File size: 5,147 Bytes
7c27268
 
 
 
 
 
7a6bafa
 
7c27268
 
 
 
 
82fa24a
7c27268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02d2686
 
 
 
de5bd2a
02d2686
de5bd2a
48d0430
7c27268
c5f38fa
7a6bafa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82fa24a
 
 
 
 
 
 
 
 
7a6bafa
 
82fa24a
 
7a6bafa
7c27268
 
 
 
6ceac94
 
7c27268
 
 
187c6c8
7c27268
 
 
6ceac94
7c27268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
187c6c8
7c27268
 
 
 
187c6c8
7c27268
 
 
 
 
 
 
 
 
 
45a5139
7c27268
45a5139
7c27268
 
 
 
 
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
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
import safetensors

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")

def create_tensor(storage, info, offset):
    DTYPES = {"F32": torch.float32}
    dtype = DTYPES[info["dtype"]]
    shape = info["shape"]
    start, stop = info["data_offsets"]
    return torch.asarray(storage[start + offset : stop + offset], dtype=torch.uint8).view(dtype=dtype).reshape(shape)

def load_file(filename):
    with open(filename, mode="r", encoding="utf8") as file_obj:
        with mmap.mmap(file_obj.fileno(), length=0, access=mmap.ACCESS_READ) as m:
            header = m.read(8)
            n = int.from_bytes(header, "little")
            metadata_bytes = m.read(n)
            metadata = json.loads(metadata_bytes)

    size = os.stat(filename).st_size
    storage = torch.ByteStorage.from_file(filename, shared=False, size=size).untyped()
    offset = n + 8
    return {name: create_tensor(storage, info, offset) for name, info in metadata.items() if name != "__metadata__"}

tensor_data = safetensors.load(filepath)

# Convert to PyTorch tensor
if isinstance(tensor_data, np.ndarray):
    pytorch_tensor = torch.tensor(tensor_data)
elif isinstance(tensor_data, safetensors.Tensor):
    pytorch_tensor = torch.tensor(tensor_data.numpy())  # Assuming safetensors Tensor has a .numpy() method
else:
    raise TypeError("Unsupported data type from safetensors")

#state_dict = torch.load(filepath, map_location="cpu", weights_only=True)
#state_dict = load_file(filepath)
state_dict = pytorch_tensor

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

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 model.infer_image(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='numpy', elem_id='img-display-input')
        depth_image_slider = ImageSlider(label="Depth Map with Slider View", elem_id='img-display-output', position=0.5)
    submit = gr.Button(value="Compute Depth")
    gray_depth_file = gr.File(label="Grayscale depth map", elem_id="download",)
    raw_file = gr.File(label="16-bit raw output (can be considered as disparity)", elem_id="download",)

    cmap = matplotlib.colormaps.get_cmap('Spectral_r')

    def on_submit(image):
        original_image = image.copy()

        h, w = image.shape[:2]

        depth = predict_depth(image[:, :, ::-1])

        raw_depth = Image.fromarray(depth.astype('uint16'))
        tmp_raw_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        raw_depth.save(tmp_raw_depth.name)

        depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
        depth = depth.astype(np.uint8)
        colored_depth = (cmap(depth)[:, :, :3] * 255).astype(np.uint8)

        gray_depth = Image.fromarray(depth)
        tmp_gray_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        gray_depth.save(tmp_gray_depth.name)

        return [(original_image, colored_depth), tmp_gray_depth.name, tmp_raw_depth.name]

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

    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, gray_depth_file, raw_file], fn=on_submit)


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