We have released a sample of 1000 images per dataset, and we will provide access to all datasets and code (which are already included in this submission) once the paper is accepted.
Download link: https://sandbox.zenodo.org/record/1153424#.Y9dALnZByw4
Additionally, we offer an auto-downloader to simplify the process of downloading each image and make them permanently available. To initiate the download process, run the NineRec_downloader.exe
file. Currently, the auto-downloader is only compatible with Windows systems, but we will provide a Linux version after acceptance.
Pytorch==1.12.1
cudatoolkit==11.2.1
sklearn==1.2.0
python==3.9.12
Run get_lmdb.py
to get lmdb database for image loading. Run get_behaviour.py
to convert the user-item pairs into item sequences format.
Run train.py
for pre-training and transferring. Run test.py
for testing.
coming soon.