README.md

---
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]

<!-- Provide the basic links for the model. -->

- **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:

```python
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)
```