def inference():
thandler = trainer.handler(args.process_command())
rt_data = rt()
data = trainer.load_data(rt_data.data, data_type=rt_data.data_type)
test_loader = data
model_ = models.MLP(300, classes=2)
#print(model_)
total = sum(p.numel() for p in model_.parameters() if p.requires_grad)
print('# of para: {}'.format(total))
model_name = 'MLP.pt'
predicted = thandler.predict(model_, test_loader, model_name)
print([np.argmax(np.array(i)) for i in predicted])
train_x = torch.LongTensor(self.process(train_x))
dev_x = torch.LongTensor(self.process(dev_x))
test_x = torch.LongTensor(self.process(test_x))
print(train_x.shape)
print(dev_x.shape)
print(test_x.shape)
return (train_x, torch.LongTensor(train_y)), (
dev_x, torch.LongTensor(dev_y)), (test_x, torch.LongTensor(test_y))
if __name__ == '__main__':
rt = rt()
handler = trainer.handler()
#data preprocess
training, valid, testing = rt.simple_data()
train_loader = handler.torch_data(training)
valid_loader = handler.torch_data(valid)
test_loader = handler.torch_data(testing)
import model
trial = handler.trial
scores = []
for i in range(trial):
#setting
model_ = model.BertCls(BertModel, rt.weight, handler.trainable)
model_name = 'model_' + str(i) + '.pt'
model_path = handler.save + model_name
import args
import rt_data as rt
import sys
import torch
import torch_model as models
import training_handler
import util
from tensorflow import keras
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
thandler = training_handler.handler(args.process_command())
def RUN_SVC(data):
print('SVC')
(train_data, train_labels), (test_data, test_labels) = data
clf = SVC(C=0.1, gamma='auto')
clf.fit(util.padding(train_data), train_labels)
y_pred = clf.predict(util.padding(test_data))
print('Accuracy: {}'.format(accuracy_score(test_labels, y_pred)))
def data_loader(data_, data_type=[torch.LongTensor, torch.LongTensor]):
(train_data, train_labels), (test_data, test_labels) = data_
train_size = int(len(train_data) * 0.1)
valid_data = train_data[:train_size]