forked from thuml/iTransformer
-
Notifications
You must be signed in to change notification settings - Fork 0
/
run.py
166 lines (146 loc) · 8.94 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
import argparse
import torch
from experiments.exp_long_term_forecasting import Exp_Long_Term_Forecast
from experiments.exp_long_term_forecasting_partial import Exp_Long_Term_Forecast_Partial
import random
import numpy as np
if __name__ == '__main__':
fix_seed = 2023
random.seed(fix_seed)
torch.manual_seed(fix_seed)
np.random.seed(fix_seed)
parser = argparse.ArgumentParser(description='iTransformer')
# basic config
parser.add_argument('--is_training', type=int, required=True, default=1, help='status')
parser.add_argument('--model_id', type=str, required=True, default='test', help='model id')
parser.add_argument('--model', type=str, required=True, default='iTransformer',
help='model name, options: [iTransformer, iInformer, iReformer, iFlowformer, iFlashformer]')
# data loader
parser.add_argument('--data', type=str, required=True, default='custom', help='dataset type')
parser.add_argument('--root_path', type=str, default='./data/electricity/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='electricity.csv', help='data csv 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')
# 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') # no longer needed in inverted Transformers
parser.add_argument('--pred_len', type=int, default=96, help='prediction sequence length')
# 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') # applicable on arbitrary number of variates in inverted Transformers
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', 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('--dropout', type=float, default=0.1, 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=1, 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='0,1,2,3', help='device ids of multile gpus')
# iTransformer
parser.add_argument('--exp_name', type=str, required=False, default='MTSF',
help='experiemnt name, options:[MTSF, partial_train]')
parser.add_argument('--channel_independence', type=bool, default=False, help='whether to use channel_independence mechanism')
parser.add_argument('--inverse', action='store_true', help='inverse output data', default=False)
parser.add_argument('--class_strategy', type=str, default='projection', help='projection/average/cls_token')
parser.add_argument('--target_root_path', type=str, default='./data/electricity/', help='root path of the data file')
parser.add_argument('--target_data_path', type=str, default='electricity.csv', help='data file')
parser.add_argument('--efficient_training', type=bool, default=False, help='whether to use efficient_training (exp_name should be partial train)') # See Figure 8 of our paper for the detail
parser.add_argument('--use_norm', type=int, default=True, help='use norm and denorm')
parser.add_argument('--partial_start_index', type=int, default=0, help='the start index of variates for partial training, '
'you can select [partial_start_index, min(enc_in + partial_start_index, N)]')
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.devices = 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)
if args.exp_name == 'partial_train': # See Figure 8 of our paper, for the detail
Exp = Exp_Long_Term_Forecast_Partial
else: # MTSF: multivariate time series forecasting
Exp = Exp_Long_Term_Forecast
if args.is_training:
for ii in range(args.itr):
# setting record of experiments
setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(
args.model_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,
args.class_strategy, 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{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(
args.model_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,
args.class_strategy, ii)
exp = Exp(args) # set experiments
print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
exp.test(setting, test=1)
torch.cuda.empty_cache()