Depth-Anything/run.py at main · RAS-Devs/Depth-Anything · GitHub

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
import argparse
import cv2
import numpy as np
import os
import torch
import torch.nn.functional as F
from torchvision.transforms import Compose
from tqdm import tqdm

from depth_anything.dpt import DepthAnything
from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--img-path', type=str)
    parser.add_argument('--outdir', type=str, default='./vis_depth')
    parser.add_argument('--encoder', type=str, default='vitl',
                        choices=['vits', 'vitb', 'vitl'])

    parser.add_argument('--pred-only', dest='pred_only',
                        action='store_true', help='only display the prediction')
    parser.add_argument('--grayscale', dest='grayscale',
                        action='store_true', help='do not apply colorful palette')

    args = parser.parse_args()

    margin_width = 50
    caption_height = 60

    font = cv2.FONT_HERSHEY_SIMPLEX
    font_scale = 1
    font_thickness = 2

    DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'

    depth_anything = DepthAnything.from_pretrained(
        'LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()

    total_params = sum(param.numel() for param in depth_anything.parameters())
    print('Total parameters: {:.2f}M'.format(total_params / 1e6))

    transform = Compose([
        Resize(
            width=518,
            height=518,
            resize_target=False,
            keep_aspect_ratio=True,
            ensure_multiple_of=14,
            resize_method='lower_bound',
            image_interpolation_method=cv2.INTER_CUBIC,
        ),
        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        PrepareForNet(),
    ])

    if os.path.isfile(args.img_path):
        if args.img_path.endswith('txt'):
            with open(args.img_path, 'r') as f:
                filenames = f.read().splitlines()
        else:
            filenames = [args.img_path]
    else:
        filenames = os.listdir(args.img_path)
        filenames = [os.path.join(args.img_path, filename)
                     for filename in filenames if not filename.startswith('.')]
        filenames.sort()

    os.makedirs(args.outdir, exist_ok=True)

    for filename in tqdm(filenames):
        raw_image = cv2.imread(filename)
        image = cv2.cvtColor(raw_image, cv2.COLOR_BGR2RGB) / 255.0

        h, w = image.shape[:2]

        image = transform({'image': image})['image']
        image = torch.from_numpy(image).unsqueeze(0).to(DEVICE)

        with torch.no_grad():
            depth = depth_anything(image)

        depth = F.interpolate(depth[None], (h, w),
                              mode='bilinear', align_corners=False)[0, 0]
        depth = (depth - depth.min()) / (depth.max() -
                                         depth.min()) * np.iinfo(np.uint16).max

        depth = depth.cpu().numpy().astype(np.uint16)

        if args.grayscale:
            depth = np.repeat(depth[..., np.newaxis], 3, axis=-1)
        else:
            depth = cv2.applyColorMap(depth, cv2.COLORMAP_INFERNO)

        filename = os.path.basename(filename)

        if args.pred_only:
            cv2.imwrite(os.path.join(
                args.outdir, filename[:filename.rfind('.')] + '_depth.png'), depth)
        else:
            split_region = np.ones(
                (raw_image.shape[0], margin_width, 3), dtype=np.uint8) * 255
            combined_results = cv2.hconcat([raw_image, split_region, depth])

            caption_space = np.ones(
                (caption_height, combined_results.shape[1], 3), dtype=np.uint8) * 255
            captions = ['Raw image', 'Depth Anything']
            segment_width = w + margin_width

            for i, caption in enumerate(captions):
                # Calculate text size
                text_size = cv2.getTextSize(
                    caption, font, font_scale, font_thickness)[0]

                # Calculate x-coordinate to center the text
                text_x = int((segment_width * i) + (w - text_size[0]) / 2)

                # Add text caption
                cv2.putText(caption_space, caption, (text_x, 40),
                            font, font_scale, (0, 0, 0), font_thickness)

            final_result = cv2.vconcat([caption_space, combined_results])

            cv2.imwrite(os.path.join(
                args.outdir, filename[:filename.rfind('.')] + '_img_depth.png'), final_result)