File size: 6,962 Bytes
a64b7d4 |
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 |
import math
import numpy as np
import torch
def cubic(x):
"""cubic function used for calculate_weights_indices."""
absx = torch.abs(x)
absx2 = absx**2
absx3 = absx**3
return (1.5 * absx3 - 2.5 * absx2 + 1) * (
(absx <= 1).type_as(absx)) + (-0.5 * absx3 + 2.5 * absx2 - 4 * absx + 2) * (((absx > 1) *
(absx <= 2)).type_as(absx))
def calculate_weights_indices(in_length, out_length, scale, kernel, kernel_width, antialiasing):
"""Calculate weights and indices, used for imresize function.
Args:
in_length (int): Input length.
out_length (int): Output length.
scale (float): Scale factor.
kernel_width (int): Kernel width.
antialisaing (bool): Whether to apply anti-aliasing when downsampling.
"""
if (scale < 1) and antialiasing:
# Use a modified kernel (larger kernel width) to simultaneously
# interpolate and antialias
kernel_width = kernel_width / scale
# Output-space coordinates
x = torch.linspace(1, out_length, out_length)
# Input-space coordinates. Calculate the inverse mapping such that 0.5
# in output space maps to 0.5 in input space, and 0.5 + scale in output
# space maps to 1.5 in input space.
u = x / scale + 0.5 * (1 - 1 / scale)
# What is the left-most pixel that can be involved in the computation?
left = torch.floor(u - kernel_width / 2)
# What is the maximum number of pixels that can be involved in the
# computation? Note: it's OK to use an extra pixel here; if the
# corresponding weights are all zero, it will be eliminated at the end
# of this function.
p = math.ceil(kernel_width) + 2
# The indices of the input pixels involved in computing the k-th output
# pixel are in row k of the indices matrix.
indices = left.view(out_length, 1).expand(out_length, p) + torch.linspace(0, p - 1, p).view(1, p).expand(
out_length, p)
# The weights used to compute the k-th output pixel are in row k of the
# weights matrix.
distance_to_center = u.view(out_length, 1).expand(out_length, p) - indices
# apply cubic kernel
if (scale < 1) and antialiasing:
weights = scale * cubic(distance_to_center * scale)
else:
weights = cubic(distance_to_center)
# Normalize the weights matrix so that each row sums to 1.
weights_sum = torch.sum(weights, 1).view(out_length, 1)
weights = weights / weights_sum.expand(out_length, p)
# If a column in weights is all zero, get rid of it. only consider the
# first and last column.
weights_zero_tmp = torch.sum((weights == 0), 0)
if not math.isclose(weights_zero_tmp[0], 0, rel_tol=1e-6):
indices = indices.narrow(1, 1, p - 2)
weights = weights.narrow(1, 1, p - 2)
if not math.isclose(weights_zero_tmp[-1], 0, rel_tol=1e-6):
indices = indices.narrow(1, 0, p - 2)
weights = weights.narrow(1, 0, p - 2)
weights = weights.contiguous()
indices = indices.contiguous()
sym_len_s = -indices.min() + 1
sym_len_e = indices.max() - in_length
indices = indices + sym_len_s - 1
return weights, indices, int(sym_len_s), int(sym_len_e)
@torch.no_grad()
def imresize(img, scale, antialiasing=True):
"""imresize function same as MATLAB.
It now only supports bicubic.
The same scale applies for both height and width.
Args:
img (Tensor | Numpy array):
Tensor: Input image with shape (c, h, w), [0, 1] range.
Numpy: Input image with shape (h, w, c), [0, 1] range.
scale (float): Scale factor. The same scale applies for both height
and width.
antialisaing (bool): Whether to apply anti-aliasing when downsampling.
Default: True.
Returns:
Tensor: Output image with shape (c, h, w), [0, 1] range, w/o round.
"""
squeeze_flag = False
if type(img).__module__ == np.__name__: # numpy type
numpy_type = True
if img.ndim == 2:
img = img[:, :, None]
squeeze_flag = True
img = torch.from_numpy(img.transpose(2, 0, 1)).float()
else:
numpy_type = False
if img.ndim == 2:
img = img.unsqueeze(0)
squeeze_flag = True
in_c, in_h, in_w = img.size()
out_h, out_w = math.ceil(in_h * scale), math.ceil(in_w * scale)
kernel_width = 4
kernel = 'cubic'
# get weights and indices
weights_h, indices_h, sym_len_hs, sym_len_he = calculate_weights_indices(in_h, out_h, scale, kernel, kernel_width,
antialiasing)
weights_w, indices_w, sym_len_ws, sym_len_we = calculate_weights_indices(in_w, out_w, scale, kernel, kernel_width,
antialiasing)
# process H dimension
# symmetric copying
img_aug = torch.FloatTensor(in_c, in_h + sym_len_hs + sym_len_he, in_w)
img_aug.narrow(1, sym_len_hs, in_h).copy_(img)
sym_patch = img[:, :sym_len_hs, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
img_aug.narrow(1, 0, sym_len_hs).copy_(sym_patch_inv)
sym_patch = img[:, -sym_len_he:, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
img_aug.narrow(1, sym_len_hs + in_h, sym_len_he).copy_(sym_patch_inv)
out_1 = torch.FloatTensor(in_c, out_h, in_w)
kernel_width = weights_h.size(1)
for i in range(out_h):
idx = int(indices_h[i][0])
for j in range(in_c):
out_1[j, i, :] = img_aug[j, idx:idx + kernel_width, :].transpose(0, 1).mv(weights_h[i])
# process W dimension
# symmetric copying
out_1_aug = torch.FloatTensor(in_c, out_h, in_w + sym_len_ws + sym_len_we)
out_1_aug.narrow(2, sym_len_ws, in_w).copy_(out_1)
sym_patch = out_1[:, :, :sym_len_ws]
inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(2, inv_idx)
out_1_aug.narrow(2, 0, sym_len_ws).copy_(sym_patch_inv)
sym_patch = out_1[:, :, -sym_len_we:]
inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(2, inv_idx)
out_1_aug.narrow(2, sym_len_ws + in_w, sym_len_we).copy_(sym_patch_inv)
out_2 = torch.FloatTensor(in_c, out_h, out_w)
kernel_width = weights_w.size(1)
for i in range(out_w):
idx = int(indices_w[i][0])
for j in range(in_c):
out_2[j, :, i] = out_1_aug[j, :, idx:idx + kernel_width].mv(weights_w[i])
if squeeze_flag:
out_2 = out_2.squeeze(0)
if numpy_type:
out_2 = out_2.numpy()
if not squeeze_flag:
out_2 = out_2.transpose(1, 2, 0)
return out_2
|