# teacher
teacher = BiLSTMClassifier(n_feature=Config.n_features,
n_class=Config.n_classes,
n_hidden=Config.n_hidden_nodes,
num_layers=3)
teacher_save = torch.load(
Config.teacher_tar_fmt.format(plbl=Config.part_labeled))
teacher.load_state_dict(teacher_save['state_dict'])
teacher.to(device)
# ========================================================================
# student
student = LSTMClassifier(n_feature=Config.n_features,
n_class=Config.n_classes,
n_hidden=Config.n_hidden_nodes,
num_layers=3)
student.to(device)
# ========================================================================
# Pre evaluate if not shuffle
if not Config.shuffle:
teacher.eval()
target_logist_list = []
with torch.no_grad():
for pack_inputs, _ in tqdm(trainloader, desc="TeacherTagging"):
pack_inputs = pack_inputs.to(device)
target_logit = teacher(pack_inputs)
target_logist_list.append(target_logit)
else:
target_logist_list = None
# =======================================================================
# make optimizer and scheduler
import time
import torch
import torch.optim as optim
from torch.utils.data import DataLoader
from utils.dataloader import TIMITDataset
from utils.dataloader import pad_seqs_to_batch
from models.lstm import LSTMClassifier
import torch.backends.cudnn as cudnn
from utils import train
device = 'cuda' if torch.cuda.is_available() else 'cpu'
if device == 'cuda':
cudnn.benchmark = True
if __name__ == "__main__":
net = LSTMClassifier(39, 48, n_hidden=78, num_layers=3)
traindata = TIMITDataset(root="./data", split="train")
trainloader = DataLoader(dataset=traindata,
batch_size=100,
shuffle=True,
collate_fn=pad_seqs_to_batch)
# ==============================
optimizer = optim.Adam(net.parameters(), lr=0.05)
net.to(device)
# net.train()
for epoch in range(30):
train(trainloader, net, optimizer, device=device)
train_pairs = preprocess.read_pairs(mode='train', config=conf)
for pair in train_pairs:
x_train.append(pair[0])
y_train.append(pair[1])
val_pairs = preprocess.read_pairs(mode='test', config=conf)
for pair in val_pairs:
x_val.append(pair[0])
y_val.append(pair[1])
print('Train and Test Label distribution respectively:')
print(Counter(y_train), Counter(y_val))
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
model = LSTMClassifier(conf, embedding_wts, n_lables=len(labels_dict))
model = model.to(device)
criterion = nn.CrossEntropyLoss(reduction='sum')
optimizer = optim.Adadelta(model.parameters(),
lr=conf['lr'],
weight_decay=1e-5)
best_f1 = 0
for e in range(conf['n_epochs']):
losses = []
all_train_predictions = np.array([])
all_train_targets = np.array(y_train)
for iter in range(0, len(x_train), conf['batch_size']):
input_seq, input_lengths = preprocess.btmcd(
vocab, x_train[iter:iter + conf['batch_size']])
targets = torch.tensor(y_train[iter:iter + conf['batch_size']])