app.py

import gradio as gr

import torch
import numpy as np
from PIL import Image
import requests
from transformers import AutoImageProcessor, AutoModelForDepthEstimation

def greet(name):
    
    
    
    url = "http://images.cocodataset.org/val2017/000000039769.jpg"
    image = Image.open(requests.get(url, stream=True).raw)
    
    image_processor = AutoImageProcessor.from_pretrained("LiheYoung/depth-anything-small-hf")
    model = AutoModelForDepthEstimation.from_pretrained("LiheYoung/depth-anything-small-hf")
    
    # prepare image for the model
    inputs = image_processor(images=image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model(**inputs)
        predicted_depth = outputs.predicted_depth
    
    # interpolate to original size
    prediction = torch.nn.functional.interpolate(
        predicted_depth.unsqueeze(1),
        size=image.size[::-1],
        mode="bicubic",
        align_corners=False,
    )
    
    # visualize the prediction
    output = prediction.squeeze().cpu().numpy()
    formatted = (output * 255 / np.max(output)).astype("uint8")
    depth = Image.fromarray(formatted)
    return name+": " + depth 

iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()