0
$\begingroup$

I have a transform-encoder only architecture, which has the following structure:

      Input
        |
        v
     ResNet(-50)
        |
        v
fully-connected (on embedding dimension)
        |
        v
positional-encoding
        |
        v
transformer encoder
        |
        v
Linear layer to alphabet.

I am trying to visualize the self-attention of the encoder layer to check how each input of the attention attends other inputs. (E.g. https://github.com/jessevig/bertviz)

Where I encounter difficulty is in how I can visualize these activations in terms of the original input of the ResNet and not its output, in order to make my model visually interpretable.

Do you have any ideas or suggestions?

$\endgroup$
2
  • $\begingroup$ Hello. Is this just a programming issue or are you asking to conceptually solve your problem? This is not clear from your post. $\endgroup$
    – nbro
    Jun 1 at 9:05
  • $\begingroup$ My question is conceptual but I plan to implement it. $\endgroup$
    – John Sig
    Jun 1 at 14:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.