import gradio as gr

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

feature_extractor = SegformerFeatureExtractor.from_pretrained(
     "nvidia/segformer-b0-finetuned-ade-512-512"
)

processor = SegformerImageProcessor.from_pretrained(
    "nvidia/segformer-b0-finetuned-ade-512-512"
)
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")



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)