search

lambert-x / medical_mae

The official implementation of "Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification"
Apache License 2.0
67 stars 15 forks source link

Use the pretrain model as a feature extractor #12

Open lullcant opened 2 months ago

lullcant commented 2 months ago

I'd like to ask if I want to use the pretrain model as a feature extractor, I should load the pretrain model and use the forward_encoder function with the mask ratio = 0.0. Am I right? Thanks