Joao P C Bertoldo

(asking this here but i will create a proper issue if necessary) context: `FeatureExtractor` The `__init__` will call `_map_layer_to_idx()` to get the timm-specific indices of the submodules given by the...

i created a sketch of the things i suggested in #564 i only modified `base.py` to be clear about the things i said above feel free to consider it or...

Please ignore for now, I will wait for PR #558. Also, I realize that the pre-loading of data is probably unnecessary so I'll remove it to make the PR simpler.

I'll try if i have time today. Btw tests were failing in my local env. I think it was in the other branch but it wasn't related to my changes....

this was integrated in #576

Shouldn't this one be closed?

Why was this closed?

Ah yes, I confused with #1377 my bad hehe > hope one day it will get accepted inshallah! it's a major upgrade > For this reason we used random istead...

> `np.random` Do you know if there's any issue open in numpy for this issue? I'm not sure because I don't know that much about parallelization, but could there be...

> @jpcbertoldo, @phcarval, @blaz-r , do you guys have any concerns about this pr I'll have sometime to check on wed only 😬