app.py

from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import torch
import torch.nn.functional as F
import time
 
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
processor = ViTImageProcessor.from_pretrained("LCZs_v2",local_files_only=True)
model = ViTForImageClassification.from_pretrained("LCZs_v2",local_files_only=True).to(device)
 
def predict(image):
    inputs = processor(images=image, return_tensors="pt").to(device)
    outputs = model(**inputs)
    logits = outputs.logits
    predicted_class_prob = F.softmax(logits, dim=-1).detach().cpu().numpy().max()
    predicted_class_idx = logits.argmax(-1).item()
    label = model.config.id2label[predicted_class_idx].split(",")[0]
    time.sleep(2)
    return {label: float(predicted_class_prob)}
import gradio as gr
 
gr.Interface(predict, gr.Image(type="pil"), "label").launch()