Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neka-nat/image_completion_tf2
"Globally and Locally Consistent Image Completion" with Tensorflow2 Keras
https://github.com/neka-nat/image_completion_tf2
deep-learning gan image-completion keras tensorflow tensorflow2
Last synced: 2 months ago
JSON representation
"Globally and Locally Consistent Image Completion" with Tensorflow2 Keras
- Host: GitHub
- URL: https://github.com/neka-nat/image_completion_tf2
- Owner: neka-nat
- Created: 2018-01-08T17:13:48.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-10-17T16:05:56.000Z (about 5 years ago)
- Last Synced: 2024-10-14T19:42:55.621Z (3 months ago)
- Topics: deep-learning, gan, image-completion, keras, tensorflow, tensorflow2
- Language: Python
- Homepage:
- Size: 364 KB
- Stars: 31
- Watchers: 6
- Forks: 11
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Globally and Locally Consistent Image Completion
This is a Tensorflow2 Keras implementation of ["Globally and Locally Consistent Image Completion"](http://hi.cs.waseda.ac.jp/%7Eiizuka/projects/completion/data/completion_sig2017.pdf).
## Install python libraries
```
pip install pipenv
cd image_completion_keras
pipenv install
```
## Prepare dataset
Please download appropriate image dataset and put it under the "data" folder and "test" folder.
For example, please put the images as follows.
```
data
└── place365
├── Places365_00000001.jpg
├── Places365_00000002.jpg
├── Places365_00000003.jpg
├── Places365_00000004.jpg
├── Places365_00000005.jpg
├── Places365_00000006.jpg
├── Places365_00000007.jpg
├── Places365_00000008.jpg
...
test
└── place365_test
├── Places365_test_00000001.jpg
├── Places365_test_00000002.jpg
├── Places365_test_00000003.jpg
├── Places365_test_00000004.jpg
├── Places365_test_00000005.jpg
├── Places365_test_00000006.jpg
├── Places365_test_00000007.jpg
├── Places365_test_00000008.jpg
...
```
## Train
```
pipenv shell
python train.py
```
## Test
```
pipenv shell
python test.py
```
## Result
