File size: 9,508 Bytes
79cf6ef |
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 |
# Copyright 2019 The TensorFlow 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.
# ==============================================================================
"""ImageNet preprocessing."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from absl import logging
import tensorflow.compat.v1 as tf
IMAGE_SIZE = 224
CROP_PADDING = 32
def distorted_bounding_box_crop(image_bytes,
bbox,
min_object_covered=0.1,
aspect_ratio_range=(0.75, 1.33),
area_range=(0.05, 1.0),
max_attempts=100,
scope=None):
"""Generates cropped_image using one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image_bytes: `Tensor` of binary image data.
bbox: `Tensor` of bounding boxes arranged `[1, num_boxes, coords]`
where each coordinate is [0, 1) and the coordinates are arranged
as `[ymin, xmin, ymax, xmax]`. If num_boxes is 0 then use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding
box supplied.
aspect_ratio_range: An optional list of `float`s. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `float`s. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional `str` for name scope.
Returns:
cropped image `Tensor`
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image_bytes, bbox]):
shape = tf.image.extract_jpeg_shape(image_bytes)
sample_distorted_bounding_box = tf.image.sample_distorted_bounding_box(
shape,
bounding_boxes=bbox,
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
bbox_begin, bbox_size, _ = sample_distorted_bounding_box
# Crop the image to the specified bounding box.
offset_y, offset_x, _ = tf.unstack(bbox_begin)
target_height, target_width, _ = tf.unstack(bbox_size)
crop_window = tf.stack([offset_y, offset_x, target_height, target_width])
image = tf.image.decode_and_crop_jpeg(image_bytes, crop_window, channels=3)
return image
def _at_least_x_are_equal(a, b, x):
"""At least `x` of `a` and `b` `Tensors` are equal."""
match = tf.equal(a, b)
match = tf.cast(match, tf.int32)
return tf.greater_equal(tf.reduce_sum(match), x)
def _decode_and_random_crop(image_bytes, image_size):
"""Make a random crop of image_size."""
bbox = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=tf.float32, shape=[1, 1, 4])
image = distorted_bounding_box_crop(
image_bytes,
bbox,
min_object_covered=0.1,
aspect_ratio_range=(3. / 4, 4. / 3.),
area_range=(0.08, 1.0),
max_attempts=10,
scope=None)
original_shape = tf.image.extract_jpeg_shape(image_bytes)
bad = _at_least_x_are_equal(original_shape, tf.shape(image), 3)
image = tf.cond(
bad,
lambda: _decode_and_center_crop(image_bytes, image_size),
lambda: tf.image.resize_bicubic([image], # pylint: disable=g-long-lambda
[image_size, image_size])[0])
return image
def _decode_and_center_crop(image_bytes, image_size):
"""Crops to center of image with padding then scales image_size."""
shape = tf.image.extract_jpeg_shape(image_bytes)
image_height = shape[0]
image_width = shape[1]
padded_center_crop_size = tf.cast(
((image_size / (image_size + CROP_PADDING)) *
tf.cast(tf.minimum(image_height, image_width), tf.float32)),
tf.int32)
offset_height = ((image_height - padded_center_crop_size) + 1) // 2
offset_width = ((image_width - padded_center_crop_size) + 1) // 2
crop_window = tf.stack([offset_height, offset_width,
padded_center_crop_size, padded_center_crop_size])
image = tf.image.decode_and_crop_jpeg(image_bytes, crop_window, channels=3)
image = tf.image.resize_bicubic([image], [image_size, image_size])[0]
return image
def _flip(image):
"""Random horizontal image flip."""
image = tf.image.random_flip_left_right(image)
return image
def preprocess_for_train(image_bytes, use_bfloat16, image_size=IMAGE_SIZE,
augment_name=None,
randaug_num_layers=None, randaug_magnitude=None):
"""Preprocesses the given image for evaluation.
Args:
image_bytes: `Tensor` representing an image binary of arbitrary size.
use_bfloat16: `bool` for whether to use bfloat16.
image_size: image size.
augment_name: `string` that is the name of the augmentation method
to apply to the image. `autoaugment` if AutoAugment is to be used or
`randaugment` if RandAugment is to be used. If the value is `None` no
augmentation method will be applied applied. See autoaugment.py for more
details.
randaug_num_layers: 'int', if RandAug is used, what should the number of
layers be. See autoaugment.py for detailed description.
randaug_magnitude: 'int', if RandAug is used, what should the magnitude
be. See autoaugment.py for detailed description.
Returns:
A preprocessed image `Tensor`.
"""
image = _decode_and_random_crop(image_bytes, image_size)
image = _flip(image)
image = tf.reshape(image, [image_size, image_size, 3])
image = tf.image.convert_image_dtype(
image, dtype=tf.bfloat16 if use_bfloat16 else tf.float32)
if augment_name:
try:
import autoaugment # pylint: disable=g-import-not-at-top
except ImportError as e:
logging.exception('Autoaugment is not supported in TF 2.x.')
raise e
logging.info('Apply AutoAugment policy %s', augment_name)
input_image_type = image.dtype
image = tf.clip_by_value(image, 0.0, 255.0)
image = tf.cast(image, dtype=tf.uint8)
if augment_name == 'autoaugment':
logging.info('Apply AutoAugment policy %s', augment_name)
image = autoaugment.distort_image_with_autoaugment(image, 'v0')
elif augment_name == 'randaugment':
image = autoaugment.distort_image_with_randaugment(
image, randaug_num_layers, randaug_magnitude)
else:
raise ValueError('Invalid value for augment_name: %s' % (augment_name))
image = tf.cast(image, dtype=input_image_type)
return image
def preprocess_for_eval(image_bytes, use_bfloat16, image_size=IMAGE_SIZE):
"""Preprocesses the given image for evaluation.
Args:
image_bytes: `Tensor` representing an image binary of arbitrary size.
use_bfloat16: `bool` for whether to use bfloat16.
image_size: image size.
Returns:
A preprocessed image `Tensor`.
"""
image = _decode_and_center_crop(image_bytes, image_size)
image = tf.reshape(image, [image_size, image_size, 3])
image = tf.image.convert_image_dtype(
image, dtype=tf.bfloat16 if use_bfloat16 else tf.float32)
return image
def preprocess_image(image_bytes,
is_training=False,
use_bfloat16=False,
image_size=IMAGE_SIZE,
augment_name=None,
randaug_num_layers=None,
randaug_magnitude=None):
"""Preprocesses the given image.
Args:
image_bytes: `Tensor` representing an image binary of arbitrary size.
is_training: `bool` for whether the preprocessing is for training.
use_bfloat16: `bool` for whether to use bfloat16.
image_size: image size.
augment_name: `string` that is the name of the augmentation method
to apply to the image. `autoaugment` if AutoAugment is to be used or
`randaugment` if RandAugment is to be used. If the value is `None` no
augmentation method will be applied applied. See autoaugment.py for more
details.
randaug_num_layers: 'int', if RandAug is used, what should the number of
layers be. See autoaugment.py for detailed description.
randaug_magnitude: 'int', if RandAug is used, what should the magnitude
be. See autoaugment.py for detailed description.
Returns:
A preprocessed image `Tensor` with value range of [0, 255].
"""
if is_training:
return preprocess_for_train(
image_bytes, use_bfloat16, image_size, augment_name,
randaug_num_layers, randaug_magnitude)
else:
return preprocess_for_eval(image_bytes, use_bfloat16, image_size)
|