quoccuongle/Grounded-SAM-2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add docs for multi class detection using Florence-2 open-vocab func

Browse Source
This commit is contained in:
rentainhe
2024-08-20 14:15:37 +08:00
parent da69bf587e
commit a67a213e90
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -298,8 +298,10 @@ python grounded_sam2_florence2_image_demo.py \
python grounded_sam2_florence2_image_demo.py \ python grounded_sam2_florence2_image_demo.py \
--pipeline open_vocabulary_detection_segmentation \ --pipeline open_vocabulary_detection_segmentation \
--image_path ./notebooks/images/cars.jpg \ --image_path ./notebooks/images/cars.jpg \
--text_input "two cars" --text_input "car <and> building"
``` ```
- Note that if you want to detect multi-objects you should split them with `<and>` in your input text.
### Grounded SAM 2 Florence-2 Image Auto-Labeling Demo ### Grounded SAM 2 Florence-2 Image Auto-Labeling Demo
`Florence-2` can be used as a auto image annotator by cascading its caption capability with its grounding capability. `Florence-2` can be used as a auto image annotator by cascading its caption capability with its grounding capability.