forked from MAZiqing/FEDformer
-
Notifications
You must be signed in to change notification settings - Fork 0
/
run.py
174 lines (151 loc) · 9.93 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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
import argparse
import os
import sys
import torch
from exp.exp_main import Exp_Main
import random
import numpy as np
def main():
fix_seed = 2021
random.seed(fix_seed)
torch.manual_seed(fix_seed)
np.random.seed(fix_seed)
parser = argparse.ArgumentParser(description='Autoformer & Transformer family for Time Series Forecasting')
# basic config
parser.add_argument('--is_training', type=int, default=1, help='status')
parser.add_argument('--task_id', type=str, default='test', help='task id')
parser.add_argument('--model', type=str, default='FEDformer',
help='model name, options: [FEDformer, Autoformer, Informer, Transformer]')
# supplementary config for FEDformer model
parser.add_argument('--version', type=str, default='Fourier',
help='for FEDformer, there are two versions to choose, options: [Fourier, Wavelets]')
parser.add_argument('--mode_select', type=str, default='random',
help='for FEDformer, there are two mode selection method, options: [random, low]')
parser.add_argument('--modes', type=int, default=64, help='modes to be selected random 64')
parser.add_argument('--L', type=int, default=3, help='ignore level')
parser.add_argument('--base', type=str, default='legendre', help='mwt base')
parser.add_argument('--cross_activation', type=str, default='tanh',
help='mwt cross atention activation function tanh or softmax')
# data loader
parser.add_argument('--data', type=str, default='ETTh1', help='dataset type')
parser.add_argument('--root_path', type=str, default='./dataset/ETT/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='ETTh1.csv', help='data file')
parser.add_argument('--data_prefix', type=str, default='', help='data file')
parser.add_argument('--zeros_pct', type=float, default=1.0, help='percentage of zero only input sequence included')
parser.add_argument('--features', type=str, default='M',
help='forecasting task, options:[M, S, MS, MR]; M:multivariate predict multivariate, '
'S:univariate predict univariate, MS:multivariate predict univariate, MR:multivariate regression')
parser.add_argument('--target', type=str, default='OT', help='target feature in S or MS task')
parser.add_argument('--count_target', type=str, default='OT', help='target feature used to filter out zero only input sequence')
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('--detail_freq', type=str, default='h', help='like freq, but use in predict')
parser.add_argument('--checkpoints', type=str, default='./checkpoints/', help='location of model checkpoints')
# forecasting task
parser.add_argument('--seq_len', type=int, default=96, help='input sequence length')
parser.add_argument('--label_len', type=int, default=48, help='start token length')
parser.add_argument('--pred_len', type=int, default=96, help='prediction sequence length')
# parser.add_argument('--cross_activation', type=str, default='tanh'
# model define
parser.add_argument('--enc_in', type=int, default=7, help='encoder input size')
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('--d_model', type=int, default=512, help='dimension of model')
parser.add_argument('--n_heads', type=int, default=8, help='num of heads')
parser.add_argument('--e_layers', type=int, default=2, 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=2048, help='dimension of fcn')
parser.add_argument('--moving_avg', default=[24], 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('--dropout', type=float, default=0.05, help='dropout')
parser.add_argument('--embed', type=str, default='timeF',
help='time features encoding, options:[timeF, fixed, learned]')
parser.add_argument('--activation', type=str, default='gelu', help='activation')
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=3, help='experiments times')
parser.add_argument('--train_epochs', type=int, default=10, help='train epochs')
parser.add_argument('--batch_size', type=int, default=32, help='batch size of train input data')
parser.add_argument('--patience', type=int, default=3, help='early stopping patience')
parser.add_argument('--learning_rate', type=float, default=0.0001, 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='type1', help='adjust learning rate')
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', help='device ids of multi gpus')
args = parser.parse_args()
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 = '{}_{}_{}_modes{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(
args.task_id,
args.model,
args.mode_select,
args.modes,
args.data,
args.features,
args.seq_len,
args.label_len,
args.pred_len,
args.d_model,
args.n_heads,
args.e_layers,
args.d_layers,
args.d_ff,
args.factor,
args.embed,
args.distil,
args.des,
ii)
exp = Exp(args) # set experiments
print('>>>>>>>start training : {}>>>>>>>>>>>>>>>>>>>>>>>>>>'.format(setting))
# exp.train_regression(setting)
print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.test_regression(setting)
if args.do_predict:
print('>>>>>>>predicting : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.predict(setting, True)
torch.cuda.empty_cache()
else:
ii = 0
setting = '{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(args.task_id,
args.model,
args.data,
args.features,
args.seq_len,
args.label_len,
args.pred_len,
args.d_model,
args.n_heads,
args.e_layers,
args.d_layers,
args.d_ff,
args.factor,
args.embed,
args.distil,
args.des, ii)
exp = Exp(args) # set experiments
print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.test(setting, test=1)
torch.cuda.empty_cache()
if __name__ == "__main__":
main()