IMPORTANT NOTE
: On Google-Colab
All data files and dependencies can be installed by running the uppermost cell of the notebook! See Usage
!
- Pre-trained VGG19 network weights - put it in
models/
directory - torchvision -
torchvision.models
contains the VGG19 model skeleton
You will be running the notebook in Google Colab! Colab is a cloud service with an interface similar to Jupyter notebook. It allows you to get an accelerator, such as a GPU, for Free!
Uncomment and run the first cell to download the demo pictures, and VGG19 weights. It will also install the dependencies (i.e. PyTorch and torchvision).
# Download VGG19 Model
!wget -c https://s3-us-west-2.amazonaws.com/jcjohns-models/vgg19-d01eb7cb.pth
!mkdir models
!cp vgg19-d01eb7cb.pth models/
# Download Images
!wget -c https://github.com/ofirbb/spectrum-workshop/archive/master.zip
!unzip -q master.zip
!mkdir images
!cp neural-style-pytorch-master/images/1-content.png images
!cp neural-style-pytorch-master/images/1-style.jpg images
MAX_IMAGE_SIZE
: sets the max dimension of height or weight. Bigger GPU memory is needed to run larger images. Default is512
px.INIT_IMAGE
: sets the initial image file to either'random'
or'content'
. Default israndom
which initializes a noise image. Content copies a resized content image, giving free optimization of content loss!CONTENT_PATH
: path of the content imageSTYLE_PATH
: path of the style imagePRESERVE_COLOR
: determines whether to preserve the color of the content image.True
preserves the color of the content image. Default value isFalse
PIXEL_CLIP
: determines whether to clip the resulting image.True
clips the pixel values to [0, 255]. Default value isTrue
OPTIMIZER
: sets the optimizer to either 'adam' or 'lbfgs'. Default optimizer isAdam
with learning rate of 10. L-BFGS was used in the original (matlab) implementation of the reference paper.ADAM_LR
: learning rate of the adam optimizer. Default is1e1
CONTENT_WEIGHT
: Multiplier weight of the loss between content representations and the generated image. Default is5e0
STYLE_WEIGHT
: Multiplier weight of the loss between style representations and the generated image. Default is1e2
TV_WEIGHT
: Multiplier weight of the Total Variation Denoising. Default is1e-3
NUM_ITER
: Iterations of the style transfer. Default is500
SHOW_ITER
: Number of iterations before showing and saving the generated image. Default is100
VGG19_PATH
= path of VGG19 Pretrained weights. Default is'models/vgg19-d01eb7cb.pth'
POOL
: Defines which pooling layer to use. The reference paper suggests using average pooling! Default is'max'
An implementation of the neural style in PyTorch! This notebook implements Image Style Transfer Using Convolutional Neural Networks by Leon Gatys, Alexander Ecker, and Matthias Bethge. Color preservation/Color transfer is based on the 2nd approach of discussed in Preserving Color in Neural Artistic Style Transfer by Leon Gatys, Matthias Betge, Aaron Hertzmann, and Eli Schetman.
This implementation is a slight adaptation of the code by Rusty.
The original caffe pretrained weights of VGG19 were used for this implementation, instead of the pretrained VGG19's in PyTorch's model zoo.