Tianlong Ai
Tianlong Ai
please running `!mim install mmcv` to install latest version of mmcv.
It seems that the issue has been fixed in the latest version. Please update your mmseg to the latest version.
加入 TODO List，需要更多的社区同学参与进来。哎。。。
> 一种可能的解决方案是在 conda 环境中安装，然后打包 conda 环境以进行离线部署。 Yeah，Liike this https://github.com/AI-Tianlong/Useful-Tools/blob/main/docs/Conda%E7%9B%B8%E5%85%B3%E9%97%AE%E9%A2%98.md#conda-%E6%89%93%E5%8C%85%E7%8E%AF%E5%A2%83%E4%B8%BAtargz-%E5%B9%B6%E8%A7%A3%E5%8E%8B
I guass u could rewrite `LoadImageFromFile` and `LoadAnnotations`
So you mean, in predict, seg_logits = (0,1)? Or is the final mask {0,1} of these two classes?
You can change your dataset configs ```suggestion train_pipeline = [ dict(type=LoadSingleRSImagFromFile) ``` more details about `LoadSingleRSImagFromFile` in, https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/mmseg/datasets/transforms/loading.py#L503-L556
> > Contributor > > How is this different than using `imdecode_backend=tifffile` in the 'LoadAnnotation' or 'LoadImageFromFile' transformations? I'm not sure whether backends `tifffile` support, but if you want to...
> > You can change your dataset configs > > ``` > > train_pipeline = [ > > dict(type=LoadSingleRSImagFromFile) > > ``` > > > > > > > >...
https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/advanced_guides/evaluation.md#ioumetric Is this useful to you?