4F2E4A2E

This is a quite interesting PR, thank you, for that. For me, it is unclear why exactly the CI [1] is failing. Do you need a hand investigating that? 1:...

It would be great to have such mechanism, we are filtering every property already. We've checked that with superagent but it is still very slow. Thank you a lot for...

@ASBaj why did you reopen?

So, python 2.7 only for this script? Not working with python 3.6: > the error was encountered with number of clusters > 3, everything from 3 and below works fine.

thanks @Jumabek! Just to be sure and for better comprehension, why are there set [5 anchors on line 246](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.cfg#L246) when on [Line 242 10 Anchors](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.cfg#L242) are being used? Edit: got...

Can you please explain on how it would depend on the object?

Please elaborate, could any network know any difference besides the information given by the semantic segmentation labeling?

Exactly, that's my honest opinion too, but my question is, how to train _with_ the segmented ground truth data?

This one? https://arxiv.org/pdf/1601.05150.pdf

```yaml # This file is auto generated from it's template, # see citusdata/tools/packaging_automation/templates/docker/latest/docker-compose.tmpl.yml. version: "3" services: master: image: "citusdata/citus:10.2.3" ports: ["${COORDINATOR_EXTERNAL_PORT:-5432}:5432"] labels: ["com.citusdata.role=Master"] environment: &AUTH POSTGRES_USER: "${POSTGRES_USER:-postgres}" POSTGRES_PASSWORD: "${POSTGRES_PASSWORD}" PGUSER:...