Introducere în LSTM-uri

Introducere în Deep Learning cu Keras

Miguel Esteban

Data Scientist & Founder

Ce sunt RNN-urile?

Când se folosesc LSTM-urile?

Descrierea imaginilor
Conversie vorbire în text
Traducere automată
Rezumarea documentelor
Generare de text
Compoziție muzicală
...

¹ Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions.

text = 'Hi this is a small sentence'

# We choose a sequence length
seq_len = 3

# Split text into a list of words
words = text.split()

['Hi', 'this', 'is', 'a', 'small', 'sentence']

# Make lines
lines = []
for i in range(seq_len, len(words) + 1):
  line = ' '.join(words[i-seq_len:i])
  lines.append(line)

['Hi this is', 'this is a', 'is a small', 'a small sentence']

# Import Tokenizer from keras preprocessing text
from tensorflow.keras.preprocessing.text import Tokenizer

# Instantiate Tokenizer
tokenizer = Tokenizer()

# Fit it on the previous lines
tokenizer.fit_on_texts(lines)

# Turn the lines into numeric sequences
sequences = tokenizer.texts_to_sequences(lines)

array([[5, 3, 1], [3, 1, 2], [1, 2, 4], [2, 4, 6]])

print(tokenizer.index_word)

{1: 'is', 2: 'a', 3: 'this', 4: 'small', 5: 'hi', 6: 'sentence'}

# Import Dense, LSTM and Embedding layers
from tensorflow.keras.layers import Dense, LSTM, Embedding
model = Sequential()

# Vocabulary size
vocab_size = len(tokenizer.index_word) + 1

# Starting with an embedding layer
model.add(Embedding(input_dim=vocab_size, output_dim=8, input_length=2))

# Adding an LSTM layer
model.add(LSTM(8))

# Adding a Dense hidden layer
model.add(Dense(8, activation='relu'))

# Adding an output layer with softmax
model.add(Dense(vocab_size, activation='softmax'))

Să exersăm!

Introducere în Deep Learning cu Keras