Precomputed features

Open gadermayr opened this issue 3 years ago • 4 comments

I have a question regarding the precomputed features (Camelion/TCGA) which can be downloaded (e.g. $ python download.py --dataset=tcga).

Where these features generated with a ResNet trained on image-net, or based on self supervised training (simclr)? Are the features for the other case also available in the precomputed form?

Thank you very much!

Mar 28 '23 12:03 gadermayr

Those are based on self-supervised training.

Apr 06 '23 13:04 binli123

Thank you very much for the information!

Apr 18 '23 13:04 gadermayr

thank you! And are these features multi scale or single scale for Camelion?

Aug 08 '23 14:08 jan-engelmann

found the answer here: https://github.com/binli123/dsmil-wsi/issues/50

Aug 08 '23 14:08 jan-engelmann