Can't reproduce outliers (patch embeddings of very high norm)

#7
by niktheod - opened

Hi. I was trying to reproduce the behaviour mentioned in the paper "Vision Transformers need registers" but I never got a single outlier. I encoded 1000 different images with this model and the norm of all the patch embeddings in the output was constantly < 60. Is this an improved version of the model that has resolved this issue?

Sign up or log in to comment