File size: 4,103 Bytes
a93afca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.

# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

from copy import deepcopy
from typing import Tuple

import numpy as np
import torch
from torch.nn import functional as F
from torchvision.transforms.functional import resize  # type: ignore
from torchvision.transforms.functional import to_pil_image


class ResizeLongestSide:
    """
    Resizes images to the longest side 'target_length', as well as provides
    methods for resizing coordinates and boxes. Provides methods for
    transforming both numpy array and batched torch tensors.
    """

    def __init__(self, target_length: int) -> None:
        self.target_length = target_length

    def apply_image(self, image: np.ndarray) -> np.ndarray:
        """
        Expects a numpy array with shape HxWxC in uint8 format.
        """
        target_size = self.get_preprocess_shape(
            image.shape[0], image.shape[1], self.target_length
        )
        return np.array(resize(to_pil_image(image), target_size))

    def apply_coords(
        self, coords: np.ndarray, original_size: Tuple[int, ...]
    ) -> np.ndarray:
        """
        Expects a numpy array of length 2 in the final dimension. Requires the
        original image size in (H, W) format.
        """
        old_h, old_w = original_size
        new_h, new_w = self.get_preprocess_shape(
            original_size[0], original_size[1], self.target_length
        )
        coords = deepcopy(coords).astype(float)
        coords[..., 0] = coords[..., 0] * (new_w / old_w)
        coords[..., 1] = coords[..., 1] * (new_h / old_h)
        return coords

    def apply_boxes(
        self, boxes: np.ndarray, original_size: Tuple[int, ...]
    ) -> np.ndarray:
        """
        Expects a numpy array shape Bx4. Requires the original image size
        in (H, W) format.
        """
        boxes = self.apply_coords(boxes.reshape(-1, 2, 2), original_size)
        return boxes.reshape(-1, 4)

    def apply_image_torch(self, image: torch.Tensor) -> torch.Tensor:
        """
        Expects batched images with shape BxCxHxW and float format. This
        transformation may not exactly match apply_image. apply_image is
        the transformation expected by the model.
        """
        # Expects an image in BCHW format. May not exactly match apply_image.
        target_size = self.get_preprocess_shape(
            image.shape[0], image.shape[1], self.target_length
        )
        return F.interpolate(
            image, target_size, mode="bilinear", align_corners=False, antialias=True
        )

    def apply_coords_torch(
        self, coords: torch.Tensor, original_size: Tuple[int, ...]
    ) -> torch.Tensor:
        """
        Expects a torch tensor with length 2 in the last dimension. Requires the
        original image size in (H, W) format.
        """
        old_h, old_w = original_size
        new_h, new_w = self.get_preprocess_shape(
            original_size[0], original_size[1], self.target_length
        )
        coords = deepcopy(coords).to(torch.float)
        coords[..., 0] = coords[..., 0] * (new_w / old_w)
        coords[..., 1] = coords[..., 1] * (new_h / old_h)
        return coords

    def apply_boxes_torch(
        self, boxes: torch.Tensor, original_size: Tuple[int, ...]
    ) -> torch.Tensor:
        """
        Expects a torch tensor with shape Bx4. Requires the original image
        size in (H, W) format.
        """
        boxes = self.apply_coords_torch(boxes.reshape(-1, 2, 2), original_size)
        return boxes.reshape(-1, 4)

    @staticmethod
    def get_preprocess_shape(
        oldh: int, oldw: int, long_side_length: int
    ) -> Tuple[int, int]:
        """
        Compute the output size given input size and target long side length.
        """
        scale = long_side_length * 1.0 / max(oldh, oldw)
        newh, neww = oldh * scale, oldw * scale
        neww = int(neww + 0.5)
        newh = int(newh + 0.5)
        return (newh, neww)