def test(dataset_size, model_type):
""" opens fit dataset and trains SVM/LogReg/Forest model with it, then tests it"""
print "MODEL TEST", dataset_size, model_type
dset = dataset.read('contradictions', dataset_size)
data, targets = [], []
for case in dset['content']:
data.append(case)
targets.append(case['contradiction'])
fit_data, test_data = [], []
fit_cases, test_cases, fit_target, test_target = train_test_split(
data, targets, test_size=0.25, shuffle=True, random_state=0)
for fit_case in fit_cases:
fit_data.append(
get_features(fit_case['sentence'], fit_case['hypothesis']))
for test_case in test_cases:
test_data.append(
get_features(test_case['sentence'], test_case['hypothesis']))
model = ClassificationModel(model_type)
start_time = time.time()
model.train(fit_data, fit_target, dataset_size)
elapsed_time = time.time() - start_time
test_results = model.test(test_data)
with open(
config.CONTRADICTIONS_RESULTS_PATH.format(dataset_size,
model_type),
'wb') as csvfile:
csv_writer = csv.writer(csvfile, delimiter=',')
csv_writer.writerow([
'hypothesis', 'sentence', 'type', 'contradiction', 'prediction',
'features'
])
for (test_case, result, features) in zip(test_cases, test_results,
test_data):
csv_writer.writerow([
test_case['hypothesis'], test_case['sentence'],
test_case['type'], test_case['contradiction'], result, features
])
precision = metrics.precision_score(test_target, test_results)
recall = metrics.recall_score(test_target, test_results)
f1_score = metrics.f1_score(test_target, test_results)
print "FIT TIME", elapsed_time
print "PRECISION", precision
print "RECALL", recall
print "F1 SCORE", f1_score
model.save(dataset_size)
def train():
# 加载数据
tokenizer = Tokenizer(cfg.char2idx)
train_dataset = CustomDataset(cfg.train_data_path, tokenizer, cfg)
train_dataloader = DataLoader(train_dataset,
batch_size=cfg.batch_size,
collate_fn=padding,
shuffle=True,
num_workers=4,
pin_memory=True)
model = ClassificationModel(len(cfg.char2idx))
# model = load_pretrained_bert(model, cfg.pretrained_model_path, keep_tokens=cfg.keep_tokens).to(cfg.device)
model = load_custom_model(model, cfg.save_model_path).to(cfg.device)
loss_function = nn.CrossEntropyLoss().to(cfg.device)
optimizer = torch.optim.Adam(model.parameters(), lr=cfg.learn_rate)
# 迭代训练
iteration, train_loss = 0, 0
model.train()
for inputs, mask, targets in tqdm(train_dataloader, position=0,
leave=True):
inputs, mask, targets = inputs.to(cfg.device), mask.to(
cfg.device), targets.to(cfg.device)
prediction = model(inputs, mask)
loss = loss_function(prediction, targets.reshape(-1))
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
iteration += 1
if iteration % cfg.print_loss_steps == 0:
eval_loss = evaluate(model, tokenizer, loss_function)
print('')
print('train_loss:{}'.format(train_loss / cfg.print_loss_steps))
print('evalu_loss:{}'.format(eval_loss))
accuracy(model, tokenizer, cfg.valid_data_path)
accuracy(model, tokenizer, cfg.test_data_path)
model.train()
train_loss = 0
if iteration % cfg.save_model_steps == 0:
torch.save(model.state_dict(), cfg.save_model_path)
epoch = 0
iter = 0
while True:
try:
# Fetch the dataset (tf.Tensor -> numpy array)
_img, _label = sess.run([img, labels])
# print(_img.shape)
# print(_img[0].shape)
# print(_label)
# import cv2
# cv2.imshow("img", _img[0])
# cv2.waitKey(0)
# cv2.destroyAllWindows()
# exit()
# Feed numpy array (data) To model's placeholder
cost, _ = model.train(_img, _label)
iter = iter + 1
if(iter%100 == 0):
acc = model.get_accuracy(_img, _label)
print('Iter:', '%02d' % (iter), 'cost =', '{:.9f}'.format(cost), 'acc =', acc)
except tf.errors.OutOfRangeError:
val_acc = 0.0
for i in range(train_dataset._val_array_len):
_img_val, _label_val = sess.run([img_val, label_val])
val_acc = val_acc + model.get_accuracy(_img_val, _label_val)
print('Validation set acc :', val_acc/train_dataset._val_array_len)
print("Validation End")
break
