You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-4Lines changed: 1 addition & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,10 +8,6 @@ We kicked off the project in February/March 2025 and aim to have the work delive
8
8
9
9
#### _BTW: this tool is an experimental project, is not intended to be used yet by the general user/mapper to update OSM_
10
10
11
-
## Demo
12
-
13
-
Try it [here](https://hotosm.github.io/osm-tagger/)
14
-
15
11
## Setup & run
16
12
17
13
### Model (local)
@@ -169,3 +165,4 @@ For persisting the data, media can be uploaded to a S3 bucket and the map’s Ge
169
165
OSMTagger API should receive a request with an image URL, geo-location and category, and return OSM valid tags. The category will help the API to decide a prompt and maybe other configurations.
170
166
171
167
Two models will be used, one focused on extracting text from an image and the other for generating OSM tags from the text. This will divide the problem in two and provide more flexibility for the final solution.
0 commit comments