app.py

import torch
torch.jit.script = lambda f: f
import gradio as gr
import spaces

from zoedepth.utils.misc import colorize, save_raw_16bit
from zoedepth.utils.geometry import depth_to_points, create_triangles

from PIL import Image
import numpy as np

css = """
img {
    max-height: 500px;
    object-fit: contain;
}
"""

# DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
MODEL = torch.hub.load('isl-org/ZoeDepth', "ZoeD_N", pretrained=True).eval()

# ----------- Depth functions
def save_raw_16bit(depth, fpath="raw.png"):
    if isinstance(depth, torch.Tensor):
        depth = depth.squeeze().cpu().numpy()
    
    # assert isinstance(depth, np.ndarray), "Depth must be a torch tensor or numpy array"
    # assert depth.ndim == 2, "Depth must be 2D"
    depth = depth * 256  # scale for 16-bit png
    depth = depth.astype(np.uint16)
    return depth

@spaces.GPU(enable_queue=True)
def process_image(image: Image.Image):
    global MODEL
    image = image.convert("RGB")

    device = "cuda" if torch.cuda.is_available() else "cpu"
    MODEL.to(device)
    depth = MODEL.infer_pil(image)

    processed_array = save_raw_16bit(colorize(depth)[:, :, 0])
    return Image.fromarray(processed_array)

# ----------- Depth functions


title = "# ZoeDepth"
description = """Unofficial demo for **ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth**."""

with gr.Blocks(css=css) as API:
    gr.Markdown(title)
    gr.Markdown(description)
    with gr.Tab("Depth Prediction"):
        with gr.Row():
            inputs=gr.Image(label="Input Image", type='pil', height=500)  # Input is an image
            outputs=gr.Image(label="Depth Map", type='pil', height=500)  # Output is also an image
        generate_btn = gr.Button(value="Generate")
        generate_btn.click(process_image, inputs=inputs, outputs=outputs, api_name="generate_depth")

if __name__ == '__main__':
    API.launch()