-
While going through kraken's commits, i noticed that the polygonization is a constant issue. So i think i have a solution for you, why don't you skip the textline detection part.
Recent advancement…
-
@noinia, do you know if such an algorithm exists or if this is impossible or an open problem?
-
sdat2 updated
3 years ago
-
While running inference, it shows error for the below mentioned two trained models, but it works well for inria model. Please help me to resolve this
mapping_dataset.unet_resnet101_pretrained.train…
-
Hi, i saw your paper and got something unclear: when you did the edge segmentation task, were you using dice loss + weighted cross entropy (2 classes: edge and background)? For the weighted BCE, were …
-
hi, may i ask how to calculate the distance to the second nearest building? i'm not quite familiar with that, i know with cv2.distanceTransform we can calculate distance to the nearest building.
-
Could you please tell me the training procedure for Indria dataset from scratch? I have aerial images and corresponding masks in .png format right now.
-
**Problem description**
- What did you do?
I am working on road network analysis tool.
I use OSMnx so as to clean the network topology, and them I pass the data as a geodataframe to shapely so…
-
I just read your [blog post](http://lin-ear-th-inking.blogspot.com/2020/05/jts-overlay-next-generation.html) and am excited to see if this does indeed eliminate dreaded TopologyExceptions!
I'm loo…
-
As described here: https://github.com/mdsumner/spex/issues/11#issuecomment-377487762
Can this work
* obtain quadmesh, convert to edge table
* group by pixel value and visit each group in turn
…