def objective(trial):
nl = trial.suggest_int("num_layers", 1, 2)
bi = trial.suggest_categorical("bidirectional", [False, True])
model = RNN(d_w, d_h, L, emb, num_layers=nl, bidirectional=bi)
lr = trial.suggest_loguniform("learning_rate", 1e-5, 1e-1)
bs = trial.suggest_categorical("batch_size", [32, -1])
model = run_train(train,
valid,
model,
epochs=11,
lr=lr,
batch_size=bs,
device=device)
loss_eval, acc_eval = run_eval(model, valid, device=device)
return acc_eval
if __name__ == "__main__":
x_train = get_feature(open('train2.feature.txt'))
y_train = joblib.load('train_label.pkl').tolist()
x_valid = get_feature(open('valid2.feature.txt'))
y_valid = joblib.load('valid_label.pkl').tolist()
x_test = get_feature(open('test2.feature.txt'))
y_test = joblib.load('test_label.pkl').tolist()
tr_text2id, tr_word2id = word2ids(x_train)
train_set = CreateDataset(x_train, y_train, tr_text2id)
val_text2id, val_word2id = word2ids(x_valid)
valid_set = CreateDataset(x_valid, y_valid, val_text2id)
test_text2id, test_word2id = word2ids(x_test)
test_set = CreateDataset(x_test, y_test, test_text2id)
VOCAB_SIZE = len(set(tr_word2id.values())) + 1
EMB_SIZE = 300
PADDING_IDX = len(set(tr_word2id.values()))
OUTPUT_SIZE = 4
HIDDEN_SIZE = 50
LEARNING_RATE = 1e-3
BATCH_SIZE = 1
NUM_EPOCHS = 10
model = RNN(VOCAB_SIZE, EMB_SIZE, PADDING_IDX, OUTPUT_SIZE, HIDDEN_SIZE)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LEARNING_RATE)
log = train_model(train_set, valid_set, BATCH_SIZE, model, criterion, optimizer, NUM_EPOCHS)
from knock82 import run_eval, run_train
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
from kiyuna.utils.pickle import load # noqa: E402 isort:skip
logging.basicConfig(level=logging.DEBUG)
d_w = 300
d_h = 50
V = get_V()
L = 4
if __name__ == "__main__":
train = torch.load("./data/train.pt")
valid = torch.load("./data/valid.pt")
test = torch.load("./data/test.pt")
device = torch.device("cuda:6")
emb = torch.Tensor(d_w, V).normal_()
wv = load("chap07-embeddings")
for i, word in enumerate(_list_valid_words()):
if word in wv:
wv_word = wv[word]
wv_word.flags["WRITEABLE"] = True
emb[:, i] = torch.from_numpy(wv_word)
rnn = RNN(d_w, d_h, L, emb, num_layers=2, bidirectional=True)
rnn = run_train(train, valid, rnn, epochs=11, lr=1e-1, batch_size=32, device=device)
loss, acc = run_eval(rnn, test, device=device)
print(f"Accuracy (test): {acc:f}, Loss (test): {loss:f}")
logging.basicConfig(level=logging.DEBUG)
d_w = 300
d_h = 50
V = get_V()
L = 4
if __name__ == "__main__":
train = torch.load("./data/train.pt")
valid = torch.load("./data/valid.pt")
test = torch.load("./data/test.pt")
device = torch.device("cuda:7")
emb = torch.Tensor(d_w, V).normal_()
wv = load("chap07-embeddings")
for i, word in enumerate(_list_valid_words()):
if word in wv:
wv_word = wv[word]
wv_word.flags["WRITEABLE"] = True
emb[:, i] = torch.from_numpy(wv_word)
rnn = RNN(d_w, d_h, L, emb)
rnn = run_train(train,
valid,
rnn,
epochs=11,
lr=1e-1,
batch_size=32,
device=device)
loss, acc = run_eval(rnn, test, device=device)
print(f"Accuracy (test): {acc:f}, Loss (test): {loss:f}")