File size: 5,478 Bytes
f3507ef | 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 | # Copyright 2016 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.
# ==============================================================================
"""Provides utilities to preprocess images in CIFAR-10.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow.compat.v1 as tf
_PADDING = 4
def preprocess_for_train(image,
output_height,
output_width,
padding=_PADDING,
add_image_summaries=True,
use_grayscale=False):
"""Preprocesses the given image for training.
Note that the actual resizing scale is sampled from
[`resize_size_min`, `resize_size_max`].
Args:
image: A `Tensor` representing an image of arbitrary size.
output_height: The height of the image after preprocessing.
output_width: The width of the image after preprocessing.
padding: The amound of padding before and after each dimension of the image.
add_image_summaries: Enable image summaries.
use_grayscale: Whether to convert the image from RGB to grayscale.
Returns:
A preprocessed image.
"""
if add_image_summaries:
tf.summary.image('image', tf.expand_dims(image, 0))
# Transform the image to floats.
image = tf.to_float(image)
if use_grayscale:
image = tf.image.rgb_to_grayscale(image)
if padding > 0:
image = tf.pad(image, [[padding, padding], [padding, padding], [0, 0]])
# Randomly crop a [height, width] section of the image.
distorted_image = tf.random_crop(image,
[output_height, output_width, 3])
# Randomly flip the image horizontally.
distorted_image = tf.image.random_flip_left_right(distorted_image)
if add_image_summaries:
tf.summary.image('distorted_image', tf.expand_dims(distorted_image, 0))
# Because these operations are not commutative, consider randomizing
# the order their operation.
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)
# Subtract off the mean and divide by the variance of the pixels.
return tf.image.per_image_standardization(distorted_image)
def preprocess_for_eval(image,
output_height,
output_width,
add_image_summaries=True,
use_grayscale=False):
"""Preprocesses the given image for evaluation.
Args:
image: A `Tensor` representing an image of arbitrary size.
output_height: The height of the image after preprocessing.
output_width: The width of the image after preprocessing.
add_image_summaries: Enable image summaries.
use_grayscale: Whether to convert the image from RGB to grayscale.
Returns:
A preprocessed image.
"""
if add_image_summaries:
tf.summary.image('image', tf.expand_dims(image, 0))
# Transform the image to floats.
image = tf.to_float(image)
if use_grayscale:
image = tf.image.rgb_to_grayscale(image)
# Resize and crop if needed.
resized_image = tf.image.resize_image_with_crop_or_pad(image,
output_width,
output_height)
if add_image_summaries:
tf.summary.image('resized_image', tf.expand_dims(resized_image, 0))
# Subtract off the mean and divide by the variance of the pixels.
return tf.image.per_image_standardization(resized_image)
def preprocess_image(image,
output_height,
output_width,
is_training=False,
add_image_summaries=True,
use_grayscale=False):
"""Preprocesses the given image.
Args:
image: A `Tensor` representing an image of arbitrary size.
output_height: The height of the image after preprocessing.
output_width: The width of the image after preprocessing.
is_training: `True` if we're preprocessing the image for training and
`False` otherwise.
add_image_summaries: Enable image summaries.
use_grayscale: Whether to convert the image from RGB to grayscale.
Returns:
A preprocessed image.
"""
if is_training:
return preprocess_for_train(
image,
output_height,
output_width,
add_image_summaries=add_image_summaries,
use_grayscale=use_grayscale)
else:
return preprocess_for_eval(
image,
output_height,
output_width,
add_image_summaries=add_image_summaries,
use_grayscale=use_grayscale)
|