Registry / ai-ml / rf-groundingdino

rf-groundingdino

library0.3.0pypypi✓ verified 82d ago

A Roboflow-maintained fork of Grounding DINO, a state-of-the-art open-set object detector that can detect arbitrary objects based on text prompts. Version 0.3.0 combines image and text encoders with a transformer-based fusion approach. Release cadence is irregular; actively maintained.

ai-ml

pip install rf-groundingdino

github ↗package ↗

INSTALL

IMPORT

SIG · RF-GROUNDINGDINO

rf-groundingdino

ai-mlpythonv0.3.0

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

groundingdino

✓ import groundingdino

✗ from rf_groundingdino import groundingdino

Load the model and run inference on an image with text prompts.

from rf_groundingdino import groundingdino from rf_groundingdino.util.inference import load_model, predict import torch device = 'cuda' if torch.cuda.is_available() else 'cpu' model = load_model('groundingdino_swint_ogc', 'path/to/config.py', 'path/to/weights.pth') # For inference, use predict() or model() import cv2 image = cv2.imread('image.jpg') prompts = 'cat . dog .' # separate classes with ' . ' boxes, logits, phrases = predict(model, image, prompts, box_threshold=0.3, text_threshold=0.25) print('Detections:', len(phrases))

Debug

Known issues

breakingPackage renamed from 'groundingdino' to 'rf_groundingdino' in v0.1.2. All imports must use 'rf_groundingdino' prefix.

fix

Change imports: 'import groundingdino' -> 'from rf_groundingdino import groundingdino'

affects: >=0.1.2

gotchaThe predict() function expects prompts in a specific format: separate each class with ' . ' (space-dot-space). Omitting spaces or using different separators leads to zero detections.

fix

Use format: 'cat . dog . person' (note the spaces around the dot).

affects: all

gotchaModel weights are not included in pip install. You must download them manually from the GitHub releases page.

fix

Download weights from https://github.com/roboflow/GroundingDINO/releases and provide the path.

affects: all

deprecatedThe old 'groundingdino' package (v0.1.0) is unmaintained and incompatible with this fork.

fix

Uninstall old package and install rf-groundingdino: pip install rf-groundingdino

affects: <=0.1.0

Upgrade

Version history

0.3.0latest on PyPI · released Dec 8, 2025

Audit

Dependencies

torchrequiredCore dependency for model computation

transformersrequiredRequired for text encoder (BERT-based)

supervisionoptionalUsed for detection result processing (loading, annotation)

Agent activity

7 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/roboflow/GroundingDINO ↗

packagehttps://pypi.org/project/rf-groundingdino/ ↗