search

Ackesnal / GTP-ViT

This is the official code for paper: Token Summarisation for Efficient Vision Transformers via Graph-based Token Propagation
Apache License 2.0
25 stars 1 forks source link

no graph structure in the model of the current training code #3

Open xiaridehehe opened 1 month ago

xiaridehehe commented 1 month ago

I debug the code step by step, and there is no graph structure in the model of the current training code. Do I need to build it by myself? I found that the model in the current training code is a VIT-based classification model.

xiaridehehe commented 1 month ago

It has been solved. It turns out that there are three model codes, and the code of graph structure is in models_v3