ThinResNet34

[gancx]

Thanks for your open-source code. I found that your ThinResNet34 implementation is different from that in your paper. I wonder if you have a revised version.

[gancx]

Also, in the original paper, I didn't notice that the SE block exists in the whole architecture.

[theolepage]

Hello,

Indeed, the implementation of the Thin ResNet-34 encoder from "Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification" is different from the one used in "Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning" (current state of this repository).

I am going to update the repository shortly.

Thanks.