tom white

We have a version of BLIP loss this we plan on adding to an upcoming release. So far in our testing the BLIP guided loss works but doesn't "outperform" CLIP...

Thanks for the feedback! Glad to work on this a bit more with you if you are interested. In response to your questions: 1) This current version uses ITM only...

I made a standalone utility to do this - it can run inference on any of their three pre-trained models given an input sequence of image files. You can find...

I like the idea of supporting this feature exactly as proposed (owner=tzXXX) in the context of 1/1 OBJKTs where there is always a single owner to any particular token.

Thanks heaps @mrapplexz - this is indeed working well for me. So far I'm surprised how powerful even 100 iterations of fine tuning is (I'll probably tweak the learning rate...

(this has been updated to be compatible with the now merged 0.2 branch)

I am willing to make this compatible with 0.3, but am going to wait until there is some feedback indicating this is a desired feature in the main release.

OK, without pulling my punches here are my thoughts: - the hidden power of this library is that it can potentially learn to map between any two image datasets, thought...

I ended up not taking this route but instead adapted the dataset to be classes (positive / negative). I did find a more detailed read of issues trying to use...

Here's the `vggface2_class_index.json` to support this new function. This file could eventually replace the need for `rcmalli_vggface_labels_v2.npy` (it contains the same label information but also includes class-ids) and is in...