This repository contains the code supporting the RemoteCLIP base model for use with Autodistill.
RemoteCLIP is a vision-language CLIP model trained on remote sensing data. According to the RemoteCLIP README:
RemoteCLIP outperforms previous SoTA by 9.14% mean recall on the RSICD dataset and by 8.92% on RSICD dataset. For zero-shot classification, our RemoteCLIP outperforms the CLIP baseline by up to 6.39% average accuracy on 12 downstream datasets.
Read the full Autodistill documentation.
Read the RemoteCLIP Autodistill documentation.
To use RemoteCLIP with autodistill, you need to install the following dependency:
pip3 install autodistill-remote-clip
from autodistill_remote_clip import RemoteCLIP
from autodistill.detection import CaptionOntology
# define an ontology to map class names to our RemoteCLIP prompt
# the ontology dictionary has the format {caption: class}
# where caption is the prompt sent to the base model, and class is the label that will
# be saved for that caption in the generated annotations
# then, load the model
base_model = RemoteCLIP(
ontology=CaptionOntology(
{
"airport runway": "runway",
"countryside": "countryside",
}
)
)
predictions = base_model.predict("runway.jpg")
print(predictions)
This Autodistill module is licensed under an MIT license. At the time of publishing this project, the RemoteCLIP model and weights had no attached license. Refer to the RemoteCLIP repository for the most up-to-date licensing information regarding the model.
We love your input! Please see the core Autodistill contributing guide to get started. Thank you 🙏 to all our contributors!