Spaces:
Running
Running
File size: 8,586 Bytes
aaa2047 |
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 |
import cv2
import math
import numpy as np
import os
import torch
from torchvision.utils import make_grid
def img2tensor(imgs, bgr2rgb=True, float32=True):
"""Numpy array to tensor.
Args:
imgs (list[ndarray] | ndarray): Input images.
bgr2rgb (bool): Whether to change bgr to rgb.
float32 (bool): Whether to change to float32.
Returns:
list[tensor] | tensor: Tensor images. If returned results only have
one element, just return tensor.
"""
def _totensor(img, bgr2rgb, float32):
if img.shape[2] == 3 and bgr2rgb:
if img.dtype == 'float64':
img = img.astype('float32')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = torch.from_numpy(img.transpose(2, 0, 1))
if float32:
img = img.float()
return img
if isinstance(imgs, list):
return [_totensor(img, bgr2rgb, float32) for img in imgs]
else:
return _totensor(imgs, bgr2rgb, float32)
def tensor2img(tensor, rgb2bgr=True, out_type=np.uint8, min_max=(0, 1)):
"""Convert torch Tensors into image numpy arrays.
After clamping to [min, max], values will be normalized to [0, 1].
Args:
tensor (Tensor or list[Tensor]): Accept shapes:
1) 4D mini-batch Tensor of shape (B x 3/1 x H x W);
2) 3D Tensor of shape (3/1 x H x W);
3) 2D Tensor of shape (H x W).
Tensor channel should be in RGB order.
rgb2bgr (bool): Whether to change rgb to bgr.
out_type (numpy type): output types. If ``np.uint8``, transform outputs
to uint8 type with range [0, 255]; otherwise, float type with
range [0, 1]. Default: ``np.uint8``.
min_max (tuple[int]): min and max values for clamp.
Returns:
(Tensor or list): 3D ndarray of shape (H x W x C) OR 2D ndarray of
shape (H x W). The channel order is BGR.
"""
if not (torch.is_tensor(tensor) or (isinstance(tensor, list) and all(torch.is_tensor(t) for t in tensor))):
raise TypeError(f'tensor or list of tensors expected, got {type(tensor)}')
if torch.is_tensor(tensor):
tensor = [tensor]
result = []
for _tensor in tensor:
_tensor = _tensor.squeeze(0).float().detach().cpu().clamp_(*min_max)
_tensor = (_tensor - min_max[0]) / (min_max[1] - min_max[0])
n_dim = _tensor.dim()
if n_dim == 4:
img_np = make_grid(_tensor, nrow=int(math.sqrt(_tensor.size(0))), normalize=False).numpy()
img_np = img_np.transpose(1, 2, 0)
if rgb2bgr:
img_np = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
elif n_dim == 3:
img_np = _tensor.numpy()
img_np = img_np.transpose(1, 2, 0)
if img_np.shape[2] == 1: # gray image
img_np = np.squeeze(img_np, axis=2)
else:
if rgb2bgr:
img_np = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
elif n_dim == 2:
img_np = _tensor.numpy()
else:
raise TypeError(f'Only support 4D, 3D or 2D tensor. But received with dimension: {n_dim}')
if out_type == np.uint8:
# Unlike MATLAB, numpy.unit8() WILL NOT round by default.
img_np = (img_np * 255.0).round()
img_np = img_np.astype(out_type)
result.append(img_np)
if len(result) == 1:
result = result[0]
return result
def tensor2img_fast(tensor, rgb2bgr=True, min_max=(0, 1)):
"""This implementation is slightly faster than tensor2img.
It now only supports torch tensor with shape (1, c, h, w).
Args:
tensor (Tensor): Now only support torch tensor with (1, c, h, w).
rgb2bgr (bool): Whether to change rgb to bgr. Default: True.
min_max (tuple[int]): min and max values for clamp.
"""
output = tensor.squeeze(0).detach().clamp_(*min_max).permute(1, 2, 0)
output = (output - min_max[0]) / (min_max[1] - min_max[0]) * 255
output = output.type(torch.uint8).cpu().numpy()
if rgb2bgr:
output = cv2.cvtColor(output, cv2.COLOR_RGB2BGR)
return output
def imfrombytes(content, flag='color', float32=False):
"""Read an image from bytes.
Args:
content (bytes): Image bytes got from files or other streams.
flag (str): Flags specifying the color type of a loaded image,
candidates are `color`, `grayscale` and `unchanged`.
float32 (bool): Whether to change to float32., If True, will also norm
to [0, 1]. Default: False.
Returns:
ndarray: Loaded image array.
"""
img_np = np.frombuffer(content, np.uint8)
imread_flags = {'color': cv2.IMREAD_COLOR, 'grayscale': cv2.IMREAD_GRAYSCALE, 'unchanged': cv2.IMREAD_UNCHANGED}
img = cv2.imdecode(img_np, imread_flags[flag])
if float32:
img = img.astype(np.float32) / 255.
return img
def imwrite(img, file_path, params=None, auto_mkdir=True):
"""Write image to file.
Args:
img (ndarray): Image array to be written.
file_path (str): Image file path.
params (None or list): Same as opencv's :func:`imwrite` interface.
auto_mkdir (bool): If the parent folder of `file_path` does not exist,
whether to create it automatically.
Returns:
bool: Successful or not.
"""
if auto_mkdir:
dir_name = os.path.abspath(os.path.dirname(file_path))
os.makedirs(dir_name, exist_ok=True)
ok = cv2.imwrite(file_path, img, params)
if not ok:
raise IOError('Failed in writing images.')
def crop_border(imgs, crop_border):
"""Crop borders of images.
Args:
imgs (list[ndarray] | ndarray): Images with shape (h, w, c).
crop_border (int): Crop border for each end of height and weight.
Returns:
list[ndarray]: Cropped images.
"""
if crop_border == 0:
return imgs
else:
if isinstance(imgs, list):
return [v[crop_border:-crop_border, crop_border:-crop_border, ...] for v in imgs]
else:
return imgs[crop_border:-crop_border, crop_border:-crop_border, ...]
def tensor_lab2rgb(labs, illuminant="D65", observer="2"):
"""
Args:
lab : (B, C, H, W)
Returns:
tuple : (C, H, W)
"""
illuminants = \
{"A": {'2': (1.098466069456375, 1, 0.3558228003436005),
'10': (1.111420406956693, 1, 0.3519978321919493)},
"D50": {'2': (0.9642119944211994, 1, 0.8251882845188288),
'10': (0.9672062750333777, 1, 0.8142801513128616)},
"D55": {'2': (0.956797052643698, 1, 0.9214805860173273),
'10': (0.9579665682254781, 1, 0.9092525159847462)},
"D65": {'2': (0.95047, 1., 1.08883), # This was: `lab_ref_white`
'10': (0.94809667673716, 1, 1.0730513595166162)},
"D75": {'2': (0.9497220898840717, 1, 1.226393520724154),
'10': (0.9441713925645873, 1, 1.2064272211720228)},
"E": {'2': (1.0, 1.0, 1.0),
'10': (1.0, 1.0, 1.0)}}
xyz_from_rgb = np.array([[0.412453, 0.357580, 0.180423], [0.212671, 0.715160, 0.072169],
[0.019334, 0.119193, 0.950227]])
rgb_from_xyz = np.array([[3.240481340, -0.96925495, 0.055646640], [-1.53715152, 1.875990000, -0.20404134],
[-0.49853633, 0.041555930, 1.057311070]])
B, C, H, W = labs.shape
arrs = labs.permute((0, 2, 3, 1)).contiguous() # (B, 3, H, W) -> (B, H, W, 3)
L, a, b = arrs[:, :, :, 0:1], arrs[:, :, :, 1:2], arrs[:, :, :, 2:]
y = (L + 16.) / 116.
x = (a / 500.) + y
z = y - (b / 200.)
invalid = z.data < 0
z[invalid] = 0
xyz = torch.cat([x, y, z], dim=3)
mask = xyz.data > 0.2068966
mask_xyz = xyz.clone()
mask_xyz[mask] = torch.pow(xyz[mask], 3.0)
mask_xyz[~mask] = (xyz[~mask] - 16.0 / 116.) / 7.787
xyz_ref_white = illuminants[illuminant][observer]
for i in range(C):
mask_xyz[:, :, :, i] = mask_xyz[:, :, :, i] * xyz_ref_white[i]
rgb_trans = torch.mm(mask_xyz.view(-1, 3), torch.from_numpy(rgb_from_xyz).type_as(xyz)).view(B, H, W, C)
rgb = rgb_trans.permute((0, 3, 1, 2)).contiguous()
mask = rgb.data > 0.0031308
mask_rgb = rgb.clone()
mask_rgb[mask] = 1.055 * torch.pow(rgb[mask], 1 / 2.4) - 0.055
mask_rgb[~mask] = rgb[~mask] * 12.92
neg_mask = mask_rgb.data < 0
large_mask = mask_rgb.data > 1
mask_rgb[neg_mask] = 0
mask_rgb[large_mask] = 1
return mask_rgb |