-
Notifications
You must be signed in to change notification settings - Fork 59
/
data_util.py
129 lines (109 loc) · 4.18 KB
/
data_util.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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
'''
this file is modified from keras implemention of data process multi-threading,
see https://github.com/fchollet/keras/blob/master/keras/utils/data_utils.py
'''
import time
import numpy as np
import threading
import multiprocessing
try:
import queue
except ImportError:
import Queue as queue
class GeneratorEnqueuer():
"""Builds a queue out of a data generator.
Used in `fit_generator`, `evaluate_generator`, `predict_generator`.
# Arguments
generator: a generator function which endlessly yields data
use_multiprocessing: use multiprocessing if True, otherwise threading
wait_time: time to sleep in-between calls to `put()`
random_seed: Initial seed for workers,
will be incremented by one for each workers.
"""
def __init__(self, generator,
use_multiprocessing=False,
wait_time=0.05,
random_seed=None):
self.wait_time = wait_time
self._generator = generator
self._use_multiprocessing = use_multiprocessing
self._threads = []
self._stop_event = None
self.queue = None
self.random_seed = random_seed
def start(self, workers=1, max_queue_size=10):
"""Kicks off threads which add data from the generator into the queue.
# Arguments
workers: number of worker threads
max_queue_size: queue size
(when full, threads could block on `put()`)
"""
def data_generator_task():
while not self._stop_event.is_set():
try:
if self._use_multiprocessing or self.queue.qsize() < max_queue_size:
generator_output = next(self._generator)
self.queue.put(generator_output)
else:
time.sleep(self.wait_time)
except Exception:
self._stop_event.set()
raise
try:
if self._use_multiprocessing:
self.queue = multiprocessing.Queue(maxsize=max_queue_size)
self._stop_event = multiprocessing.Event()
else:
self.queue = queue.Queue()
self._stop_event = threading.Event()
for _ in range(workers):
if self._use_multiprocessing:
# Reset random seed else all children processes
# share the same seed
np.random.seed(self.random_seed)
thread = multiprocessing.Process(target=data_generator_task)
thread.daemon = True
if self.random_seed is not None:
self.random_seed += 1
else:
thread = threading.Thread(target=data_generator_task)
self._threads.append(thread)
thread.start()
except:
self.stop()
raise
def is_running(self):
return self._stop_event is not None and not self._stop_event.is_set()
def stop(self, timeout=None):
"""Stops running threads and wait for them to exit, if necessary.
Should be called by the same thread which called `start()`.
# Arguments
timeout: maximum time to wait on `thread.join()`.
"""
if self.is_running():
self._stop_event.set()
for thread in self._threads:
if thread.is_alive():
if self._use_multiprocessing:
thread.terminate()
else:
thread.join(timeout)
if self._use_multiprocessing:
if self.queue is not None:
self.queue.close()
self._threads = []
self._stop_event = None
self.queue = None
def get(self):
"""Creates a generator to extract data from the queue.
Skip the data if it is `None`.
# Returns
A generator
"""
while self.is_running():
if not self.queue.empty():
inputs = self.queue.get()
if inputs is not None:
yield inputs
else:
time.sleep(self.wait_time)