from PIL import Image
import requests
from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("jrheiner/thesis-clip-geoloc-continent")
processor = CLIPProcessor.from_pretrained("jrheiner/thesis-clip-geoloc-continent")

url = "https://huggingface.co/spaces/jrheiner/thesis-demo/resolve/main/kerger-test-images/Oceania_Australia_-32.947127313081_151.47903359833_kerger.jpg"
image = Image.open(requests.get(url, stream=True).raw)
choices = ["North America", "Africa", "Asia", "Oceania", "South America", "Europe"]
inputs = processor(text=choices, images=image, return_tensors="pt", padding=True)
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities

Training Details

The model was fine-tuned on 177 270 images (29 545 per continent) sourced from Mapillary.