File size: 9,836 Bytes
7b7527a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 |
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import cv2
import numpy as np
def decode_image(im_file, im_info):
"""read rgb image
Args:
im_file (str|np.ndarray): input can be image path or np.ndarray
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
if isinstance(im_file, str):
with open(im_file, 'rb') as f:
im_read = f.read()
data = np.frombuffer(im_read, dtype='uint8')
im = cv2.imdecode(data, 1) # BGR mode, but need RGB mode
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
else:
im = im_file
im_info['im_shape'] = np.array(im.shape[:2], dtype=np.float32)
im_info['scale_factor'] = np.array([1., 1.], dtype=np.float32)
return im, im_info
class Resize(object):
"""resize image by target_size and max_size
Args:
target_size (int): the target size of image
keep_ratio (bool): whether keep_ratio or not, default true
interp (int): method of resize
"""
def __init__(self, target_size, keep_ratio=True, interp=cv2.INTER_LINEAR):
if isinstance(target_size, int):
target_size = [target_size, target_size]
self.target_size = target_size
self.keep_ratio = keep_ratio
self.interp = interp
def __call__(self, im, im_info):
"""
Args:
im (np.ndarray): image (np.ndarray)
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
assert len(self.target_size) == 2
assert self.target_size[0] > 0 and self.target_size[1] > 0
im_channel = im.shape[2]
im_scale_y, im_scale_x = self.generate_scale(im)
im = cv2.resize(
im,
None,
None,
fx=im_scale_x,
fy=im_scale_y,
interpolation=self.interp)
im_info['im_shape'] = np.array(im.shape[:2]).astype('float32')
im_info['scale_factor'] = np.array(
[im_scale_y, im_scale_x]).astype('float32')
return im, im_info
def generate_scale(self, im):
"""
Args:
im (np.ndarray): image (np.ndarray)
Returns:
im_scale_x: the resize ratio of X
im_scale_y: the resize ratio of Y
"""
origin_shape = im.shape[:2]
im_c = im.shape[2]
if self.keep_ratio:
im_size_min = np.min(origin_shape)
im_size_max = np.max(origin_shape)
target_size_min = np.min(self.target_size)
target_size_max = np.max(self.target_size)
im_scale = float(target_size_min) / float(im_size_min)
if np.round(im_scale * im_size_max) > target_size_max:
im_scale = float(target_size_max) / float(im_size_max)
im_scale_x = im_scale
im_scale_y = im_scale
else:
resize_h, resize_w = self.target_size
im_scale_y = resize_h / float(origin_shape[0])
im_scale_x = resize_w / float(origin_shape[1])
return im_scale_y, im_scale_x
class NormalizeImage(object):
"""normalize image
Args:
mean (list): im - mean
std (list): im / std
is_scale (bool): whether need im / 255
is_channel_first (bool): if True: image shape is CHW, else: HWC
"""
def __init__(self, mean, std, is_scale=True):
self.mean = mean
self.std = std
self.is_scale = is_scale
def __call__(self, im, im_info):
"""
Args:
im (np.ndarray): image (np.ndarray)
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
im = im.astype(np.float32, copy=False)
mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
std = np.array(self.std)[np.newaxis, np.newaxis, :]
if self.is_scale:
im = im / 255.0
im -= mean
im /= std
return im, im_info
class Permute(object):
"""permute image
Args:
to_bgr (bool): whether convert RGB to BGR
channel_first (bool): whether convert HWC to CHW
"""
def __init__(self, ):
super(Permute, self).__init__()
def __call__(self, im, im_info):
"""
Args:
im (np.ndarray): image (np.ndarray)
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
im = im.transpose((2, 0, 1)).copy()
return im, im_info
class PadStride(object):
""" padding image for model with FPN, instead PadBatch(pad_to_stride) in original config
Args:
stride (bool): model with FPN need image shape % stride == 0
"""
def __init__(self, stride=0):
self.coarsest_stride = stride
def __call__(self, im, im_info):
"""
Args:
im (np.ndarray): image (np.ndarray)
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
coarsest_stride = self.coarsest_stride
if coarsest_stride <= 0:
return im, im_info
im_c, im_h, im_w = im.shape
pad_h = int(np.ceil(float(im_h) / coarsest_stride) * coarsest_stride)
pad_w = int(np.ceil(float(im_w) / coarsest_stride) * coarsest_stride)
padding_im = np.zeros((im_c, pad_h, pad_w), dtype=np.float32)
padding_im[:, :im_h, :im_w] = im
return padding_im, im_info
class LetterBoxResize(object):
def __init__(self, target_size):
"""
Resize image to target size, convert normalized xywh to pixel xyxy
format ([x_center, y_center, width, height] -> [x0, y0, x1, y1]).
Args:
target_size (int|list): image target size.
"""
super(LetterBoxResize, self).__init__()
if isinstance(target_size, int):
target_size = [target_size, target_size]
self.target_size = target_size
def letterbox(self, img, height, width, color=(127.5, 127.5, 127.5)):
# letterbox: resize a rectangular image to a padded rectangular
shape = img.shape[:2] # [height, width]
ratio_h = float(height) / shape[0]
ratio_w = float(width) / shape[1]
ratio = min(ratio_h, ratio_w)
new_shape = (round(shape[1] * ratio),
round(shape[0] * ratio)) # [width, height]
padw = (width - new_shape[0]) / 2
padh = (height - new_shape[1]) / 2
top, bottom = round(padh - 0.1), round(padh + 0.1)
left, right = round(padw - 0.1), round(padw + 0.1)
img = cv2.resize(
img, new_shape, interpolation=cv2.INTER_AREA) # resized, no border
img = cv2.copyMakeBorder(
img, top, bottom, left, right, cv2.BORDER_CONSTANT,
value=color) # padded rectangular
return img, ratio, padw, padh
def __call__(self, im, im_info):
"""
Args:
im (np.ndarray): image (np.ndarray)
im_info (dict): info of image
Returns:
im (np.ndarray): processed image (np.ndarray)
im_info (dict): info of processed image
"""
assert len(self.target_size) == 2
assert self.target_size[0] > 0 and self.target_size[1] > 0
height, width = self.target_size
h, w = im.shape[:2]
im, ratio, padw, padh = self.letterbox(im, height=height, width=width)
new_shape = [round(h * ratio), round(w * ratio)]
im_info['im_shape'] = np.array(new_shape, dtype=np.float32)
im_info['scale_factor'] = np.array([ratio, ratio], dtype=np.float32)
return im, im_info
class Pad(object):
def __init__(self, size, fill_value=[114.0, 114.0, 114.0]):
"""
Pad image to a specified size.
Args:
size (list[int]): image target size
fill_value (list[float]): rgb value of pad area, default (114.0, 114.0, 114.0)
"""
super(Pad, self).__init__()
if isinstance(size, int):
size = [size, size]
self.size = size
self.fill_value = fill_value
def __call__(self, im, im_info):
im_h, im_w = im.shape[:2]
h, w = self.size
if h == im_h and w == im_w:
im = im.astype(np.float32)
return im, im_info
canvas = np.ones((h, w, 3), dtype=np.float32)
canvas *= np.array(self.fill_value, dtype=np.float32)
canvas[0:im_h, 0:im_w, :] = im.astype(np.float32)
im = canvas
return im, im_info
def preprocess(im, preprocess_ops):
# process image by preprocess_ops
im_info = {
'scale_factor': np.array(
[1., 1.], dtype=np.float32),
'im_shape': None,
}
im, im_info = decode_image(im, im_info)
for operator in preprocess_ops:
im, im_info = operator(im, im_info)
return im, im_info
|