from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
from PIL import Image
import requests

feature_extractor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b1-finetuned-cityscapes-1024-1024")

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

inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)