https://github.com/ducthienbui97/celebrity-faces-classifier
Classifier can detect 88 celebrities with accuracy of 50%
https://github.com/ducthienbui97/celebrity-faces-classifier
classification classifier cntk convolutional-neural-networks deep-learning deep-neural-networks jupyter-notebook keras python python3
Last synced: 22 days ago
JSON representation
Classifier can detect 88 celebrities with accuracy of 50%
- Host: GitHub
- URL: https://github.com/ducthienbui97/celebrity-faces-classifier
- Owner: ducthienbui97
- License: mit
- Created: 2017-07-18T16:38:16.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2017-07-19T07:44:12.000Z (almost 8 years ago)
- Last Synced: 2025-02-09T20:47:21.734Z (3 months ago)
- Topics: classification, classifier, cntk, convolutional-neural-networks, deep-learning, deep-neural-networks, jupyter-notebook, keras, python, python3
- Language: Jupyter Notebook
- Homepage:
- Size: 22.5 MB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Celebrity Faces Classifier
I use keras with CNTK back end to train a model class 88 celebrities with the data from [Microsoft](https://www.microsoft.com/en-us/research/project/msra-cfw-data-set-of-celebrity-faces-on-the-web/)
Due to a limited computing resources, my model's accuracy is very low ~ 40% - 50%.