File size: 1,897 Bytes
9ce984a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
"""
Title: Bidirectional LSTM on IMDB
Author: [fchollet](https://twitter.com/fchollet)
Date created: 2020/05/03
Last modified: 2020/05/03
Description: Train a 2-layer bidirectional LSTM on the IMDB movie review sentiment classification dataset.
Accelerator: GPU
"""

"""
## Setup
"""

import numpy as np
import keras
from keras import layers

max_features = 20000  # Only consider the top 20k words
maxlen = 200  # Only consider the first 200 words of each movie review

"""
## Build the model
"""

# Input for variable-length sequences of integers
inputs = keras.Input(shape=(None,), dtype="int32")
# Embed each integer in a 128-dimensional vector
x = layers.Embedding(max_features, 128)(inputs)
# Add 2 bidirectional LSTMs
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True))(x)
x = layers.Bidirectional(layers.LSTM(64))(x)
# Add a classifier
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs, outputs)
model.summary()

"""
## Load the IMDB movie review sentiment data
"""

(x_train, y_train), (x_val, y_val) = keras.datasets.imdb.load_data(
    num_words=max_features
)
print(len(x_train), "Training sequences")
print(len(x_val), "Validation sequences")
# Use pad_sequence to standardize sequence length:
# this will truncate sequences longer than 200 words and zero-pad sequences shorter than 200 words.
x_train = keras.utils.pad_sequences(x_train, maxlen=maxlen)
x_val = keras.utils.pad_sequences(x_val, maxlen=maxlen)

"""
## Train and evaluate the model

You can use the trained model hosted on [Hugging Face Hub](https://huggingface.co/keras-io/bidirectional-lstm-imdb)
and try the demo on [Hugging Face Spaces](https://huggingface.co/spaces/keras-io/bidirectional_lstm_imdb).
"""

model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
model.fit(x_train, y_train, batch_size=32, epochs=2, validation_data=(x_val, y_val))