README.md

metadata

language: en
license: mit
library_name: pytorch
model-index:
  - name: baseline
    results:
      - task:
          type: Geoscore
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: geoscore
            value: 3361
      - task:
          type: Haversine Distance
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: haversine distance
            value: 1814
      - task:
          type: Country classification
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: country accuracy
            value: 68
      - task:
          type: Region classification
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: region accuracy
            value: 39.4
      - task:
          type: Area classification
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: area accuracy
            value: 10.3
      - task:
          type: City classification
        dataset:
          name: OSV-5M
          type: geolocation
        metrics:
          - type: city accuracy
            value: 5.9

Geolocation baseline on OSV-5M

More details to be released upon publication (<tbr>). Everything is based on the OSV-5M benchmark dataset.

Model Details

<tbr>

Model Description

<tbr>

• Developed by: <tbr>
• License: mit
• Based on hf models: <tbr>

Model Sources [optional]

• Repository: <tbr>
• Paper: <tbr>
• Human Evaluation <tbr>

Usage

The main purpose of this model is academic usage. We provide a hugging face repo both to facilitate accessing and run inference to our model.

Example usage

First download the repo !git clone <tbr>. Then from any script whose cwd is the repos main directory (cd <tbr>) run:

from PIL import Image
from huggingface import Geolocalizer
Geolocalizer.from_pretrained('osv5m/baseline')
img = Image.open('.media/examples/img1.jpeg')
x = geoloc.transform(img).unsqueeze(0) # transform the image using our dedicated transformer
gps = geolocalizer(x) # B, 2 (lat, lon - tensor in rad)