mb-29 / optimal-textures

Optimal deep texture generation and style transfer based on Eric Risser's paper

Optimal textures

An implementation of the texture generation algorithm proposed in Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport.

Example

Texture generation

python run.py scale.jpg decoder_states/scale/ -n 5 

Style transfer

python run.py scale.jpg -c university.jpg decoder_states/scale/ -n 5 

Usage

• In order to used pre-trained decoder weights, set up a directory containing .pth weight files with the form

Relu1_1_decoder_state.pth
Relu2_1_decoder_state.pth
Relu3_1_decoder_state.pth
Relu4_1_decoder_state.pth
Relu5_1_decoder_state.pth

If you want to train your decoders on your own image instead, this directory will be used to store the generated weights.

• Set layer-specific parameters like the number of epoch and the learning rate for the decoders training phase, as well as iteration parameters in the dictionary observed_layers at the bottom of the file decoders.py.

• Run the generation process with

python run.py path_to_source_image path_to_decoder_states_directory -o output_path -n n_passes [--train]

• Run the style transfer process with

python run.py path_to_source_image path_to_decoder_states_directory -c path_to_content_image -s content_strength -o output_path -n n_passes [--train]

Requirements

• Python 3
• torch

optimal-textures's Issues

code is not complete?

Dear MB-29

I'm very interesting with this "optimal-textures", but it looks the code is not complete?

there is no "utils" module.

could you please complete the code? thanks!

output_value_hook

Traceback (most recent call last):
File "run.py", line 10, in
from style_transfer import StyleTransfer
File "/content/optimal-textures/style_transfer.py", line 5, in
from utils import output_value_hook, sliced_transport, image_preprocessing, vgg_normalization
ImportError: cannot import name 'output_value_hook' from 'utils' (/content/optimal-textures/utils.py)

Bad results

I used the WCT decoder, but the results were bad , like this

Why?

code issue

Relu1_1_decoder_state.pth
Relu2_1_decoder_state.pth
Relu3_1_decoder_state.pth
Relu4_1_decoder_state.pth
Relu5_1_decoder_state.pth
缺失训练权重吗？