Repository files navigation

conda env create -n SSDA.yml

The code is written for Pytorch 0.4.0, but should work for other versionwith some modifications.

Download the cleaned version of the domainnet data fromhere and place them inside the './data/multi/' folder.

The images will be stored in the following way.

./data/multi/real/category_name,

./data/multi/sketch/category_name

The dataset split files are stored as follows,

./data/txt/multi/labeled_source_images_real.txt,

./data/txt/multi/unlabeled_target_images_sketch_3.txt,

With regard to office and office home dataset, store the image files in the following ways,

./data/office/amazon/category_name,./data/office_home/Real/category_name,

We provide the split of office and office-home.

To run training using alexnet,

sh run_train.sh gpu_id method alexnet

where, gpu_id = 0,1,2,3...., method=[MME,ENT,S+T].