-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrun.py
151 lines (121 loc) · 8.03 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 ExpMain
import numpy as np
from utils.logger import make_logger
from utils.recorder import Recorder
from utils.tools import fix_seed
import json
if __name__ == '__main__':
fix_seed()
parser = argparse.ArgumentParser(description='Time Series Forecasting')
# basic config
parser.add_argument('--exp_name', type=str, required=True, default='test', help='exp_name')
parser.add_argument('--model', type=str, required=True, default='TDformer',
help='model name, options: [Autoformer, Informer, Transformer, ns_FEDformer, ns_Autoformer, TDformer]')
parser.add_argument('--result_dir', type=str, default='./save/results', help='result path')
parser.add_argument('--checkpoint_dir', type=str, default='./save/checkpoints', help='checkpoint path')
# data loader
parser.add_argument('--version', type=str, default='Wavelets',
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')
parser.add_argument('--data', type=str, required=True, default='custom', help='dataset type')
parser.add_argument('--root_path', type=str, default='./data/ETT/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='result.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='t',
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')
# 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')
# model define
parser.add_argument('--enc_in', type=int, default=5, help='encoder input size')
parser.add_argument('--dec_in', type=int, default=5, help='decoder input size')
parser.add_argument('--c_out', type=int, default=5, 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', 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=0.05, 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('--output_stl', default='False')
parser.add_argument('--temp', default=1)
parser.add_argument('--activation', default='softmax')
# optimization
parser.add_argument('--num_workers', type=int, default=8, 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('--optimizer', type=str, default='adam', choices=['sgd', 'adam', 'adamw'], help='optimizer')
parser.add_argument('--lr', type=float, default=0.0001, help='optimizer learning rate')
parser.add_argument('--lr_decay_factor', type=float, default=0.5, help='optimizer learning rate decay factor')
parser.add_argument('--loss', type=str, default='MSE')
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)
# EMA
parser.add_argument('--use_ema', action='store_true')
parser.add_argument('--epsilon', type=float, default=0.01)
parser.add_argument('--moving_average_decay', type=float, default=0.99)
parser.add_argument('--standing_steps', type=int, default=100)
parser.add_argument('--start_iter', type=int, default=300)
parser.add_argument('--ema_loss', type=str, default='BDFMSE')
parser.add_argument('--ema_eval_model', type=str, default='target', choices=['source', 'target'])
# 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')
# de-stationary projector params
parser.add_argument('--p_hidden_dims', type=int, nargs='+', default=[128, 128],
help='hidden layer dimensions of projector (List)')
parser.add_argument('--p_hidden_layers', type=int, default=2, help='number of hidden layers in projector')
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]
os.makedirs(os.path.join(args.checkpoint_dir, args.exp_name), exist_ok=True)
with open(os.path.join(args.checkpoint_dir, args.exp_name, 'arguments.json'), 'w') as f:
json.dump(args.__dict__, f, indent=2)
logger = make_logger(os.path.join(args.checkpoint_dir, args.exp_name, f'{args.exp_name}.log'))
logger.info('Args in experiment:')
logger.info(args)
valid_recorder = Recorder(args, 'valid_metrics')
test_recorder = Recorder(args, 'test_metrics')
Exp = ExpMain
for ii in range(args.itr):
exp = Exp(args, ii, logger) # set experiments
logger.info('>>>>>>> training <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<')
exp.train()
logger.info('>>>>>>> testing <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<')
valid_metric_dict = exp.test('valid')
valid_recorder.writerow(ii, valid_metric_dict)
test_metric_dict = exp.test('test')
test_recorder.writerow(ii, test_metric_dict)
torch.cuda.empty_cache()
valid_recorder.write_statistics()
valid_recorder.close()
test_recorder.write_statistics()
test_recorder.close()