search

TACJu / TransFG

This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).
MIT License
382 stars 88 forks source link

About train.py #9

Open Christine620 opened 3 years ago

Christine620 commented 3 years ago

I found you write scheduler.step() before optimizer.step() in line 267-268 in train.py, when I run it,i got a UserWarning UserWarning: Seems like optimizer.step() has been overridden after learning rate scheduler initialization. Please, make sure to call optimizer.step() before lr_scheduler.step().,so is your code right on that place ?

cwq63 commented 3 years ago

I also use that,but it didn't report an UserWarning like this.