https://github.com/aleju/cat-bbs-regression
Detect cat faces in images using CNNs with regression
https://github.com/aleju/cat-bbs-regression
bounding-boxes deep-learning network neural regression
Last synced: about 1 year ago
JSON representation
Detect cat faces in images using CNNs with regression
- Host: GitHub
- URL: https://github.com/aleju/cat-bbs-regression
- Owner: aleju
- License: mit
- Created: 2015-11-06T20:43:06.000Z (over 10 years ago)
- Default Branch: master
- Last Pushed: 2017-08-16T19:17:45.000Z (almost 9 years ago)
- Last Synced: 2025-03-25T03:12:48.826Z (about 1 year ago)
- Topics: bounding-boxes, deep-learning, network, neural, regression
- Language: Python
- Homepage:
- Size: 107 KB
- Stars: 17
- Watchers: 2
- Forks: 5
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# About
Simple convolutional neural network to detect cat bounding boxes in images.
The system is restricted to one bounding box per image, which is localized using regression (i.e. directly predicting the bounding box coordinates).
The model consists of 7 convolutional layers and 2 fully connected layers (including output layer).
# Dependencies
* python 2.7 (only tested with that version)
* keras (tested in v1.06)
* scipy
* numpy
* scikit-image
# Usage
* Download the [10k cats dataset](https://web.archive.org/web/20150520175645/http://137.189.35.203/WebUI/CatDatabase/catData.html) and extract it, e.g. into directory `/foo/bar/10k-cats`. That directory should contain the subdirectories `CAT_00`, `CAT_01`, etc.
* Train the model using `train_convnet.py --dataset="/foo/bar/10k-cats"`.
* Apply the model using `train_convnet.py --dataset="/foo/bar/directory-with-cat-images"`.
# Images
Example results:
