-
Notifications
You must be signed in to change notification settings - Fork 17
/
run.py
151 lines (125 loc) · 8.56 KB
/
run.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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
import argparse
import os
import torch
from exp.exp_main import Exp_Main
import random
import numpy as np
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Autoformer & Transformer family for Time Series Forecasting')
# random seed
parser.add_argument('--random_seed', type=int, default=2021, help='random seed')
# basic config
parser.add_argument('--is_training', type=int, default=1, help='status')
parser.add_argument('--model_id', type=str, default='test', help='model id')
parser.add_argument('--model', type=str, default='TSMixer',
help='model name, options: [Autoformer, Informer, Transformer]')
# data loader
parser.add_argument('--data', type=str, default='ETTh1', help='dataset type')
parser.add_argument('--root_path', type=str, default='./dataset/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='ETTh1.csv', help='data file')
parser.add_argument('--features', type=str, default='M',
help='forecasting task, options:[M, S, MS]; M:multivariate predict multivariate, S:univariate predict univariate, MS:multivariate predict univariate')
parser.add_argument('--target', type=str, default='OT', help='target feature in S or MS task')
parser.add_argument('--freq', type=str, default='h',
help='freq for time features encoding, options:[s:secondly, t:minutely, h:hourly, d:daily, b:business days, w:weekly, m:monthly], you can also use more detailed freq like 15min or 3h')
parser.add_argument('--checkpoints', type=str, default='./checkpoints/', help='location of model checkpoints')
parser.add_argument('--embed', type=str, default='timeF',
help='time features encoding, options:[timeF, fixed, learned]')
# task
parser.add_argument('--seq_len', type=int, default=336, help='input sequence length')
parser.add_argument('--pred_len', type=int, default=336, help='prediction sequence length')
parser.add_argument('--enc_in', type=int, default=7, help='channel or dimension')
# model
parser.add_argument('--patch_len', type=int, default=16, help='patch length')
parser.add_argument('--stride', type=int, default=8, help='stride')
parser.add_argument('--padding_patch', default='end', help='None: None; end: padding on the end')
parser.add_argument('--d_model', type=int, default=256, help='dimension of model')
parser.add_argument('--dropout', type=float, default=0.3, help='dropout')
# Formers
parser.add_argument('--embed_type', type=int, default=0,
help='0: default 1: value embedding + temporal embedding + positional embedding 2: value embedding + temporal embedding 3: value embedding + positional embedding 4: value embedding')
parser.add_argument('--dec_in', type=int, default=7, help='decoder input size')
parser.add_argument('--c_out', type=int, default=7, help='output size')
parser.add_argument('--n_heads', type=int, default=4, help='num of heads')
parser.add_argument('--e_layers', type=int, default=3, help='num of encoder layers')
parser.add_argument('--d_layers', type=int, default=1, help='num of decoder layers')
parser.add_argument('--d_ff', type=int, default=128, help='dimension of fcn')
parser.add_argument('--moving_avg', type=int, default=25, help='window size of moving average')
parser.add_argument('--factor', type=int, default=1, help='attn factor')
parser.add_argument('--distil', action='store_false',
help='whether to use distilling in encoder, using this argument means not using distilling',
default=True)
parser.add_argument('--activation', type=str, default='gelu', help='activation')
parser.add_argument('--res_attention', type=bool, default=True, help='res attention')
# unused
# (just for the convenience of using this code framework, which is commonly used by most researchers in the field.)
parser.add_argument('--label_len', type=int, default=0, help='unused fot this model')
parser.add_argument('--output_attention', action='store_true', help='whether to output attention in ecoder')
parser.add_argument('--do_predict', action='store_true', help='whether to predict unseen future data')
# optimization
parser.add_argument('--num_workers', type=int, default=10, help='data loader num workers')
parser.add_argument('--itr', type=int, default=1, help='experiments times')
parser.add_argument('--train_epochs', type=int, default=10, help='train epochs')
parser.add_argument('--batch_size', type=int, default=256, help='batch size of train input data')
parser.add_argument('--patience', type=int, default=100, help='early stopping patience')
parser.add_argument('--learning_rate', type=float, default=0.001, help='optimizer learning rate')
parser.add_argument('--des', type=str, default='test', help='exp description')
parser.add_argument('--loss', type=str, default='mse', help='loss function')
parser.add_argument('--lradj', type=str, default='type3', help='adjust learning rate')
parser.add_argument('--pct_start', type=float, default=0.3, help='pct_start')
parser.add_argument('--use_amp', action='store_true', help='use automatic mixed precision training', default=False)
# GPU
parser.add_argument('--use_gpu', type=bool, default=True, help='use gpu')
parser.add_argument('--gpu', type=int, default=0, help='gpu')
parser.add_argument('--use_multi_gpu', action='store_true', help='use multiple gpus', default=False)
parser.add_argument('--devices', type=str, default='0,1,2,3', help='device ids of multile gpus')
parser.add_argument('--test_flop', action='store_true', default=False, help='See utils/tools for usage')
args = parser.parse_args()
# random seed
fix_seed = args.random_seed
random.seed(fix_seed)
torch.manual_seed(fix_seed)
np.random.seed(fix_seed)
args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False
if args.use_gpu and args.use_multi_gpu:
args.dvices = args.devices.replace(' ', '')
device_ids = args.devices.split(',')
args.device_ids = [int(id_) for id_ in device_ids]
args.gpu = args.device_ids[0]
print('Args in experiment:')
print(args)
Exp = Exp_Main
if args.is_training:
for ii in range(args.itr):
# setting record of experiments
setting = '{}_{}_{}_ft{}_sl{}_pl{}_eb{}_{}_{}'.format(args.model_id,
args.model,
args.data,
args.features,
args.seq_len,
args.pred_len,
args.embed,
args.des, ii)
exp = Exp(args) # set experiments
print('>>>>>>>start training : {}>>>>>>>>>>>>>>>>>>>>>>>>>>'.format(setting))
exp.train(setting)
print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.test(setting)
if args.do_predict:
print('>>>>>>>predicting : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.predict(setting, True)
torch.cuda.empty_cache()
else:
ii = 0
setting = '{}_{}_{}_ft{}_sl{}_pl{}_eb{}_{}_{}'.format(args.model_id,
args.model,
args.data,
args.features,
args.seq_len,
args.pred_len,
args.embed,
args.des, ii)
exp = Exp(args) # set experiments
print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.test(setting, test=1)
torch.cuda.empty_cache()