File size: 3,175 Bytes
7c27268
 
 
 
 
 
7a6bafa
 
7c27268
 
 
 
 
2b8834a
050c6f5
7c27268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02d2686
 
 
 
de5bd2a
02d2686
de5bd2a
48d0430
7c27268
c5f38fa
7a6bafa
82fa24a
7a6bafa
050c6f5
7a6bafa
050c6f5
 
 
f6e95ff
 
7c27268
 
6ceac94
 
7c27268
055cd1b
7c27268
bc1d278
7c27268
055cd1b
7c27268
6ceac94
7c27268
 
 
2c36086
eabf5af
7c27268
 
ad367d9
055cd1b
5e51d3c
f165604
7c27268
d66adea
7c27268
055cd1b
 
45a5139
7798364
7c27268
055cd1b
7c27268
 
055cd1b
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
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)