Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/anyesh/sketch-to-anime
https://github.com/anyesh/sketch-to-anime
Last synced: 3 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/anyesh/sketch-to-anime
- Owner: Anyesh
- Created: 2021-02-19T03:13:05.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2022-05-02T08:49:28.000Z (over 2 years ago)
- Last Synced: 2023-02-27T23:56:26.712Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 9.71 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Sketch2Color-anime-translation:
Given a plain anime sketch the model outputs a random colored anime image using Generative Adversarial Networks (GANs).
Implemented the anime sketch colorization using the reference(s) paper-1 below.
- Dataset: [Anime sketch colorization pair](https://www.kaggle.com/ktaebum/anime-sketch-colorization-pair)
References:
[1] https://arxiv.org/abs/1705.01908
[2] https://machinelearningmastery.com
[3] https://github.com/soumith/ganhacks
# Tensorboard logs:
![Tensorboard](./Images/TensorboardLogs.png)
# In progress training results:
**At epoch 30,**
![result_epoch_30](./Images/Epoch30.PNG)
**At epoch 40,**
![result_epoch_40](./Images/Epoch40.PNG)
**At epoch 43,**
![result_epoch_43](./Images/Epoch43.PNG)
# Prediction:
![Sample_1](./Images/TestSample1.PNG)
![Sample_2](./Images/TestSample2.PNG)