Find similar patches with DINOv3¶

This notebook demonstrates how to find similar patches with DINOv3.

Install packages¶

To use the new functionality, ensure the required packages are installed.

In [ ]:

# %pip install geoai-py

# %pip install geoai-py

Import libraries¶

In [ ]:

import geoai

import geoai

Download sample data¶

In [ ]:

url = "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip/m_4609931_ne_14_1_20100629_subset.tif"
image = geoai.download_file(url)

url = "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip/m_4609931_ne_14_1_20100629_subset.tif" image = geoai.download_file(url)

Initialize the DINOv3 processor¶

In [ ]:

processor = geoai.DINOv3GeoProcessor(
    model_name="dinov3_vitl16",
)

processor = geoai.DINOv3GeoProcessor( model_name="dinov3_vitl16", )

Extract features¶

In [ ]:

features, h_patches, w_patches = processor.extract_features(image)

features, h_patches, w_patches = processor.extract_features(image)

Find similar patches¶

In [ ]:

m = geoai.LeafMap()
m.add_dinov3_gui(image, processor, features)
m

m = geoai.LeafMap() m.add_dinov3_gui(image, processor, features) m