Spaces:
Sleeping
Sleeping
File size: 7,483 Bytes
e1ccef5 |
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 |
from data_provider.data_factory import data_provider
from exp.exp_basic import Exp_Basic
from utils.tools import EarlyStopping, adjust_learning_rate, cal_accuracy
import torch
import torch.nn as nn
from torch import optim
import os
import time
import warnings
import numpy as np
import pdb
warnings.filterwarnings('ignore')
class Exp_Classification(Exp_Basic):
def __init__(self, args):
super(Exp_Classification, self).__init__(args)
def _build_model(self):
# model input depends on data
train_data, train_loader = self._get_data(flag='TRAIN')
test_data, test_loader = self._get_data(flag='TEST')
self.args.seq_len = max(train_data.max_seq_len, test_data.max_seq_len)
self.args.pred_len = 0
self.args.enc_in = train_data.feature_df.shape[1]
self.args.num_class = len(train_data.class_names)
# model init
model = self.model_dict[self.args.model].Model(self.args).float()
if self.args.use_multi_gpu and self.args.use_gpu:
model = nn.DataParallel(model, device_ids=self.args.device_ids)
return model
def _get_data(self, flag):
data_set, data_loader = data_provider(self.args, flag)
return data_set, data_loader
def _select_optimizer(self):
model_optim = optim.Adam(self.model.parameters(), lr=self.args.learning_rate)
return model_optim
def _select_criterion(self):
criterion = nn.CrossEntropyLoss()
return criterion
def vali(self, vali_data, vali_loader, criterion):
total_loss = []
preds = []
trues = []
self.model.eval()
with torch.no_grad():
for i, (batch_x, label, padding_mask) in enumerate(vali_loader):
batch_x = batch_x.float().to(self.device)
padding_mask = padding_mask.float().to(self.device)
label = label.to(self.device)
outputs = self.model(batch_x, padding_mask, None, None)
pred = outputs.detach().cpu()
loss = criterion(pred, label.long().squeeze().cpu())
total_loss.append(loss)
preds.append(outputs.detach())
trues.append(label)
total_loss = np.average(total_loss)
preds = torch.cat(preds, 0)
trues = torch.cat(trues, 0)
probs = torch.nn.functional.softmax(preds) # (total_samples, num_classes) est. prob. for each class and sample
predictions = torch.argmax(probs, dim=1).cpu().numpy() # (total_samples,) int class index for each sample
trues = trues.flatten().cpu().numpy()
accuracy = cal_accuracy(predictions, trues)
self.model.train()
return total_loss, accuracy
def train(self, setting):
train_data, train_loader = self._get_data(flag='TRAIN')
vali_data, vali_loader = self._get_data(flag='TEST')
test_data, test_loader = self._get_data(flag='TEST')
path = os.path.join(self.args.checkpoints, setting)
if not os.path.exists(path):
os.makedirs(path)
time_now = time.time()
train_steps = len(train_loader)
early_stopping = EarlyStopping(patience=self.args.patience, verbose=True)
model_optim = self._select_optimizer()
criterion = self._select_criterion()
for epoch in range(self.args.train_epochs):
iter_count = 0
train_loss = []
self.model.train()
epoch_time = time.time()
for i, (batch_x, label, padding_mask) in enumerate(train_loader):
iter_count += 1
model_optim.zero_grad()
batch_x = batch_x.float().to(self.device)
padding_mask = padding_mask.float().to(self.device)
label = label.to(self.device)
outputs = self.model(batch_x, padding_mask, None, None)
loss = criterion(outputs, label.long().squeeze(-1))
train_loss.append(loss.item())
if (i + 1) % 100 == 0:
print("\titers: {0}, epoch: {1} | loss: {2:.7f}".format(i + 1, epoch + 1, loss.item()))
speed = (time.time() - time_now) / iter_count
left_time = speed * ((self.args.train_epochs - epoch) * train_steps - i)
print('\tspeed: {:.4f}s/iter; left time: {:.4f}s'.format(speed, left_time))
iter_count = 0
time_now = time.time()
loss.backward()
nn.utils.clip_grad_norm_(self.model.parameters(), max_norm=4.0)
model_optim.step()
print("Epoch: {} cost time: {}".format(epoch + 1, time.time() - epoch_time))
train_loss = np.average(train_loss)
vali_loss, val_accuracy = self.vali(vali_data, vali_loader, criterion)
test_loss, test_accuracy = self.vali(test_data, test_loader, criterion)
print(
"Epoch: {0}, Steps: {1} | Train Loss: {2:.3f} Vali Loss: {3:.3f} Vali Acc: {4:.3f} Test Loss: {5:.3f} Test Acc: {6:.3f}"
.format(epoch + 1, train_steps, train_loss, vali_loss, val_accuracy, test_loss, test_accuracy))
early_stopping(-val_accuracy, self.model, path)
if early_stopping.early_stop:
print("Early stopping")
break
if (epoch + 1) % 5 == 0:
adjust_learning_rate(model_optim, epoch + 1, self.args)
best_model_path = path + '/' + 'checkpoint.pth'
self.model.load_state_dict(torch.load(best_model_path))
return self.model
def test(self, setting, test=0):
test_data, test_loader = self._get_data(flag='TEST')
if test:
print('loading model')
self.model.load_state_dict(torch.load(os.path.join('./checkpoints/' + setting, 'checkpoint.pth')))
preds = []
trues = []
folder_path = './test_results/' + setting + '/'
if not os.path.exists(folder_path):
os.makedirs(folder_path)
self.model.eval()
with torch.no_grad():
for i, (batch_x, label, padding_mask) in enumerate(test_loader):
batch_x = batch_x.float().to(self.device)
padding_mask = padding_mask.float().to(self.device)
label = label.to(self.device)
outputs = self.model(batch_x, padding_mask, None, None)
preds.append(outputs.detach())
trues.append(label)
preds = torch.cat(preds, 0)
trues = torch.cat(trues, 0)
print('test shape:', preds.shape, trues.shape)
probs = torch.nn.functional.softmax(preds) # (total_samples, num_classes) est. prob. for each class and sample
predictions = torch.argmax(probs, dim=1).cpu().numpy() # (total_samples,) int class index for each sample
trues = trues.flatten().cpu().numpy()
accuracy = cal_accuracy(predictions, trues)
# result save
folder_path = './results/' + setting + '/'
if not os.path.exists(folder_path):
os.makedirs(folder_path)
print('accuracy:{}'.format(accuracy))
file_name='result_classification.txt'
f = open(os.path.join(folder_path,file_name), 'a')
f.write(setting + " \n")
f.write('accuracy:{}'.format(accuracy))
f.write('\n')
f.write('\n')
f.close()
return
|