forked from mrharicot/monodepth
-
Notifications
You must be signed in to change notification settings - Fork 0
/
monodepth_dataloader.py
115 lines (90 loc) · 5.07 KB
/
monodepth_dataloader.py
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
# Copyright UCL Business plc 2017. Patent Pending. All rights reserved.
#
# The MonoDepth Software is licensed under the terms of the UCLB ACP-A licence
# which allows for non-commercial use only, the full terms of which are made
# available in the LICENSE file.
#
# For any other use of the software not covered by the UCLB ACP-A Licence,
# please contact [email protected]
"""Monodepth data loader.
"""
from __future__ import absolute_import, division, print_function
import tensorflow as tf
def string_length_tf(t):
return tf.py_func(len, [t], [tf.int64])
class MonodepthDataloader(object):
"""monodepth dataloader"""
def __init__(self, data_path, filenames_file, params, dataset, mode):
self.data_path = data_path
self.params = params
self.dataset = dataset
self.mode = mode
self.left_image_batch = None
self.right_image_batch = None
input_queue = tf.train.string_input_producer([filenames_file], shuffle=False)
line_reader = tf.TextLineReader()
_, line = line_reader.read(input_queue)
split_line = tf.string_split([line]).values
# we load only one image for test, except if we trained a stereo model
if mode == 'test' and not self.params.do_stereo:
left_image_path = tf.string_join([self.data_path, split_line[0]])
left_image_o = self.read_image(left_image_path)
else:
left_image_path = tf.string_join([self.data_path, split_line[0]])
right_image_path = tf.string_join([self.data_path, split_line[1]])
left_image_o = self.read_image(left_image_path)
right_image_o = self.read_image(right_image_path)
if mode == 'train':
# randomly flip images
do_flip = tf.random_uniform([], 0, 1)
left_image = tf.cond(do_flip > 0.5, lambda: tf.image.flip_left_right(right_image_o), lambda: left_image_o)
right_image = tf.cond(do_flip > 0.5, lambda: tf.image.flip_left_right(left_image_o), lambda: right_image_o)
# randomly augment images
do_augment = tf.random_uniform([], 0, 1)
left_image, right_image = tf.cond(do_augment > 0.5, lambda: self.augment_image_pair(left_image, right_image), lambda: (left_image, right_image))
left_image.set_shape( [None, None, 3])
right_image.set_shape([None, None, 3])
# capacity = min_after_dequeue + (num_threads + a small safety margin) * batch_size
min_after_dequeue = 2048
capacity = min_after_dequeue + 4 * params.batch_size
self.left_image_batch, self.right_image_batch = tf.train.shuffle_batch([left_image, right_image],
params.batch_size, capacity, min_after_dequeue, params.num_threads)
elif mode == 'test':
self.left_image_batch = tf.stack([left_image_o, tf.image.flip_left_right(left_image_o)], 0)
self.left_image_batch.set_shape( [2, None, None, 3])
if self.params.do_stereo:
self.right_image_batch = tf.stack([right_image_o, tf.image.flip_left_right(right_image_o)], 0)
self.right_image_batch.set_shape( [2, None, None, 3])
def augment_image_pair(self, left_image, right_image):
# randomly shift gamma
random_gamma = tf.random_uniform([], 0.8, 1.2)
left_image_aug = left_image ** random_gamma
right_image_aug = right_image ** random_gamma
# randomly shift brightness
random_brightness = tf.random_uniform([], 0.5, 2.0)
left_image_aug = left_image_aug * random_brightness
right_image_aug = right_image_aug * random_brightness
# randomly shift color
random_colors = tf.random_uniform([3], 0.8, 1.2)
white = tf.ones([tf.shape(left_image)[0], tf.shape(left_image)[1]])
color_image = tf.stack([white * random_colors[i] for i in range(3)], axis=2)
left_image_aug *= color_image
right_image_aug *= color_image
# saturate
left_image_aug = tf.clip_by_value(left_image_aug, 0, 1)
right_image_aug = tf.clip_by_value(right_image_aug, 0, 1)
return left_image_aug, right_image_aug
def read_image(self, image_path):
# tf.decode_image does not return the image size, this is an ugly workaround to handle both jpeg and png
path_length = string_length_tf(image_path)[0]
file_extension = tf.substr(image_path, path_length - 3, 3)
file_cond = tf.equal(file_extension, 'jpg')
image = tf.cond(file_cond, lambda: tf.image.decode_jpeg(tf.read_file(image_path)), lambda: tf.image.decode_png(tf.read_file(image_path)))
# if the dataset is cityscapes, we crop the last fifth to remove the car hood
if self.dataset == 'cityscapes':
o_height = tf.shape(image)[0]
crop_height = (o_height * 4) // 5
image = image[:crop_height,:,:]
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize_images(image, [self.params.height, self.params.width], tf.image.ResizeMethod.AREA)
return image