https://github.com/zjykzj/crow-pytorch
[ECCV 2016] Cross-dimensional weighting for aggregated deep convolutional features.
https://github.com/zjykzj/crow-pytorch
crow pytorch
Last synced: about 2 months ago
JSON representation
[ECCV 2016] Cross-dimensional weighting for aggregated deep convolutional features.
- Host: GitHub
- URL: https://github.com/zjykzj/crow-pytorch
- Owner: zjykzj
- License: apache-2.0
- Created: 2022-06-22T11:22:04.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-06-27T12:15:09.000Z (almost 4 years ago)
- Last Synced: 2025-06-15T10:42:24.417Z (about 1 year ago)
- Topics: crow, pytorch
- Language: Python
- Homepage:
- Size: 78.1 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
«crow-pytorch» uses Pytorch to reproduce the CroW implementation.
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Background](#background)
- [Installation](#installation)
- [Usage](#usage)
- [Maintainers](#maintainers)
- [Thanks](#thanks)
- [Contributing](#contributing)
- [License](#license)
## Background
[CroW](https://arxiv.org/abs/1512.04065) provides a general convolution feature extraction framework, and proposes parameterless spatial weighting and channel weighting algorithms. In addition, a very detailed implementation is provided - [YahooArchive/crow](https://github.com/YahooArchive/crow).
The official implementation is based on [caffe2](https://caffe2.ai/), but the most popular deep reasoning framework at present is [pytorch](http://caffe.berkeleyvision.org/). In order to better understand the implementation of CroW, I try to replace the implementation of caffe in the warehouse with pytorch.
## Installation
```shell
pip install -r requirements.txt
```
## Usage
1. Get data
```shell
bash oxford/get_oxford.sh
bash paris/get_paris.sh
```
2. Extract features
```shell
python extract_features.py --images oxford/data/* --out oxford/layer4 --layer layer4
python extract_features.py --images paris/data/* --out paris/layer4 --layer layer4
python extract_queries.py --dataset oxford --images data --groundtruth groundtruth --layer layer4
```
3. Compile eval tool
```shell
g++ -O compute_ap.cpp -o compute_ap
```
4. Evaluate
```shell
python evaluate.py --queries oxford/layer4_queries --groundtruth oxford/groundtruth --index_features oxford/layer4 --wt crow --dw 3 --whiten_features paris/layer4 --d 512 --qe 3
```
## Maintainers
* Clayton Mellina - *Initial work* - [pumpikano](https://github.com/pumpikano)
* zhujian - *Enhance work* - [zjykzj](https://github.com/zjykzj)
## Thanks
* [YahooArchive/crow](https://github.com/YahooArchive/crow)
## Contributing
Anyone's participation is welcome! Open an [issue](https://github.com/zjykzj/crow-pytorch/issues) or submit PRs.
Small note:
* Git submission specifications should be complied
with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0-beta.4/)
* If versioned, please conform to the [Semantic Versioning 2.0.0](https://semver.org) specification
* If editing the README, please conform to the [standard-readme](https://github.com/RichardLitt/standard-readme)
specification.
## License
[Apache License 2.0](LICENSE) © 2022 zjykzj