Bo Miao

Error when handling input image with 480x854 resolution

4

Hi, I try to use Lite-HRNet on some videos with 480x854 resolution. But the following part has a size mismatch error (at row ~630). Following are the code and log...

Hi, Thank you for your great work. In table 5, the cross attention computing time is reduced significantly. May I know did you consider the computing time of optical flow...

Inference on YouTube-VOS dataset

3

Hi, May I know how you test on YouTube-VOS since some new objects are added in middle frames in that dataset? In that case, I am confused about how to...

Hi, There are two columns for each result, ie., "pretrain" and "model". The model denotes the final weights after pretraining and main training. May I know what "pretrain" mean? Does...