Implementation of "Deep Feature Interpolation for Image Content Changes"(https://arxiv.org/abs/1611.05507) using Chainer.

• Python 2.7
• Chainer 1.16.0
• Pillow 3.1.0

Download VGG_ILSVRC_19_layers.caffemodel from https://gist.github.com/ksimonyan/3785162f95cd2d5fee77.

$ python src/create_chainer_model.py

• Download "All images aligned with deep funneling"(lfw-deepfunneled.tgz) from LFW web site
• Download "LFW attributes file"(lfw_attributes.txt) from the same site.
• Extract tgz file.

Example:

python src/train_lfw.py lfw-deepfunneled lfw_attributes.txt "Silvio Berlusconi" 23 smiling image/lfw_out.jpg -g 0

person name: "Silvio Berlusconi"
image number: 23

Original	Weight: 0.1	Weight: 0.2	Weight: 0.3	Weight: 0.4	Weight: 0.5

Original	Weight: 0.1	Weight: 0.2	Weight: 0.3	Weight: 0.4	Weight: 0.5

• Download img_align_celeba.zip and list_attr_celeba.txt from CelebA Dataset web site.
• Extract zip file.

Example:

$ python src/extract_image.py img_align_celeba list_attr_celeba.txt image_normal.txt image_smile.txt smiling young,bags_under_eyes -e eyeglasses,male,pale_skin,narrow_eyes,bushy_eyebrows,chubby,double_chin,bald,bangs,receding_hairline,sideburns,wavy_hair,blond_hair,gray_hair,mouth_slightly_open

Example:

$ python src/train.py sample/sample.png image/out/out.png image_normal.txt image_smile.txt -g 0 -c 19,39,159,179

Original	Weight: 0.1	Weight: 0.2

Weight: 0.3	Weight: 0.4	Weight: 0.5

• feature φ(x) is not normalized.
• attribute vector w is normalized by w -> ||φ(x)|| * w / ||w|| (||w|| means L2 norm)

MIT License