app.py

import gradio as gr
import cv2
import matplotlib
import numpy as np
import os
from PIL import Image
import mmap
import json
import spaces
import torch
import tempfile
from gradio_imageslider import ImageSlider
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from transformers import pipeline
from depth_anything_v2.dpt import DepthAnythingV2

css = """
#img-display-container {
    max-height: 100vh;
}
#img-display-input {
    max-height: 80vh;
}
#img-display-output {
    max-height: 80vh;
}
#download {
    height: 62px;
}
"""
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
model_configs = {
    'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]},
    'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]},
    'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]},
    'vitg': {'encoder': 'vitg', 'features': 384, 'out_channels': [1536, 1536, 1536, 1536]}
}
encoder2name = {
    'vits': 'Small',
    'vitb': 'Base',
    'vitl': 'Large',
    'vitg': 'Giant', # we are undergoing company review procedures to release our giant model checkpoint
}
encoder = 'vitl'
model_name = encoder2name[encoder]
model = DepthAnythingV2(**model_configs[encoder])
filepath = hf_hub_download(repo_id="depth-anything/Depth-Anything-V2-Metric-Indoor-Large-hf", filename="model.safetensors", repo_type="model")

# Convert to PyTorch tensor
#state_dict = torch.load(filepath, map_location="cpu", weights_only=True)
#state_dict = load_file(filepath)

#model.load_state_dict(state_dict)
#model = model.to(DEVICE).eval()

pipe = pipeline(task="depth-estimation", model="depth-anything/Depth-Anything-V2-Metric-Outdoor-Large-hf", device=DEVICE) 
#pipe = pipeline(task="depth-estimation", model="LiheYoung/Depth-Anything", device=DEVICE) 

title = "# Depth Anything V2"
description = """Official demo for **Depth Anything V2**.
Please refer to our [paper](https://arxiv.org/abs/2406.09414), [project page](https://depth-anything-v2.github.io), and [github](https://github.com/DepthAnything/Depth-Anything-V2) for more details."""

@spaces.GPU
def predict_depth(image):
    return pipe(image)

with gr.Blocks(css=css) as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    gr.Markdown("### Depth Prediction demo")

    with gr.Row():
        input_image = gr.Image(label="Input Image", type="pil" ,elem_id='img-display-input')
        depth_image_slider = gr.Image(label="Depth Map with Slider View", type="pil", elem_id='img-display-output')
    submit = gr.Button(value="Compute Depth")

    def on_submit(image):
        original_image = image.copy()
        result = predict_depth(image)
        return result["depth"]

    submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider])

    example_files = os.listdir('assets/examples')
    example_files.sort()
    example_files = [os.path.join('assets/examples', filename) for filename in example_files]
    examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider], fn=on_submit)


if __name__ == '__main__':
    demo.queue().launch(share=True)