def test_reset_model(self):
for model_path in self.model_paths:
original_aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path, top_p=0.5)
original_temperature = original_aug.model.temperature
original_top_k = original_aug.model.top_k
# original_top_p = original_aug.model.top_p
new_aug = nas.ContextualWordEmbsForSentenceAug(
model_path=model_path, temperature=original_temperature+1, top_k=original_top_k+1)
new_temperature = new_aug.model.temperature
new_top_k = new_aug.model.top_k
# new_top_p = new_aug.model.top_p
self.assertEqual(original_temperature+1, new_temperature)
self.assertEqual(original_top_k + 1, new_top_k)
def execute_by_device(self, device):
for model_path in self.model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path, force_reload=True, device=device)
self.empty_input(aug)
self.insert(aug)
self.assertLess(0, len(self.model_paths))
def setUpClass(cls):
env_config_path = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..', '..', '.env'))
load_dotenv(env_config_path)
cls.augs = [
nac.RandomCharAug(),
naw.ContextualWordEmbsAug(),
nas.ContextualWordEmbsForSentenceAug()
]
def execute_by_device(self, device):
for model_path in self.model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path, device=device)
self.empty_input(aug)
for data in [self.text, self.texts]:
self.insert(aug, data)
self.assertLess(0, len(self.model_paths))
def test_batch_size(self):
# 1 per batch
aug = nas.ContextualWordEmbsForSentenceAug(model_path='distilgpt2', batch_size=1)
aug_data = aug.augment(self.texts)
self.assertEqual(len(aug_data), len(self.texts))
# batch size = input size
aug = nas.ContextualWordEmbsForSentenceAug(model_path='distilgpt2', batch_size=len(self.texts))
aug_data = aug.augment(self.texts)
self.assertEqual(len(aug_data), len(self.texts))
# batch size > input size
aug = nas.ContextualWordEmbsForSentenceAug(model_path='distilgpt2', batch_size=len(self.texts)+1)
aug_data = aug.augment(self.texts)
self.assertEqual(len(aug_data), len(self.texts))
# input size > batch size
aug = nas.ContextualWordEmbsForSentenceAug(model_path='distilgpt2', batch_size=2)
aug_data = aug.augment(self.texts * 2)
self.assertEqual(len(aug_data), len(self.texts)*2)
def execute_by_device(self, device):
for model_path in self.model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path, device=device)
self.empty_input(aug)
self.insert(aug)
self.top_k(aug)
self.top_p(aug)
self.top_k_top_p(aug)
self.no_top_k_top_p(aug)
self.assertLess(0, len(self.model_paths))
def test_optimize(self):
model_paths = ['gpt2', 'distilgpt2']
device = 'cpu'
enable_optimize = {'external_memory': 1024, 'return_proba': True}
disable_optimize = {'external_memory': 0, 'return_proba': True}
epoch = 10
for model_path in model_paths:
# Optimized
durations = []
aug = nas.ContextualWordEmbsForSentenceAug(
model_path=model_path,
device=device,
optimize=enable_optimize,
force_reload=True)
for i in range(epoch):
start_dt = time.monotonic()
for j in range(epoch):
aug.augment(self.text)
end_dt = time.monotonic()
durations.append(round(end_dt - start_dt, 2))
optimized_total_duration = sum(durations)
optimized_average_duration = round(
optimized_total_duration / len(durations), 2)
# No optimized
durations = []
aug.model.optimize = disable_optimize
for _ in range(epoch):
start_dt = time.monotonic()
for _ in range(epoch):
aug.augment(self.text)
end_dt = time.monotonic()
durations.append(round(end_dt - start_dt, 2))
no_optimized_total_duration = sum(durations)
no_optimized_average_duration = round(
no_optimized_total_duration / len(durations), 2)
print('Model:{}, Optimized: {}({}), No Optimized: {}({})'.format(
model_path, optimized_total_duration,
optimized_average_duration, no_optimized_total_duration,
no_optimized_average_duration))
self.assertGreater(no_optimized_total_duration,
optimized_total_duration)
self.assertGreater(no_optimized_average_duration,
optimized_average_duration)
def test_augment_detail(self):
for model_path in self.model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path,
include_detail=True)
augmented_text, augment_details = aug.augment(self.text)
self.assertNotEqual(self.text, augmented_text)
self.assertGreater(len(augment_details), 0)
for augment_detail in augment_details:
self.assertTrue(augment_detail['orig_token'] in self.text)
self.assertEqual(augment_detail['orig_start_pos'], -1)
self.assertGreater(augment_detail['new_start_pos'], -1)
self.assertGreater(augment_detail['change_seq'], 0)
self.assertIn(augment_detail['action'], Action.getall())
self.assertNotEqual(self.text, augmented_text)
def setUpClass(cls):
env_config_path = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..', '..', '.env'))
load_dotenv(env_config_path)
# https://freewavesamples.com/yamaha-v50-rock-beat-120-bpm
cls.sample_wav_file = os.environ.get(
"DATA_DIR") + 'Yamaha-V50-Rock-Beat-120bpm.wav'
cls.audio, cls.sampling_rate = librosa.load(cls.sample_wav_file)
cls.textual_augs = [
nac.RandomCharAug(),
naw.ContextualWordEmbsAug(),
nas.ContextualWordEmbsForSentenceAug()
]
cls.audio_augs = [
naa.CropAug(sampling_rate=cls.sampling_rate),
naa.SpeedAug(),
]
def test_optimize(self):
model_paths = ['gpt2', 'distilgpt2']
# model_paths = ['xlnet-base-cased']
for model_path in model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(model_path=model_path)
enable_optimize = aug.model.get_default_optimize_config()
enable_optimize['external_memory'] = 1024
disable_optimize = aug.model.get_default_optimize_config()
disable_optimize['external_memory'] = 0
original_optimize = aug.model.optimize
aug.model.optimize = enable_optimize
augmented_data = aug.augment(self.text)
self.assertNotEqual(self.text, augmented_data)
aug.model.optimize = disable_optimize
augmented_data = aug.augment(self.text)
self.assertNotEqual(self.text, augmented_data)
aug.model.optimize = original_optimize
def test_none_device(self):
for model_path in self.model_paths:
aug = nas.ContextualWordEmbsForSentenceAug(
model_path=model_path, force_reload=True, device=None)
self.assertTrue(aug.device == 'cuda' or aug.device == 'cpu')
def test_incorrect_model_name(self):
with self.assertRaises(ValueError) as error:
nas.ContextualWordEmbsForSentenceAug(model_path='unknown')
self.assertTrue('Model name value is unexpected.' in str(error.exception))
import nlpaug.augmenter.char as nac
import nlpaug.augmenter.word as naw
import nlpaug.augmenter.sentence as nas
import nlpaug.flow as nafc
import os
from nlpaug.util import Action
text = "Embarrassment is a common emotion. But as a bot I don't really feel it."
aug = nas.ContextualWordEmbsForSentenceAug(model_path='xlnet-base-cased')
augmented_texts = aug.augment(text, n=3)
print("Original:")
print(text)
print("Augmented Texts:")
print(augmented_texts)
aug = nas.ContextualWordEmbsForSentenceAug(model_path='gpt2')
augmented_text = aug.augment(text)
print("Original:")
print(text)
print("Augmented Text:")
print(augmented_text)
aug = nas.ContextualWordEmbsForSentenceAug(model_path='distilgpt2')
augmented_text = aug.augment(text)
print("Original:")
print(text)
print("Augmented Text:")
print(augmented_text)
