If there are raw data for items (original images or texts), rather than extracted features.

[Du-danger]

• I see the google driver and find that there are only img_feats or txt_feats for items. I wonder if there are raw data for items (original images or texts), rather than extracted features.
• Thank you~

[enoche]

Hi, @Du-danger Actually, the raw data can be found at https://jmcauley.ucsd.edu/data/amazon/links.html

And you are free to use other Pre-trained encoders to extract the feature embeddings. Like here: https://github.com/enoche/BM3/issues/9