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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
|
# 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.
# ==============================================================================
"""run_config.py tests."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import copy
import json
from tensorflow.contrib.learn.python.learn.estimators import run_config as run_config_lib
from tensorflow.python.estimator import run_config as core_run_config
from tensorflow.python.platform import test
from tensorflow.python.training import server_lib
TEST_DIR = "test_dir"
ANOTHER_TEST_DIR = "another_test_dir"
RANDOM_SEED = 123
patch = test.mock.patch
class RunConfigTest(test.TestCase):
def test_instance_of_core_run_config(self):
config = run_config_lib.RunConfig()
self.assertTrue(isinstance(config, core_run_config.RunConfig))
def test_defaults_with_no_tf_config(self):
config = run_config_lib.RunConfig()
self.assertEqual(config.master, "")
self.assertEqual(config.task_id, 0)
self.assertEqual(config.num_ps_replicas, 0)
self.assertEqual(config.cluster_spec, {})
self.assertIsNone(config.task_type)
self.assertTrue(config.is_chief)
self.assertEqual(config.evaluation_master, "")
def test_values_from_tf_config(self):
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.WORKER: ["host3:3", "host4:4", "host5:5"]
},
"task": {
"type": run_config_lib.TaskType.WORKER,
"index": 1
}
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertEqual(config.master, "grpc://host4:4")
self.assertEqual(config.task_id, 1)
self.assertEqual(config.num_ps_replicas, 2)
self.assertEqual(config.num_worker_replicas, 3)
self.assertEqual(config.cluster_spec.as_dict(), tf_config["cluster"])
self.assertEqual(config.task_type, run_config_lib.TaskType.WORKER)
self.assertFalse(config.is_chief)
self.assertEqual(config.evaluation_master, "")
def test_explicitly_specified_values(self):
cluster_spec = {
run_config_lib.TaskType.PS: ["localhost:9990"],
"my_job_name": ["localhost:9991", "localhost:9992", "localhost:0"]
}
tf_config = {
"cluster": cluster_spec,
"task": {
"type": run_config_lib.TaskType.WORKER,
"index": 2
}
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig(
master="localhost:0", evaluation_master="localhost:9991")
self.assertEqual(config.master, "localhost:0")
self.assertEqual(config.task_id, 2)
self.assertEqual(config.num_ps_replicas, 1)
self.assertEqual(config.num_worker_replicas, 0)
self.assertEqual(config.cluster_spec, server_lib.ClusterSpec(cluster_spec))
self.assertEqual(config.task_type, run_config_lib.TaskType.WORKER)
self.assertFalse(config.is_chief)
self.assertEqual(config.evaluation_master, "localhost:9991")
def test_single_node_in_cluster_spec_produces_empty_master(self):
tf_config = {"cluster": {run_config_lib.TaskType.WORKER: ["host1:1"]}}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertEqual(config.master, "")
def test_no_task_type_produces_empty_master(self):
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.WORKER: ["host3:3", "host4:4", "host5:5"]
},
# Omits "task": {"type": "worker}
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertEqual(config.master, "")
def test_invalid_job_name_raises(self):
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.WORKER: ["host3:3", "host4:4", "host5:5"]
},
"task": {
"type": "not_in_cluster_spec"
}
}
expected_msg_regexp = "not_in_cluster_spec is not a valid task"
with patch.dict(
"os.environ",
{"TF_CONFIG": json.dumps(tf_config)}), self.assertRaisesRegexp(
ValueError, expected_msg_regexp):
run_config_lib.RunConfig()
def test_illegal_task_index_raises(self):
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.WORKER: ["host3:3", "host4:4", "host5:5"]
},
"task": {
"type": run_config_lib.TaskType.WORKER,
"index": 3
}
}
expected_msg_regexp = "3 is not a valid task_id"
with patch.dict(
"os.environ",
{"TF_CONFIG": json.dumps(tf_config)}), self.assertRaisesRegexp(
ValueError, expected_msg_regexp):
run_config_lib.RunConfig()
def test_is_chief_from_cloud_tf_config(self):
# is_chief should be true when ["task"]["type"] == "master" and
# index == 0 and ["task"]["environment"] == "cloud". Note that
# test_values_from_tf_config covers the non-master case.
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.MASTER: ["host3:3"],
run_config_lib.TaskType.WORKER: ["host4:4", "host5:5", "host6:6"]
},
"task": {
"type": run_config_lib.TaskType.MASTER,
"index": 0
},
"environment": "cloud"
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertTrue(config.is_chief)
def test_is_chief_from_noncloud_tf_config(self):
# is_chief should be true when ["task"]["type"] == "worker" and
# index == 0 if ["task"]["environment"] != "cloud".
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.MASTER: ["host3:3"],
run_config_lib.TaskType.WORKER: ["host4:4", "host5:5", "host6:6"]
},
"task": {
"type": run_config_lib.TaskType.WORKER,
"index": 0
},
"environment": "random"
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertTrue(config.is_chief)
# But task 0 for a job named "master" should not be.
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.MASTER: ["host3:3"],
run_config_lib.TaskType.WORKER: ["host4:4", "host5:5", "host6:6"]
},
"task": {
"type": run_config_lib.TaskType.MASTER,
"index": 0
},
"environment": "random"
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertFalse(config.is_chief)
def test_default_is_chief_from_tf_config_without_job_name(self):
tf_config = {"cluster": {}, "task": {}}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig()
self.assertTrue(config.is_chief)
def test_model_dir(self):
empty_config = run_config_lib.RunConfig()
self.assertIsNone(empty_config.model_dir)
config = run_config_lib.RunConfig(model_dir=TEST_DIR)
self.assertEqual(TEST_DIR, config.model_dir)
def test_replace(self):
config = run_config_lib.RunConfig(
tf_random_seed=RANDOM_SEED, model_dir=TEST_DIR)
self.assertEqual(TEST_DIR, config.model_dir)
self.assertEqual(RANDOM_SEED, config.tf_random_seed)
new_config = config.replace(model_dir=ANOTHER_TEST_DIR)
self.assertEqual(ANOTHER_TEST_DIR, new_config.model_dir)
self.assertEqual(RANDOM_SEED, new_config.tf_random_seed)
self.assertEqual(TEST_DIR, config.model_dir)
self.assertEqual(RANDOM_SEED, config.tf_random_seed)
with self.assertRaises(ValueError):
# tf_random_seed is not allowed to be replaced.
config.replace(tf_random_seed=RANDOM_SEED)
with self.assertRaises(ValueError):
config.replace(some_undefined_property=RANDOM_SEED)
def test_uid_for_different_configs(self):
config = run_config_lib.RunConfig(
tf_random_seed=RANDOM_SEED, model_dir=TEST_DIR)
expected_uid = config.uid()
# Check for 10 times, which should prove something.
for _ in range(10):
self.assertEqual(expected_uid, config.uid())
new_config = config.replace(model_dir=ANOTHER_TEST_DIR)
self.assertEqual(TEST_DIR, config.model_dir)
self.assertNotEqual(expected_uid, new_config.uid())
self.assertEqual(ANOTHER_TEST_DIR, new_config.model_dir)
def test_uid_for_whitelist(self):
whitelist = ["model_dir"]
config = run_config_lib.RunConfig(
tf_random_seed=RANDOM_SEED, model_dir=TEST_DIR)
expected_uid = config.uid(whitelist)
self.assertEqual(expected_uid, config.uid(whitelist))
new_config = config.replace(model_dir=ANOTHER_TEST_DIR)
self.assertEqual(TEST_DIR, config.model_dir)
self.assertEqual(expected_uid, new_config.uid(whitelist))
self.assertEqual(ANOTHER_TEST_DIR, new_config.model_dir)
def test_uid_for_default_whitelist(self):
config = run_config_lib.RunConfig(
tf_random_seed=11,
save_summary_steps=12,
save_checkpoints_steps=13,
save_checkpoints_secs=14,
session_config=15,
keep_checkpoint_max=16,
keep_checkpoint_every_n_hours=17)
self.assertEqual(11, config.tf_random_seed)
self.assertEqual(12, config.save_summary_steps)
self.assertEqual(13, config.save_checkpoints_steps)
self.assertEqual(14, config.save_checkpoints_secs)
self.assertEqual(15, config.session_config)
self.assertEqual(16, config.keep_checkpoint_max)
self.assertEqual(17, config.keep_checkpoint_every_n_hours)
new_config = run_config_lib.RunConfig(
tf_random_seed=21,
save_summary_steps=22,
save_checkpoints_steps=23,
save_checkpoints_secs=24,
session_config=25,
keep_checkpoint_max=26,
keep_checkpoint_every_n_hours=27)
self.assertEqual(config.uid(), new_config.uid())
# model_dir is not on the default whitelist.
self.assertNotEqual(config.uid(whitelist=[]),
new_config.uid(whitelist=[]))
new_config = new_config.replace(model_dir=ANOTHER_TEST_DIR)
self.assertNotEqual(config.uid(), new_config.uid())
def test_uid_for_deepcopy(self):
tf_config = {
"cluster": {
run_config_lib.TaskType.PS: ["host1:1", "host2:2"],
run_config_lib.TaskType.WORKER: ["host3:3", "host4:4", "host5:5"]
},
"task": {
"type": run_config_lib.TaskType.WORKER,
"index": 1
}
}
with patch.dict("os.environ", {"TF_CONFIG": json.dumps(tf_config)}):
config = run_config_lib.RunConfig(
tf_random_seed=RANDOM_SEED, model_dir=TEST_DIR)
self.assertEqual(config.cluster_spec.as_dict(), tf_config["cluster"])
config = run_config_lib.RunConfig(
tf_random_seed=RANDOM_SEED, model_dir=TEST_DIR)
expected_uid = config.uid()
new_config = copy.deepcopy(config)
self.assertEqual(expected_uid, new_config.uid())
if __name__ == "__main__":
test.main()
|
