Skip to content

Latest commit

 

History

History
110 lines (89 loc) · 2.54 KB

File metadata and controls

110 lines (89 loc) · 2.54 KB

NST

This is the implementation of "Neural Style Transfer".
Original paper: L. A. Gatys, A. S. Ecker, and M. Bethge. Image Style Transfer Using Convolutional Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. link

Usage

0. Download pre-trained model

Please download VGG19 pre-trained model with ImageNet.

$ wget https://huggingface.co/koba-jon/pre-train_cpp/resolve/main/models/vgg19_bn.pth

1. Build

Please build the source file according to the procedure.

$ mkdir build
$ cd build
$ cmake ..
$ make -j4
$ cd ..

2. Dataset Setting

Setting

The following hierarchical relationships are recommended.

datasets
|--Dataset1
|    |--content.png
|    |--style.png
|
|--Dataset2
|--Dataset3

3. Image Generation

Example 1

Setting

Please set the shell for executable file.

$ vi scripts/TheStarryNight.sh

The following is an example of the generation phase.
If you want to view specific examples of command line arguments, please view "src/main.cpp" or add "--help" to the argument.

#!/bin/bash

DATA='TheStarryNight'

./NST \
    --generate true \
    --iterations 1000 \
    --dataset ${DATA} \
    --content "content.png" \
    --style "style.png" \
    --gpu_id 0
Run

Please execute the following to start the program.

$ sh scripts/TheStarryNight.sh

Example 2

Setting

Please set the shell for executable file.

$ vi scripts/TheScream.sh

The following is an example of the generation phase.
If you want to view specific examples of command line arguments, please view "src/main.cpp" or add "--help" to the argument.

#!/bin/bash

DATA='TheScream'

./NST \
    --generate true \
    --iterations 1000 \
    --dataset ${DATA} \
    --content "content.png" \
    --style "style.png" \
    --gpu_id 0
Run

Please execute the following to start the program.

$ sh scripts/TheScream.sh