LMB/config.py at master · shaoboly/LMB · GitHub

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

import tensorflow as tf

from collections import namedtuple
#from tensorflow.python import debug as tf_debug


tf.set_random_seed(111)  # a seed value for randomness

flags = tf.flags
FLAGS = flags.FLAGS

flags.DEFINE_bool("debug", False, "Debug Mode")
## Required parameters
flags.DEFINE_string(
    "data_dir", None,
    "The input data dir. Should contain the .tsv files (or other data files) "
    "for the task.")

flags.DEFINE_string(
    "train_file", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")

flags.DEFINE_string(
    "dev_file", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")

flags.DEFINE_string(
    "test_file", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")

flags.DEFINE_string(
    "bert_config_file", None,
    "The config json file corresponding to the pre-trained BERT model. "
    "This specifies the model architecture.")

flags.DEFINE_string("gpus", "1,2", "The gpus use for train and test.")

flags.DEFINE_integer("candidate_num",9,"candidate number for match eval")

flags.DEFINE_string("task_name", None, "The name of the task to train.")

flags.DEFINE_string("model_name", "classify_model", "The name of the model to train.")

flags.DEFINE_string("vocab_file", None,
                    "The vocabulary file that the BERT model was trained on.")

flags.DEFINE_string(
    "output_dir", None,
    "The output directory where the model checkpoints will be written.")

## Other parameters

flags.DEFINE_string(
    "init_checkpoint", None,
    "Initial checkpoint (usually from a pre-trained BERT model).")

flags.DEFINE_bool(
    "do_lower_case", True,
    "Whether to lower case the input text. Should be True for uncased "
    "models and False for cased models.")

flags.DEFINE_integer(
    "max_seq_length", 128,
    "The maximum total input sequence length after WordPiece tokenization. "
    "Sequences longer than this will be truncated, and sequences shorter "
    "than this will be padded.")


flags.DEFINE_bool("do_train", False, "Whether to run training.")

flags.DEFINE_bool("do_eval", False, "Whether to run eval on the dev set.")

flags.DEFINE_bool("do_infer", False, "Whether to run infer on the dev set.")

flags.DEFINE_string("mode", 'train', 'must be one of train/eval/decode')

flags.DEFINE_integer("train_batch_size", 32, "Total batch size for training.")

flags.DEFINE_integer("eval_batch_size", 8, "Total batch size for eval.")

flags.DEFINE_float("learning_rate", 5e-5, "The initial learning rate for Adam.")
flags.DEFINE_float('learning_rate_decay_factor', 0.5, 'learning rate')

flags.DEFINE_float("num_train_epochs", 3.0,
                   "Total number of training epochs to perform.")

flags.DEFINE_float(
    "warmup_proportion", 0.1,
    "Proportion of training to perform linear learning rate warmup for. "
    "E.g., 0.1 = 10% of training.")

flags.DEFINE_integer("save_checkpoints_steps", 1000,
                     "How often to save the model checkpoint.")

flags.DEFINE_integer("iterations_per_loop", 1000,
                     "How many steps to make in each estimator call.")

flags.DEFINE_bool("use_tpu", False, "Whether to use TPU or GPU/CPU.")

tf.flags.DEFINE_string(
    "tpu_name", None,
    "The Cloud TPU to use for training. This should be either the name "
    "used when creating the Cloud TPU, or a grpc://ip.address.of.tpu:8470 "
    "url.")

tf.flags.DEFINE_string(
    "tpu_zone", None,
    "[Optional] GCE zone where the Cloud TPU is located in. If not "
    "specified, we will attempt to automatically detect the GCE project from "
    "metadata.")

tf.flags.DEFINE_string(
    "gcp_project", None,
    "[Optional] Project name for the Cloud TPU-enabled project. If not "
    "specified, we will attempt to automatically detect the GCE project from "
    "metadata.")

tf.flags.DEFINE_string("master", None, "[Optional] TensorFlow master URL.")

flags.DEFINE_integer(
    "num_tpu_cores", 8,
    "Only used if `use_tpu` is True. Total number of TPU cores to use.")


#for multi_task not use
flags.DEFINE_string(
    "train_file_multi", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")

flags.DEFINE_string(
    "dev_file_multi", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")

flags.DEFINE_string(
    "test_file_multi", None,
    "The input data dir. Should contain the .tsv files (or other data files) ")


def retype_FLAGS():
    # Make a namedtuple hps, containing the values of the hyperparameters that the model needs

    hps_dict = {}
    for key, val in FLAGS.__flags.items():  # for each flag
        hps_dict[key] = val._value  # add it to the dict
    hps = namedtuple("HParams", hps_dict.keys())._make(hps_dict.values())
    return hps

def generate_nametuple(hps_dict):
    return namedtuple("HParams", hps_dict.keys())._make(hps_dict.values())