Done Converted semantic seg to instance seg

Author: Youssef-Harby

README.md

@@ -30,4 +30,5 @@ git clone git@github.com:deepbands/deep-learning-datasets-maker.git
 
 - [ ] Fix: If vector layer saved in memory not in file, `rasterize` can't work.
 - [X] Fix: Splitiing Image Size.
-- [ ] Converted semantic segmentation (0 and 1) to instance segmentation for labels (the original label is 0/255) option, and the result is a single-channel image that uses a palette to color. ![](https://s3.bmp.ovh/imgs/2021/09/008c5b768b7e477a.png)
+- [X] Converted semantic segmentation (0 and 1) to instance segmentation for labels (the original label is 0/255) option, and the result is a single-channel image that uses a palette to color. ![](https://s3.bmp.ovh/imgs/2021/09/008c5b768b7e477a.png)
+- [ ] PaddlePaddle Train/Val/Testing list text.

deep-learning-datasets-maker/split_rs_data.py

@@ -306,6 +306,6 @@ def run(self):
                     saver = osp.join(save_path, name)
                     segMaskB2I(label, saver)
             else :
-                feedback.pushInfo(str(save_path))
+                feedback.pushInfo("Option instance segmentation is not selected")
 
             iface.messageBar().pushMessage("You will find the dataset in " + image_folder_path, level=Qgis.Success, duration=5)