A implementation of Artistic Style with TensorFlow
MIT License
Everyone_Is_Van_Gogh is a tensorflow implementation of style transfer which described in the next paper:
And I use VGG19 which was proposed in this paper:
To use the VGG19 networks, you have to download the npy files for VGG19 NPY from here.
git clone [email protected]:hualin95/Everyone_Is_Van_Gogh.git
cd Everyone_Is_Van_Gogh
python train.py --VGG19_Model_Path [your filepath of vgg19.npy] --content_image [your filepath of content_image] --style_image [your filepath of style_image]
For example (I have move the file vgg19.npy to the folder Everyone_Is_Van_Gogh):
python train.py --VGG19_Model_Path "vgg19.npy" --content_image "images/content/johannesburg.jpg" --style_image "images/style/starry-night.jpg"
More : I guess you want to train the project with GPU if you have one, so you can run the file train.py like this:
CUDA_VISIBLE_DEVICES=[GPU_num] python train.py --VGG19_Model_Path [your filepath of vgg19.npy] --content_image [your filepath of content_image] --style_image [your filepath of style_image]
For example :
CUDA_VISIBLE_DEVICES=4 python train.py --VGG19_Model_Path "vgg19.npy" --content_image "images/content/johannesburg.jpg" --style_image "images/style/starry-night.jpg"
The Starry Night is an oil on canvas by the Dutch post-impressionist painter Vincent van Gogh in June 1889.
This is picture of University of Chinese Academy of Sciences where I am studying now and finish this project.