search

vvvb-github / AVSegFormer

[AAAI 2024] AVSegFormer: Audio-Visual Segmentation with Transformer
https://arxiv.org/abs/2307.01146
52 stars 4 forks source link

Question about the img_size？ #3

Closed yannqi closed 6 months ago

yannqi commented 10 months ago

I found your paper said that your img_size is 224x224, however, in your code, the img_size is 512, which one is right？https://github.com/vvvb-github/AVSegFormer/blob/master/dataloader/s4_dataset.py

CleyLyChen commented 6 months ago

hi, @yannqi, the author note the img_size=512 as AVSegFormer-PVTv2* in their AAAI 2024 paper, Here is the table: image

CleyLyChen commented 6 months ago

hi, @yannqi, the author note the img_size=512 as AVSegFormer-PVTv2* in their AAAI 2024 paper, Here is the table: image

yannqi commented 6 months ago

I noticed the change of the arixv. Thanks for your reply!