import numpy as np
import tensorflow as tf
from tqdm import tqdm
from python.dataset import AutoComplete
from python.model import PureGRU
from python.summary import ContextAccuracy
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = AutoComplete(repeat=True, batch_size=64)
test_dataset = AutoComplete(dataset='test', repeat=False, batch_size=16)
model = PureGRU(train_dataset,
name='autocomplete_gru_600',
embedding_size=600,
verbose=True)
context_accuracy = ContextAccuracy()
for output_i, output in enumerate(
tqdm(model.predict(dataset=test_dataset),
total=test_dataset.observations)):
probabilities = output['probabilities']
predict_sorted = np.argsort(probabilities, axis=1)[:, ::-1]
source = test_dataset.decode_source(output['source'])
target = test_dataset.decode_target(output['target'])
predict = test_dataset.decode_target(predict_sorted)
context_accuracy.add(source, predict, target)
from python.model import PureGRU
dirname = path.dirname(path.realpath(__file__))
article_dir = path.join(dirname, '..', '..', 'public')
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = AutoComplete(repeat=True)
test_dataset = AutoCompleteFixed(
"context the formal study of grammar is an important part of education "
"from a young age through advanced learning though the rules taught in "
"schools are not a grammar in the sense most linguists use",
batch_size=1,
use_offsets=True)
model = PureGRU(train_dataset,
name='autocomplete_gru_600',
embedding_size=600,
verbose=True)
data = []
print(f'sequence:')
for output_i, output in enumerate(model.predict(dataset=test_dataset)):
probabilities = output['probabilities']
predict_index_sorted = np.argsort(probabilities, axis=1)[:, ::-1]
predict_value_sorted = np.sort(probabilities, axis=1)[:, ::-1]
source = test_dataset.decode_source(output['source'])
target = test_dataset.decode_target(output['target'])
predict = test_dataset.decode_target(predict_index_sorted)
connectivity = output['connectivity']
import numpy as np
import tensorflow as tf
from python.dataset import Generate
from python.model import PureGRU
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = Generate(repeat=True, batch_size=64)
test_dataset = Generate(dataset='test', repeat=False, batch_size=16)
model = PureGRU(train_dataset,
name='generate_gru_1200',
embedding_size=1200,
verbose=True)
print(model.evaluate(dataset=test_dataset))
import tensorflow as tf
from python.dataset import Generate
from python.model import PureGRU
tf.random.set_random_seed(450849059) # From random.org
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = Generate(repeat=True, batch_size=64)
valid_dataset = Generate(repeat=True, dataset='valid', batch_size=64)
model = PureGRU(train_dataset,
name='generate_gru_1200',
embedding_size=1200,
verbose=True)
model.train(max_steps=train_dataset.batches, valid_dataset=valid_dataset)
import numpy as np
import tensorflow as tf
from python.dataset import AutoComplete
from python.model import PureGRU
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = AutoComplete(repeat=True, batch_size=64)
test_dataset = AutoComplete(dataset='test', repeat=False, batch_size=1)
model = PureGRU(train_dataset,
name='autocomplete_gru_600',
embedding_size=600,
verbose=True)
print(model.evaluate(dataset=test_dataset))
import tensorflow as tf
from python.dataset import AutoComplete
from python.model import PureGRU
tf.random.set_random_seed(450849059) # From random.org
tf.logging.set_verbosity(tf.logging.INFO)
train_dataset = AutoComplete(repeat=True, batch_size=64)
valid_dataset = AutoComplete(repeat=True, dataset='valid', batch_size=64)
test_dataset = AutoComplete(repeat=False, dataset='test', batch_size=64)
model = PureGRU(train_dataset,
name='autocomplete_gru_600',
embedding_size=600,
verbose=True)
model.train(max_steps=train_dataset.batches * 2, valid_dataset=valid_dataset)