Why use 'step-start_step' in train_step func

vdvchen / SGMNet

Implementation of "Learning to Match Features with Seeded Graph Matching Network" ICCV2021

MIT License

136 stars 22 forks source link

Open SuhZhang opened 2 years ago

SuhZhang commented 2 years ago

train/train.py, line 87 Why use 'step-start_step'? Should data['step'] be the same as 'step-start_step'?