Spaces:
Running
Running
File size: 7,851 Bytes
d03866e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 |
import numpy as np
import torch
from torch import nn
import subprocess as sp
import os, math
class EarlyStoppingTorch:
"""Early stops the training if validation loss doesn't improve after a given patience."""
def __init__(self, save_path=None, patience=7, verbose=False, delta=0.0001):
"""
Args:
save_path :
patience (int): How long to wait after last time validation loss improved.
Default: 7
verbose (bool): If True, prints a message for each validation loss improvement.
Default: False
delta (float): Minimum change in the monitored quantity to qualify as an improvement.
Default: 0
"""
self.save_path = save_path
self.patience = patience
self.verbose = verbose
self.counter = 0
self.best_score = None
self.early_stop = False
self.val_loss_min = np.inf
self.delta = delta
def __call__(self, val_loss, model):
score = -val_loss
if self.best_score is None:
self.best_score = score
self.save_checkpoint(val_loss, model)
elif score < self.best_score + self.delta:
self.counter += 1
print(f'EarlyStopping counter: {self.counter} out of {self.patience}')
if self.counter >= self.patience:
self.early_stop = True
else:
self.best_score = score
self.save_checkpoint(val_loss, model)
self.counter = 0
def save_checkpoint(self, val_loss, model):
'''Saves model when validation loss decrease.'''
if self.verbose:
print(f'Validation loss decreased ({self.val_loss_min:.6f} --> {val_loss:.6f}). Saving model ...')
if self.save_path:
path = os.path.join(self.save_path, 'best_network.pth')
torch.save(model.state_dict(), path)
self.val_loss_min = val_loss
class PositionalEmbedding(nn.Module):
def __init__(self, d_model, max_len=5000):
super(PositionalEmbedding, self).__init__()
# Compute the positional encodings once in log space.
pe = torch.zeros(max_len, d_model).float()
pe.require_grad = False
position = torch.arange(0, max_len).float().unsqueeze(1)
div_term = (torch.arange(0, d_model, 2).float()
* -(math.log(10000.0) / d_model)).exp()
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0)
self.register_buffer('pe', pe)
def forward(self, x):
return self.pe[:, :x.size(1)]
class TokenEmbedding(nn.Module):
def __init__(self, c_in, d_model):
super(TokenEmbedding, self).__init__()
padding = 1 if torch.__version__ >= '1.5.0' else 2
self.tokenConv = nn.Conv1d(in_channels=c_in, out_channels=d_model,
kernel_size=3, padding=padding, padding_mode='circular', bias=False)
for m in self.modules():
if isinstance(m, nn.Conv1d):
nn.init.kaiming_normal_(
m.weight, mode='fan_in', nonlinearity='leaky_relu')
def forward(self, x):
x = self.tokenConv(x.permute(0, 2, 1)).transpose(1, 2)
return x
class TemporalEmbedding(nn.Module):
def __init__(self, d_model, embed_type='fixed', freq='h'):
super(TemporalEmbedding, self).__init__()
minute_size = 4
hour_size = 24
weekday_size = 7
day_size = 32
month_size = 13
Embed = FixedEmbedding if embed_type == 'fixed' else nn.Embedding
if freq == 't':
self.minute_embed = Embed(minute_size, d_model)
self.hour_embed = Embed(hour_size, d_model)
self.weekday_embed = Embed(weekday_size, d_model)
self.day_embed = Embed(day_size, d_model)
self.month_embed = Embed(month_size, d_model)
def forward(self, x):
x = x.long()
minute_x = self.minute_embed(x[:, :, 4]) if hasattr(
self, 'minute_embed') else 0.
hour_x = self.hour_embed(x[:, :, 3])
weekday_x = self.weekday_embed(x[:, :, 2])
day_x = self.day_embed(x[:, :, 1])
month_x = self.month_embed(x[:, :, 0])
return hour_x + weekday_x + day_x + month_x + minute_x
class FixedEmbedding(nn.Module):
def __init__(self, c_in, d_model):
super(FixedEmbedding, self).__init__()
w = torch.zeros(c_in, d_model).float()
w.require_grad = False
position = torch.arange(0, c_in).float().unsqueeze(1)
div_term = (torch.arange(0, d_model, 2).float()
* -(math.log(10000.0) / d_model)).exp()
w[:, 0::2] = torch.sin(position * div_term)
w[:, 1::2] = torch.cos(position * div_term)
self.emb = nn.Embedding(c_in, d_model)
self.emb.weight = nn.Parameter(w, requires_grad=False)
def forward(self, x):
return self.emb(x).detach()
class TimeFeatureEmbedding(nn.Module):
def __init__(self, d_model, embed_type='timeF', freq='h'):
super(TimeFeatureEmbedding, self).__init__()
freq_map = {'h': 4, 't': 5, 's': 6,
'm': 1, 'a': 1, 'w': 2, 'd': 3, 'b': 3}
d_inp = freq_map[freq]
self.embed = nn.Linear(d_inp, d_model, bias=False)
def forward(self, x):
return self.embed(x)
class DataEmbedding(nn.Module):
def __init__(self, c_in, d_model, embed_type='fixed', freq='h', dropout=0.1):
super(DataEmbedding, self).__init__()
self.value_embedding = TokenEmbedding(c_in=c_in, d_model=d_model)
self.position_embedding = PositionalEmbedding(d_model=d_model)
self.temporal_embedding = TemporalEmbedding(d_model=d_model, embed_type=embed_type,
freq=freq) if embed_type != 'timeF' else TimeFeatureEmbedding(
d_model=d_model, embed_type=embed_type, freq=freq)
self.dropout = nn.Dropout(p=dropout)
def forward(self, x, x_mark):
if x_mark is None:
x = self.value_embedding(x) + self.position_embedding(x)
else:
x = self.value_embedding(
x) + self.temporal_embedding(x_mark) + self.position_embedding(x)
return self.dropout(x)
def adjust_learning_rate(optimizer, epoch, lradj, learning_rate):
# lr = args.learning_rate * (0.2 ** (epoch // 2))
if lradj == 'type1':
lr_adjust = {epoch: learning_rate * (0.5 ** ((epoch - 1) // 1))}
elif lradj == 'type2':
lr_adjust = {
2: 5e-5, 4: 1e-5, 6: 5e-6, 8: 1e-6,
10: 5e-7, 15: 1e-7, 20: 5e-8
}
if epoch in lr_adjust.keys():
lr = lr_adjust[epoch]
for param_group in optimizer.param_groups:
param_group['lr'] = lr
print('Updating learning rate to {}'.format(lr))
def min_memory_id():
output = sp.check_output(["/usr/bin/nvidia-smi", "--query-gpu=memory.used", "--format=csv"])
memory = [int(s.split(" ")[0]) for s in output.decode().split("\n")[1:-1]]
assert len(memory) == torch.cuda.device_count()
return np.argmin(memory)
def get_gpu(cuda):
if cuda == True and torch.cuda.is_available():
try:
device = torch.device(f"cuda:{min_memory_id()}")
torch.cuda.set_device(device)
print(f"----- Using GPU {torch.cuda.current_device()} -----")
except:
device = torch.device("cuda")
print(f"----- Using GPU {torch.cuda.get_device_name()} -----")
else:
if cuda == True and not torch.cuda.is_available():
print("----- GPU is unavailable -----")
device = torch.device("cpu")
print("----- Using CPU -----")
return device |