资源算法Fast Neural Style for Image Style Transform by Pytorch

Fast Neural Style for Image Style Transform by Pytorch

2019-09-10 | |  100 |   0 |   0

FastNeuralStyle by Pytorch

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.

Result

Style Image | Origin Image | Generated Image |:---:|:---:|:---:| wave.jpgnymph.jpg|output_nymph.jpgwave (1).jpgchicago.jpgoutput_chicago.jpg|

How to Run

Train and Test

Training DataSet

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

Configure

put dataset under ./dataset, the folder will looks like

dataset 
 --train2014
 --put_coco_train_here

Run

train 
python train.py -h

test
python go.py -h

Pretrained Model

models are saved in ./model folder by default.

I also release two pretrained model .

wave.model

You can download and put it under ./model folder


上一篇:Unsupervised Object Counting

下一篇:vae_vpflows

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...