question about fashionbert

Thanks for sharing your code! I have the following questions about fasionbert.

(1) Have you evaluated the performance of fasionbert without pretraining? That is, training a model by removing mlm and mpm only with image-text-matching task. Besides, There are not fine-tuning on downstream task (eg. image-text matching). So why do you call that as pertaining instead of training.

(2) Have you resize the image patch (32*32->224*224) for image feature extraction?

(3) Which backbone network is selected for image feature extraction in your released pertained model? resnet50 or resnext101?

The issue names no files, tests, or entry points. Review the repository's FashionBERT implementation and released pretrained-model details, then verify the three questions about removing MLM/MPM, image resizing, and the image backbone; done means providing supported answers or updating the relevant documentation.

Written by the indexing model from the issue text.