xiaoxue_admin
/
supervision
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add: prompt engineering tip for deepseek-vl2

This commit is contained in:
soumik12345 2025-07-24 14:23:24 +05:30
parent cc1525707a
commit da70389546
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
supervision/detection/core.py
View File

@ -831,6 +831,7 @@ class Detections:
| Google Gemini 2.0 | `GOOGLE_GEMINI_2_0` | detection | `resolution_wh` | `classes` |
| Google Gemini 2.5 | `GOOGLE_GEMINI_2_5` | detection, segmentation | `resolution_wh` | `classes` |
| Moondream | `MOONDREAM` | detection | `resolution_wh` | |
| DeepSeek-VL2 | `DEEPSEEK_VL_2` | detection | `resolution_wh` | `classes` |
Args:
lmm (Union[LMM, str]): The type of LMM (Large Multimodal Model) to use.
@ -1457,6 +1458,24 @@ class Detections:
!!! example "DeepSeek-VL2"
??? tip "Prompt engineering"
To get the best results from DeepSeek-VL2, use optimized prompts that leverage
its object detection and visual grounding capabilities effectively.
**For general object detection, use the following user prompt:**
```
<image>\\n<|ref|>The giraffe at the front<|/ref|>
```
**For visual grounding, use the following user prompt:**
```
<image>\\n<|grounding|>Detect the giraffes
```
```python
from PIL import Image
import supervision as sv