Task
Zero Shot Object Detection
O
google/owlv2-base-patch16-ensemble
Zero Shot Object Detection·google· 1.4M· 124
transformers
apache-2.0
155.0M params
arxiv:2306.09683license:apache-2.0region:us
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned object detection model that can be used to query an image with one or multiple text queries.
# pull & run locally
pip install mlforge-sdk && mlforge pull google/owlv2-base-patch16-ensemble
pip install mlforge-sdk && mlforge pull google/owlv2-base-patch16-ensemble
Model details
Provider
google
Framework
transformers
Parameters
155.0M
Size
1.2 GB
License
apache-2.0
Downloads
1.4M
Likes
124
Paper
arXiv:2306.09683
Updated
2024-10-31
About google/owlv2-base-patch16-ensemble
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned object detection model that can be used to query an image with one or multiple text queries.