def train():
EMBEDDING_DIM = 100
HIDDEN_DIM = 50
EPOCH = 100
BATCH_SIZE = 10
text_field = data.Field(lower=True)
label_field = data.Field(sequential=False)
train_iter, dev_iter, test_iter = classification_datasets.load_mr(
text_field, label_field, batch_size=BATCH_SIZE)
# text_field.vocab.load_vectors('glove.6B.50d')
text_field.vocab.load_vectors('glove.6B.100d')
best_dev_acc = 0.0
model = LSTMClassifier(embedding_dim=EMBEDDING_DIM,
hidden_dim=HIDDEN_DIM,
vocab_size=len(text_field.vocab),
label_size=len(label_field.vocab) - 1,
batch_size=BATCH_SIZE)
model.word_embeddings.weight.data = text_field.vocab.vectors
loss_function = nn.NLLLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
with missinglink_project.create_experiment(
model,
display_name='LSTM Sentence Classifier PyTorch',
optimizer=optimizer,
metrics={
'Loss': loss_function,
'Accuracy': get_accuracy,
}) as experiment:
wrapped_loss_function = experiment.metrics['Loss']
global wrapped_accuracy_function
wrapped_accuracy_function = experiment.metrics['Accuracy']
no_up = 0
for i in experiment.epoch_loop(
condition=lambda epoch: epoch < EPOCH and no_up < 10):
print('epoch: %d start!' % i)
train_epoch(experiment, model, train_iter, wrapped_loss_function,
optimizer, text_field, label_field, i)
print('now best dev acc:', best_dev_acc)
dev_acc = evaluate(experiment, model, dev_iter,
wrapped_loss_function, 'dev')
test_acc = evaluate(experiment, model, test_iter,
wrapped_loss_function, 'test')
if dev_acc > best_dev_acc:
best_dev_acc = dev_acc
os.system('rm best_models/mr_best_model_minibatch_acc_*.model')
print('New Best Dev!!!')
torch.save(
model.state_dict(),
'best_models/mr_best_model_minibatch_acc_' +
str(int(test_acc * 10000)) + '.model')
no_up = 0
else:
no_up += 1
def train():
EMBEDDING_DIM = 100
HIDDEN_DIM = 50
EPOCH = 100
BATCH_SIZE = 10
text_field = data.Field(lower=True)
label_field = data.Field(sequential=False)
train_iter, dev_iter, test_iter = classification_datasets.load_mr(
text_field, label_field, batch_size=BATCH_SIZE)
text_field.vocab.load_vectors(wv_type='glove.6B', wv_dim=100)
best_dev_acc = 0.0
model = LSTMClassifier(embedding_dim=EMBEDDING_DIM,
hidden_dim=HIDDEN_DIM,
vocab_size=len(text_field.vocab),
label_size=len(label_field.vocab) - 1,
batch_size=BATCH_SIZE)
model.word_embeddings.weight.data = text_field.vocab.vectors
loss_function = nn.NLLLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)
no_up = 0
for i in range(EPOCH):
print('epoch: %d start!' % i)
train_epoch(model, train_iter, loss_function, optimizer, text_field,
label_field, i)
print('now best dev acc:', best_dev_acc)
dev_acc = evaluate(model, dev_iter, loss_function, 'dev')
test_acc = evaluate(model, test_iter, loss_function, 'test')
if dev_acc > best_dev_acc:
best_dev_acc = dev_acc
os.system('rm best_models/mr_best_model_minibatch_acc_*.model')
print('New Best Dev!!!')
torch.save(
model.state_dict(),
'best_models/mr_best_model_minibatch_acc_' +
str(int(test_acc * 10000)) + '.model')
no_up = 0
else:
no_up += 1
if no_up >= 10:
exit()
parser.add_argument('-bi-gru', action='store_true', default=False)
parser.add_argument('-bnlstm', action='store_true', default=False)
parser.add_argument('-train-cnn', action='store_true', default=False)
args = parser.parse_args()
# load dataset
print("\nLoading data...")
text_field = data.Field(lower=True)
label_field = data.Field(sequential=False)
text_nonstatic_field = data.Field(lower=True)
label_nonstatic_field = data.Field(sequential=False)
if args.class_five:
train_iter, dev_iter, test_iter = data_five.load_mr(text_field, label_field, batch_size=args.batch_size)
else:
train_iter, dev_iter, test_iter = classification_datasets.load_mr(text_field, label_field, batch_size=args.batch_size)
# train_iter, dev_iter, test_iter = classification_datasets_nonstatic.load_mr(text_field, label_field, text_nonstatic_field, label_nonstatic_field, batch_size=args.batch_size)
# train_iter_char, dev_iter_char, test_iter_char = datasets_char.load_mr(text_field, label_field, batch_size=args.batch_size)
# print(type(train_iter_char))
# print(train_iter_char)
# dict_vocab = text_field.vocab.freqs
count_words_reset = text_field.vocab.itos
# count_train_words = text_nonstatic_field.vocab.itos
# print(len(count_train_words)) # 14830
# print(count_words_reset)
# text_field_words = set(count_words_reset)
# print(len(text_field_words)) # 17575
# print(text_field_words)
# wv_cat = loader.vector_loader(text_field_words)
# wv_cat = loader.vector_loader_zero(text_field_words)
parser.add_argument('-bilstm', action='store_true', default=True)
parser.add_argument('-train-cnn', action='store_true', default=False)
parser.add_argument('-use-cuda', action='store_true', default=False)
args = parser.parse_args()
# load dataset
print("\nLoading data...")
text_field = data.Field(lower=True)
label_field = data.Field(sequential=False)
if args.class_five:
train_iter, dev_iter, test_iter = data_five.load_mr(
text_field, label_field, batch_size=args.batch_size)
else:
train_iter, dev_iter, test_iter = classification_datasets.load_mr(
text_field, label_field, batch_size=args.batch_size)
# args.word_dict = text_field.vocab.freqs
# print(args.word_dict)
args.word_list = text_field.vocab.itos
# print(args.word_list)
word_size = len(args.word_list)
args.word_dict = dict(zip(args.word_list, list(range(0, word_size))))
# print(args.word_dict)
args.padID = args.word_dict['<pad>']
# print(padID)
# wv_cat = loader.vector_loader(count_words_reset)
# pretrained_weight = wv_cat
# args.pretrained_weight = pretrained_weight