itsabouttime
Code repository for "It's About Time: Analog clock Reading in the Wild"
C. Yang, W. Xie, A. Zisserman
https://charigyang.github.io/abouttime/
Code will arrive in no time (ETA: later this month).
Category: Python / Deep Learning |
Watchers: 7 |
Star: 15 |
Fork: 0 |
Last update: Nov 21, 2021 |
Code repository for "It's About Time: Analog clock Reading in the Wild"
C. Yang, W. Xie, A. Zisserman
https://charigyang.github.io/abouttime/
Code will arrive in no time (ETA: later this month).
Hi, thank you for your amazing work. I am inspired by your work about alignment the clock. I have tried to use STN for alignment my pointer meter as followings. I picked front meter of each category as a standard meter. And online random homography matrix was generated by code to apply on these standard meters for training STN. My batchsize is 32, and iteration about 120000, trian data is 10000, but the results is not good, and the loss is about 0.5 finally. Could you give my some advice about this task?
Thanks very much.
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
Dear authors,
Thanks for this wonderful work! Could you please let me know your training time (e.g. at how many GPUS) and the total epoch number? Did you set an early stop scheme?
Thanks for sharing the excellent job! In achieving STN, instead of the pytorch tutorials of STN, the codes adopt "kornia.geometry.transform.warp_perspective" to generate new images. I wonder why kornia is adopted, and the differences between the methods.