search

charigyang / itsabouttime

Code repository for "It's About Time: Analog clock Reading in the Wild"
MIT License
67 stars 10 forks source link

About train_refine #3

Open Totorol opened 2 years ago

Totorol commented 2 years ago

Thanks for such a great job! I am implementing train_fine and have doubts about the following code: img = torch.cat([img, img2], 0) hour = torch.cat([hour, hour2], 0) minute = torch.cat([minute, minute2], 0) Why overlay data

charigyang commented 2 years ago

Thanks for your interest in our work.

Assuming batch size 32, we concatenate both pre-STN and post-STN images (so effective batch size 64), and train on both. This makes training a bit harder as the recognition model has to also be able to read the clock with and without STN.

I don't think the results will be different without it, or if so, very minor.