Chaminda Bandara
Chaminda Bandara
Hey, did you download the dataset?
@Minerva-J @lm-ZHAO98 @justchenhao I have uploaded WHU-CD dataset to DropBox and you can download it here: https://www.dropbox.com/sh/aq850z7ouvobzgw/AAAXliu8sad6f29xy8NN5ZWPa?dl=0
@Z-Yh-June Hi, see this repo: https://github.com/wgcban/ChangeFormer
Also this: Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images Paper: [https://arxiv.org/abs/2204.08454](https://arxiv.org/abs/2204.08454) Code: [https://github.com/wgcban/SemiCD](https://github.com/wgcban/SemiCD) Abstract: Remote-sensing (RS) Change Detection (CD) aims to detect "changes of interest" from...
I got following msg with the processed model weights: ` _IncompatibleKeys(missing_keys=['blocks.0.adaptmlp.down_proj.weight', 'blocks.0.adaptmlp.down_proj.bias', 'blocks.0.adaptmlp.up_proj.weight', 'blocks.0.adaptmlp.up_proj.bias', 'blocks.1.adaptmlp.down_proj.weight', 'blocks.1.adaptmlp.down_proj.bias', 'blocks.1.adaptmlp.up_proj.weight', 'blocks.1.adaptmlp.up_proj.bias', 'blocks.2.adaptmlp.down_proj.weight', 'blocks.2.adaptmlp.down_proj.bias', 'blocks.2.adaptmlp.up_proj.weight', 'blocks.2.adaptmlp.up_proj.bias', 'blocks.3.adaptmlp.down_proj.weight', 'blocks.3.adaptmlp.down_proj.bias', 'blocks.3.adaptmlp.up_proj.weight', 'blocks.3.adaptmlp.up_proj.bias', 'blocks.4.adaptmlp.down_proj.weight', 'blocks.4.adaptmlp.down_proj.bias', 'blocks.4.adaptmlp.up_proj.weight', 'blocks.4.adaptmlp.up_proj.bias',...
@ShoufaChen @yangzhen1997 I was also experiencing the same problem. Even though you removed those augmentations and AdamW optimizer, will your method still be able to improve the results? Based on...
@fyoung26 I am not exactly sure what is the reason for lower scores on the Botswana dataset. Let me look into it.
@HaiMaoShiTang Hi, I am not sure about I still have the dataset saved in my machine since I am not continuing right now, but I will check and respond to...
Hi @yisun98 What do you mean by the parameters? Do you mean the band numbers? I referred the original dataset descriptions.
@zha0x Hi, thank you for your question. your evaluation seems correct. once possible reason could be why you are not getting the same result is that, during pre-processing, I have...