adirik/owlvit-base-patch32 🖼️📝🔢✓ → ❓

▶️ 24.4K runs 📅 Oct 2023 ⚙️ Cog 0.8.3 🔗 GitHub 📄 Paper ⚖️ License

About

Zero-shot / open vocabulary object detection

Example Output

Output

{"json_data":{"objects":[{"bbox":[180,71,271,178],"label":"human face","confidence":0.35713595151901245},{"bbox":[1,1,105,509],"label":"star-spangled banner","confidence":0.13790424168109894},{"bbox":[350,-1,468,288],"label":"rocket","confidence":0.2110234647989273},{"bbox":[129,348,206,427],"label":"nasa badge","confidence":0.28099769353866577},{"bbox":[277,338,327,380],"label":"nasa badge","confidence":0.1195005401968956}]},"result_image":"https://replicate.delivery/pbxt/oO5rHoHwsrYGJh5HeElqpBBmjoi1gkXxGofpiQuxMvDNlduRA/result.png"}

Performance Metrics

5.50s Prediction Time

211.20s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/JhlycB8ScNVrMu0ke1Xlg09ajbsmMfp4TK19JXpnYq6GrHK8/astronaut.png",
  "query": "human face, rocket, star-spangled banner, nasa badge",
  "threshold": 0.11,
  "show_visualisation": true
}

Input Parameters

image Type: string: Input image to query
query Type: string: Comma seperated names of the objects to be detected in the image
threshold Type: numberDefault: 0.1Range: 0 - 1: Confidence level for object detection
show_visualisation Type: booleanDefault: true: Draw and visualize bounding boxes on the image

Output Schema

Output

Example Execution Logs

human face, rocket, star-spangled banner, nasa badge True
/root/.pyenv/versions/3.9.18/lib/python3.9/site-packages/transformers/models/owlvit/image_processing_owlvit.py:429: FutureWarning: `post_process` is deprecated and will be removed in v5 of Transformers, please use `post_process_object_detection` instead, with `threshold=0.` for equivalent results.
warnings.warn(

Version Details

Version ID: 5e899f155a1913c4b7304d09082d842ca7fe6cb1f22e066c83eb1d7849dc37c2
Version Created: October 13, 2023

Run on Replicate →