Fast Neural Style for Image Style Transform by Pytorch
This is famous Fast Neural Style of Paper Perceptual Losses for Real-Time Style Transfer and Super-Resolution of Feifei Li.
Style Image | Origin Image | Generated Image |
---|---|---|
I Strongly Recommend you to download coco80k 2014 dataset from coco80k 2014 (This is also used by the original paper)
You can use your own huge image dataset as well
put dataset under ./dataset, the folder will looks like
dataset
--train2014
--put_coco_train_here
train
python train.py -h
test
python go.py -h