metadata
library_name: kerasformers
pipeline_tag: zero-shot-object-detection
license: apache-2.0
tags:
- keras
- kerasformers
- grounding-dino
- tf
- jax
- pytorch
grounding_dino_tiny
Grounding DINO performs open-set, text-grounded object detection: a Swin backbone and a BERT text encoder feed a cross-modality transformer that grounds free-form text prompts to boxes.
Pure-Keras 3 model in kerasformers. The repo is self-describing: kf_config.json holds the architecture and tokenizer.json the text tokenizer, so it loads by its Hub repo id (weights download automatically):
from kerasformers.models.grounding_dino import (
GroundingDinoDetect,
GroundingDinoProcessor,
)
model = GroundingDinoDetect.from_weights("kerasformers/grounding_dino_tiny")
processor = GroundingDinoProcessor.from_weights("kerasformers/grounding_dino_tiny")
inputs = processor(images=image, text="a cat. a remote control.")
outputs = model(inputs) # logits + pred_boxes