sadasd67/florence2-coordinates

from transformers import AutoModelForCausalLM, AutoProcessor
from PIL import Image
import re

model = AutoModelForCausalLM.from_pretrained("sadasd67/florence2-coordinates", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("sadasd67/florence2-coordinates", trust_remote_code=True)

image = Image.open("captcha.png")
inputs = processor(text="<COORDINATE>", images=image, return_tensors="pt")
generated = model.generate(**inputs, max_new_tokens=64)
result = processor.batch_decode(generated, skip_special_tokens=False)[0]

# Parse coordinates
locs = [int(x) for x in re.findall(r'<loc_(\d+)>', result)]
w, h = image.size
coords = [(locs[i] * w / 999, locs[i+1] * h / 999) for i in range(0, len(locs), 2)]
print(coords)