Flow-Style-VTON
Flow-Style-VTON copied to clipboard
learning rate
How come ResUnetGenerator doesn't have a method update_learning_rate?
Last 3 rows of code in train_PBAFN_e2e_fs.py :

Why are we updating model (the warping model) twice ? Shouldn't model.module.update_learning_rate(optimizer_gen) be something like model_gen.module.update_learning_rate(optimizer_gen) ?