Update supervision/detection/vlm.py

Co-authored-by: Soumik Rakshit <19soumik.rakshit96@gmail.com>
This commit is contained in:
Onuralp SEZERandSoumik Rakshit authored and GitHub committed 2025-07-11 16:49:58 +03:00
1 parent 5d2616093d
commit fd1bb5b4b2
1 file changed
+13 -3
+13 -3
View File
@@ -416,9 +416,19 @@ def from_google_gemini_2_5(
resolution_wh: Tuple[int, int],
) -> Tuple[np.ndarray, np.ndarray, np.ndarray, Optional[np.ndarray]]:
"""
Parse and scale bounding boxes and masks from Google Gemini 2.5 style JSON output.
https://aistudio.google.com/
https://ai.google.dev/gemini-api/docs/vision?lang=python
Parse and scale bounding boxes and masks from Google Gemini 2.5 style
[JSON output](https://ai.google.dev/gemini-api/docs/vision?lang=python).
The JSON is expected to be enclosed in triple backticks with the format:
```json
[
{
"box_2d": [x1, y1, x2, y2],
"mask": "data:image/png;base64,...",
"label": "some class name"},
...
]
```
Args:
result: String containing the JSON snippet enclosed by triple backticks.