https://github.com/yeonghyeon/context-encoder
TensorFlow implementation of "Context Encoders: Feature Learning by Inpainting" with CelebAMask-HQ Dataset.
https://github.com/yeonghyeon/context-encoder
auto-encoder autoencoder celeba celeba-hq celeba-hq-dataset context-encoder context-encoders image-inpainting
Last synced: about 1 month ago
JSON representation
TensorFlow implementation of "Context Encoders: Feature Learning by Inpainting" with CelebAMask-HQ Dataset.
- Host: GitHub
- URL: https://github.com/yeonghyeon/context-encoder
- Owner: YeongHyeon
- License: mit
- Created: 2020-06-29T05:24:24.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2021-04-02T07:41:34.000Z (over 4 years ago)
- Last Synced: 2025-08-22T02:42:46.324Z (about 2 months ago)
- Topics: auto-encoder, autoencoder, celeba, celeba-hq, celeba-hq-dataset, context-encoder, context-encoders, image-inpainting
- Language: Python
- Homepage:
- Size: 141 MB
- Stars: 7
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Context Encoders: Feature Learning by Inpainting
=====
TensorFlow implementation of "Context Encoders: Feature Learning by Inpainting" with CelebAMask-HQ Dataset.
## Concept
The concept of 'Context Encoders' [1].
## Usage
### Training
In this repository, 'Context Encoders' is trained with 'CelebA' Dataset [2].
The 'Context Encoders' consumes about 42 hours for training.
### Test
The 'Context Encoders' consumes 0.029 seconds for each sample in inference.
The results of 'Context Encoders' [1].
## Environment
* Python 3.7.4
* Tensorflow 1.14.0
* Numpy 1.17.1
* Matplotlib 3.1.1
* Scikit Learn (sklearn) 0.21.3
## Reference
[1] Deepak Pathak, et al. (2016). Context Encoders: Feature Learning by Inpainting. arXiv preprint arXiv:1604.07379.
[2] CelebA. http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
[3] CelebAMask-HQ Dataset. https://github.com/switchablenorms/CelebAMask-HQ