from nalp.models.generators import LSTMGenerator
# Creating a character TextCorpus from file
corpus = TextCorpus(from_file='data/text/chapter1_harry.txt', corpus_type='char')
# Creating an IntegerEncoder
encoder = IntegerEncoder()
# Learns the encoding based on the TextCorpus dictionary and reverse dictionary
encoder.learn(corpus.vocab_index, corpus.index_vocab)
# Applies the encoding on new data
encoded_tokens = encoder.encode(corpus.tokens)
# Creating Language Modeling Dataset
dataset = LanguageModelingDataset(encoded_tokens, max_length=10, batch_size=64)
# Creating the LSTM
lstm = LSTMGenerator(encoder=encoder, vocab_size=corpus.vocab_size, embedding_size=256, hidden_size=512)
# As NALP's LSTMs are stateful, we need to build it with a fixed batch size
lstm.build((64, None))
# Compiling the LSTM
lstm.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001),
loss=tf.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[tf.metrics.SparseCategoricalAccuracy(name='accuracy')])
# Fitting the LSTM
lstm.fit(dataset.batches, epochs=100)
from nalp.corpus import TextCorpus
from nalp.datasets import LanguageModelingDataset
from nalp.encoders import IntegerEncoder
# Creating a character TextCorpus from file
corpus = TextCorpus(from_file='data/text/chapter1_harry.txt',
corpus_type='char')
# Creating an IntegerEncoder, learning encoding and encoding tokens
encoder = IntegerEncoder()
encoder.learn(corpus.vocab_index, corpus.index_vocab)
encoded_tokens = encoder.encode(corpus.tokens)
# Creating Language Modeling Dataset
dataset = LanguageModelingDataset(encoded_tokens,
max_contiguous_pad_length=10,
batch_size=1,
shuffle=True)
# Iterating over one batch
for input_batch, target_batch in dataset.batches.take(1):
# For every input and target inside the batch
for x, y in zip(input_batch, target_batch):
# Transforms the tensor to numpy and decodes it
print(encoder.decode(x.numpy()), encoder.decode(y.numpy()))
from nalp.corpus import AudioCorpus
from nalp.datasets import LanguageModelingDataset
from nalp.encoders import IntegerEncoder
from nalp.models.generators import RNNGenerator
# Creating an AudioCorpus from file
corpus = AudioCorpus(from_file='data/audio/sample.mid')
# Creating an IntegerEncoder, learning encoding and encoding tokens
encoder = IntegerEncoder()
encoder.learn(corpus.vocab_index, corpus.index_vocab)
encoded_tokens = encoder.encode(corpus.tokens)
# Creating Language Modeling Dataset
dataset = LanguageModelingDataset(encoded_tokens,
max_contiguous_pad_length=100,
batch_size=64)
# Creating the RNN
rnn = RNNGenerator(encoder=encoder,
vocab_size=corpus.vocab_size,
embedding_size=256,
hidden_size=512)
# As NALP's RNNs are stateful, we need to build it with a fixed batch size
rnn.build((64, None))
# Compiling the RNN
rnn.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001),
loss=tf.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[tf.metrics.SparseCategoricalAccuracy(name='accuracy')])
