Yonghyub Sakong

Thank you for sharing a wonderful code! I want to get segments of specific class from result. Segmentation results have multiple classes, but I only want to see the segmentation...

About num_classes for binary semantic segmentation in loss config

1

I'm still working for binary semantic segmentation that has two classes(background:0 / foreground:1 == building) I have some questions about config of loss. ``` num_classes=2 loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=2.0, reduction='mean',...

Build ISCE2 with CUDA version Error

1

I am currently working on creating stack data for Sentinel-1 data using stackSentinel.py. It was taking too long with just the CPU, so I'm trying to install the CUDA version....

### What's the feature? I want to use nms_rotated with class_agnostic. According to [docs](https://mmcv.readthedocs.io/en/latest/_modules/mmcv/ops/nms.html), while other NMS methods have the class_agnostic option, it is not available for nms_rotated. Do you...

phase_linking stage takes too long

1

I am performing analysis using miaplpy. Attempting to run full-resolution without applying Multi-looking in ISCE2. The configuration used is as follows. If there is a trade-off between accuracy and processing...