDA | 77.35% | 56.01% |
| IDE_ResNet_50 + dropout(0.5) + KISSME | 78.80% | 56.13% |
Contact us
If you have any questions about this code, please do not hesitate to contact us.
Related Repos
Furthermore, you may check the following codes.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].