Train model without LFT?

hytseng0509 / CrossDomainFewShot

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation (ICLR 2020 spotlight)

329 stars 62 forks source link

Train model without LFT? #15

Open lbd08 opened 4 years ago

lbd08 commented 4 years ago

Hi, thanks for sharing your code. Can you share how to train the model without LFT?

hytseng0509 commented 4 years ago

You can use the code here to create the model, and use train_baseline.py to train the model without updating the parameters in the feature-wise transformation layers.