eomt-dinov3-ade-semantic-large-512

import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, EomtDinov3ForUniversalSegmentation

model_id = "nielsr/eomt-dinov3-ade-semantic-large-512"
processor = AutoImageProcessor.from_pretrained(model_id)
model = EomtDinov3ForUniversalSegmentation.from_pretrained(model_id)

device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(images=image, return_tensors="pt").to(device)

with torch.inference_mode():
    outputs = model(**inputs)

# Semantic Segmentation
result = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
print(result.shape)  # Segmentation map with class indices