File size: 8,572 Bytes
c84e839
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
import random
from PIL import Image, ImageOps, ImageFilter
import torch
from torchvision import transforms
import torch.nn.functional as F

import numpy as np
import cv2
import math


def apply_min_size(sample, size, image_interpolation_method=cv2.INTER_AREA):
    """Rezise the sample to ensure the given size. Keeps aspect ratio.

    Args:
        sample (dict): sample
        size (tuple): image size

    Returns:
        tuple: new size
    """
    shape = list(sample["disparity"].shape)

    if shape[0] >= size[0] and shape[1] >= size[1]:
        return sample

    scale = [0, 0]
    scale[0] = size[0] / shape[0]
    scale[1] = size[1] / shape[1]

    scale = max(scale)

    shape[0] = math.ceil(scale * shape[0])
    shape[1] = math.ceil(scale * shape[1])

    # resize
    sample["image"] = cv2.resize(
        sample["image"], tuple(shape[::-1]), interpolation=image_interpolation_method
    )

    sample["disparity"] = cv2.resize(
        sample["disparity"], tuple(shape[::-1]), interpolation=cv2.INTER_NEAREST
    )
    sample["mask"] = cv2.resize(
        sample["mask"].astype(np.float32),
        tuple(shape[::-1]),
        interpolation=cv2.INTER_NEAREST,
    )
    sample["mask"] = sample["mask"].astype(bool)

    return tuple(shape)


class Resize(object):
    """Resize sample to given size (width, height).
    """

    def __init__(
        self,
        width,
        height,
        resize_target=True,
        keep_aspect_ratio=False,
        ensure_multiple_of=1,
        resize_method="lower_bound",
        image_interpolation_method=cv2.INTER_AREA,
    ):
        """Init.

        Args:
            width (int): desired output width
            height (int): desired output height
            resize_target (bool, optional):
                True: Resize the full sample (image, mask, target).
                False: Resize image only.
                Defaults to True.
            keep_aspect_ratio (bool, optional):
                True: Keep the aspect ratio of the input sample.
                Output sample might not have the given width and height, and
                resize behaviour depends on the parameter 'resize_method'.
                Defaults to False.
            ensure_multiple_of (int, optional):
                Output width and height is constrained to be multiple of this parameter.
                Defaults to 1.
            resize_method (str, optional):
                "lower_bound": Output will be at least as large as the given size.
                "upper_bound": Output will be at max as large as the given size. (Output size might be smaller than given size.)
                "minimal": Scale as least as possible.  (Output size might be smaller than given size.)
                Defaults to "lower_bound".
        """
        self.__width = width
        self.__height = height

        self.__resize_target = resize_target
        self.__keep_aspect_ratio = keep_aspect_ratio
        self.__multiple_of = ensure_multiple_of
        self.__resize_method = resize_method
        self.__image_interpolation_method = image_interpolation_method

    def constrain_to_multiple_of(self, x, min_val=0, max_val=None):
        y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int)

        if max_val is not None and y > max_val:
            y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int)

        if y < min_val:
            y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int)

        return y

    def get_size(self, width, height):
        # determine new height and width
        scale_height = self.__height / height
        scale_width = self.__width / width

        if self.__keep_aspect_ratio:
            if self.__resize_method == "lower_bound":
                # scale such that output size is lower bound
                if scale_width > scale_height:
                    # fit width
                    scale_height = scale_width
                else:
                    # fit height
                    scale_width = scale_height
            elif self.__resize_method == "upper_bound":
                # scale such that output size is upper bound
                if scale_width < scale_height:
                    # fit width
                    scale_height = scale_width
                else:
                    # fit height
                    scale_width = scale_height
            elif self.__resize_method == "minimal":
                # scale as least as possbile
                if abs(1 - scale_width) < abs(1 - scale_height):
                    # fit width
                    scale_height = scale_width
                else:
                    # fit height
                    scale_width = scale_height
            else:
                raise ValueError(
                    f"resize_method {self.__resize_method} not implemented"
                )

        if self.__resize_method == "lower_bound":
            new_height = self.constrain_to_multiple_of(
                scale_height * height, min_val=self.__height
            )
            new_width = self.constrain_to_multiple_of(
                scale_width * width, min_val=self.__width
            )
        elif self.__resize_method == "upper_bound":
            new_height = self.constrain_to_multiple_of(
                scale_height * height, max_val=self.__height
            )
            new_width = self.constrain_to_multiple_of(
                scale_width * width, max_val=self.__width
            )
        elif self.__resize_method == "minimal":
            new_height = self.constrain_to_multiple_of(scale_height * height)
            new_width = self.constrain_to_multiple_of(scale_width * width)
        else:
            raise ValueError(f"resize_method {self.__resize_method} not implemented")

        return (new_width, new_height)

    def __call__(self, sample):
        width, height = self.get_size(
            sample["image"].shape[1], sample["image"].shape[0]
        )

        # resize sample
        sample["image"] = cv2.resize(
            sample["image"],
            (width, height),
            interpolation=self.__image_interpolation_method,
        )

        if self.__resize_target:
            if "disparity" in sample:
                sample["disparity"] = cv2.resize(
                    sample["disparity"],
                    (width, height),
                    interpolation=cv2.INTER_NEAREST,
                )

            if "depth" in sample:
                sample["depth"] = cv2.resize(
                    sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST
                )

            if "semseg_mask" in sample:
                # sample["semseg_mask"] = cv2.resize(
                #     sample["semseg_mask"], (width, height), interpolation=cv2.INTER_NEAREST
                # )
                sample["semseg_mask"] = F.interpolate(torch.from_numpy(sample["semseg_mask"]).float()[None, None, ...], (height, width), mode='nearest').numpy()[0, 0]
                
            if "mask" in sample:
                sample["mask"] = cv2.resize(
                    sample["mask"].astype(np.float32),
                    (width, height),
                    interpolation=cv2.INTER_NEAREST,
                )
                # sample["mask"] = sample["mask"].astype(bool)

        # print(sample['image'].shape, sample['depth'].shape)
        return sample


class NormalizeImage(object):
    """Normlize image by given mean and std.
    """

    def __init__(self, mean, std):
        self.__mean = mean
        self.__std = std

    def __call__(self, sample):
        sample["image"] = (sample["image"] - self.__mean) / self.__std

        return sample


class PrepareForNet(object):
    """Prepare sample for usage as network input.
    """

    def __init__(self):
        pass

    def __call__(self, sample):
        image = np.transpose(sample["image"], (2, 0, 1))
        sample["image"] = np.ascontiguousarray(image).astype(np.float32)

        if "mask" in sample:
            sample["mask"] = sample["mask"].astype(np.float32)
            sample["mask"] = np.ascontiguousarray(sample["mask"])
        
        if "depth" in sample:
            depth = sample["depth"].astype(np.float32)
            sample["depth"] = np.ascontiguousarray(depth)
            
        if "semseg_mask" in sample:
            sample["semseg_mask"] = sample["semseg_mask"].astype(np.float32)
            sample["semseg_mask"] = np.ascontiguousarray(sample["semseg_mask"])

        return sample