app.py

import gradio as gr
from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import torch

# 载入模型
model_id = "watersplash/waste-classification"
processor = ViTImageProcessor.from_pretrained(model_id)
model = ViTForImageClassification.from_pretrained(model_id)

def classify(img):
    inputs = processor(images=img, return_tensors="pt")
    outputs = model(**inputs)
    logits = outputs.logits
    pred_id = torch.argmax(logits, dim=-1).item()
    label = model.config.id2label[pred_id]
    return label

iface = gr.Interface(fn=classify, 
                     inputs=gr.Image(type="pil"), 
                     outputs="text")

iface.launch()