ID: 5dc1f4d119ef63725087b9d6

FastPhotostyle

by Raj Kumar

Fast Neural Style transfer GAN


License: Common Development and Distribution License

Tags: GANS Neural Style Transfer Fast Photostyle Pytoch

 Model stats and performance
Dataset Used MS COCO
Framework PyTorch
OS Used Linux
Publication View
Post Processing Time

Screenshots


FAST PHOTO STYLE

WHAT IS IT?

GAN for neural style transfer.Photorealistic image stylization aims at changing style of a photo to that of a reference photo.The layers from conv1 1 to conv4 1 in the VGG-19 network [34] for the encoder E is used. The encoder weights are given by ImageNet-pretrained weights and the decoder D is the inverse of the encoder. The decoder runs by minimizing the sum of the L2 reconstruction loss and perceptual loss using the Microsoft COCO dataset. We adopt the multi-level stylization strategy proposed in the WCT where we apply the PhotoWCT to VGG features in different layers.

HOW TO USE?

Place input images in images folder

For help, python run.py --output_image_path results/example1_fast.png

ARGUMENTS DETAILS HELP OPTIONS
--output_image_path OUTPUT Mention the output image path

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt

Author View Profile

Raj Kumar
New Delhi, India.
Gold
20
LEVEL

6614 Profile
Views

I love coding

User Reviews



0 total ratings

Model has not been reviewed yet.

More by this user | Show All



Also checkout...