Implementation of Centroid Triplet Loss Function

[Spinachboul]

Hello Developers,

I have added the code for Centroid Triplet Loss function as an added implementation in the "Loss" folder.
I follows the basic code template, just contains a few changes in the forward function where the The Centroid Triplet Loss aims to learn embeddings (vectors) in such a way that distances between centroids belonging to the same group or cluster are minimized while distances between centroids of different groups are maximized.

[netlify]

❌ Deploy Preview for capable-unicorn-d5e336 failed.

Name	Link
🔨 Latest commit	a8a91a4
🔍 Latest deploy log	https://app.netlify.com/sites/capable-unicorn-d5e336/deploys/656c5ce9a20da6000884618b

[netlify]

❌ Deploy Preview for capable-unicorn-d5e336 failed.

Name	Link
🔨 Latest commit	9004633
🔍 Latest deploy log	https://app.netlify.com/sites/capable-unicorn-d5e336/deploys/656c5cf3af47640008d48597

[Spinachboul]

Just the code indentation is slightly shifted , no change in the logic!

[HanClinto]

Looks like the build is failing due to formatting issues:

5:51:06 AM: /opt/buildhome/python3.8/lib/python3.8/site-packages/quaterion/loss/cos_face_loss.py:docstring of quaterion.loss.cos_face_loss.CosFaceLoss.forward:3: ERROR: Unexpected indentation.
5:51:06 AM: /opt/buildhome/python3.8/lib/python3.8/site-packages/quaterion/loss/cos_face_loss.py:docstring of quaterion.loss.cos_face_loss.CosFaceLoss.forward:4: WARNING: Block quote ends without a blank line; unexpected unindent.
5:51:06 AM: /opt/build/repo/docs/source/tutorials/triplet_loss_trick.rst:2: WARNING: Title underline too short.
5:51:06 AM: Triplet Loss: Vector Collapse Prevention
5:51:06 AM: ============================

[Spinachboul]

@HanClinto
So should I again raise a PR for the function?

[HanClinto]

@HanClinto So should I again raise a PR for the function?

I can't speak for the maintainers of Quaternion, but Centroid Triplet Loss looks like a very useful function to have -- I would personally be interested in trying it out!

[Spinachboul]

For now I have deleted the branch. I also thought of implementing n-pair which is apparently better than contrastive and triplet loss.