Command line¶
stylish¶
Style transfer using deep neural network
stylish [OPTIONS] COMMAND [ARGS]...
Options
-
--version¶ Show the version and exit.
-
-v,--verbosity<verbosity>¶ Set the logging output verbosity. [default: info]
Options: debug|info|warning|error
apply¶
Apply a style generator model to an image.
stylish apply [OPTIONS]
Options
-
--model<model>¶ Path to trained style generator model which will be used to apply the style. [required]
-
-i,--input<input>¶ Path to image to transform. [required]
-
-o,--output<output>¶ Path to folder in which the transformed image will be saved. [required]
download¶
Download necessary elements to train a style generator model
Example:
stylish download vgg19 stylish download coco2014 -o /tmp
stylish download [OPTIONS] COMMAND1 [ARGS]... [COMMAND2 [ARGS]...]...
train¶
Train a style generator model.
stylish train [OPTIONS]
Options
-
--vgg<vgg>¶ Path to Vgg19 pre-trained model in the MatConvNet data format.
-
-s,--style<style>¶ Path to image from which the style features will be extracted.
-
-t,--training<training>¶ Path to a training dataset folder (e.g. COCO 2014).
-
--limit<limit>¶ Maximum number of files to use from the training dataset folder.
-
-l,--learning-rate<learning_rate>¶ Learning rate for optimizer. [default: 0.001]
-
-b,--batch-size<batch_size>¶ Batch size for training. [default: 4]
-
-e,--epochs<epochs>¶ Epochs to train for. [default: 2]
-
-C,--content-weight<content_weight>¶ Weight of content in loss function. [default: 7.5]
-
-S,--style-weight<style_weight>¶ Weight of style in loss function. [default: 100.0]
-
-T,--tv-weight<tv_weight>¶ Weight of total variation term in loss function. [default: 200.0]
-
-L,--layer-weights<layer_weights>¶ Weights of layers used for style features extraction. [default: 1.0, 1.0, 1.0, 1.0, 1.0]
-
-o,--output<output>¶ Path to folder in which the trained model will be saved.