PAMA

​ This is the Pytorch implementation of Progressive Attentional Manifold Alignment.

Requirements

• python 3.6
• pytorch 1.2.0+
• PIL, numpy, matplotlib

Checkpoints

Please download the pre-trained checkpoints at google drive and put them in ./checkpoints.

Here we also provide some other pre-trained results with different loss weights:

The checkpionts will be uploaded recently.

Training

The training set consists of two parts, the content images from COCO2014 and style images from Wikiart.

python main.py train --lr 1e-4 --content_folder ./COCO2014 --style_folder ./Wikiart

Testing

To test the code, you need to specify the path of the content image and the style image.

python main.py eval --content ./content/1.jpg --style ./style/1.jpg

If you want to do a batch operation for all pictures under the folder at one time, please execute the following code.

python main.py eval --run_folder True --content ./content/ --style ./style/

Results Presentation

​ The results prove the quality of PAMA from three dimensions: Regional Consistency, Content Proservation, Style Quality.

Regional Consistency

Content preservation

Style Quality

Other Results