sessionInfo()
## R version 4.0.2 (2020-06-22)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS High Sierra 10.13.6
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRblas.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## loaded via a namespace (and not attached):
## [1] compiler_4.0.2 magrittr_1.5 tools_4.0.2 htmltools_0.5.0
## [5] yaml_2.2.1 stringi_1.5.3 rmarkdown_2.3 knitr_1.30
## [9] stringr_1.4.0 xfun_0.17 digest_0.6.25 rlang_0.4.7
## [13] evaluate_0.14
Source: https://tensorflow.rstudio.com/guide/keras/examples/imdb_lstm/
From documentation:
Dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a sequence of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer “3” encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: “only consider the top 10,000 most common words, but eliminate the top 20 most common words”.
Retrieve IMDB data:
library(keras)
max_features <- 20000
batch_size <- 32
# Cut texts after this number of words (among top max_features most common words)
maxlen <- 80
cat('Loading data...\n')
## Loading data...
imdb <- dataset_imdb(num_words = max_features)
imdb$train$x[[1]]
## [1] 1 14 22 16 43 530 973 1622 1385 65 458 4468
## [13] 66 3941 4 173 36 256 5 25 100 43 838 112
## [25] 50 670 2 9 35 480 284 5 150 4 172 112
## [37] 167 2 336 385 39 4 172 4536 1111 17 546 38
## [49] 13 447 4 192 50 16 6 147 2025 19 14 22
## [61] 4 1920 4613 469 4 22 71 87 12 16 43 530
## [73] 38 76 15 13 1247 4 22 17 515 17 12 16
## [85] 626 18 19193 5 62 386 12 8 316 8 106 5
## [97] 4 2223 5244 16 480 66 3785 33 4 130 12 16
## [109] 38 619 5 25 124 51 36 135 48 25 1415 33
## [121] 6 22 12 215 28 77 52 5 14 407 16 82
## [133] 10311 8 4 107 117 5952 15 256 4 2 7 3766
## [145] 5 723 36 71 43 530 476 26 400 317 46 7
## [157] 4 12118 1029 13 104 88 4 381 15 297 98 32
## [169] 2071 56 26 141 6 194 7486 18 4 226 22 21
## [181] 134 476 26 480 5 144 30 5535 18 51 36 28
## [193] 224 92 25 104 4 226 65 16 38 1334 88 12
## [205] 16 283 5 16 4472 113 103 32 15 16 5345 19
## [217] 178 32
imdb$train$y[[1]]
## [1] 1
x_train <- imdb$train$x
y_train <- imdb$train$y
x_test <- imdb$test$x
y_test <- imdb$test$y
cat(length(x_train), 'train sequences\n')
## 25000 train sequences
cat(length(x_test), 'test sequences\n')
## 25000 test sequences
cat('Pad sequences (samples x time)\n')
## Pad sequences (samples x time)
x_train <- pad_sequences(x_train, maxlen = maxlen)
x_test <- pad_sequences(x_test, maxlen = maxlen)
cat('x_train shape:', dim(x_train), '\n')
## x_train shape: 25000 80
cat('x_test shape:', dim(x_test), '\n')
## x_test shape: 25000 80
cat('Build model...\n')
## Build model...
model <- keras_model_sequential()
model %>%
layer_embedding(input_dim = max_features, output_dim = 128) %>%
layer_lstm(units = 64, dropout = 0.2, recurrent_dropout = 0.2) %>%
layer_dense(units = 1, activation = 'sigmoid')
# Try using different optimizers and different optimizer configs
model %>% compile(
loss = 'binary_crossentropy',
optimizer = 'adam',
metrics = c('accuracy')
)
summary(model)
## Model: "sequential"
## ________________________________________________________________________________
## Layer (type) Output Shape Param #
## ================================================================================
## embedding (Embedding) (None, None, 128) 2560000
## ________________________________________________________________________________
## lstm (LSTM) (None, 64) 49408
## ________________________________________________________________________________
## dense (Dense) (None, 1) 65
## ================================================================================
## Total params: 2,609,473
## Trainable params: 2,609,473
## Non-trainable params: 0
## ________________________________________________________________________________
cat('Train...\n')
## Train...
system.time({
model %>% fit(
x_train, y_train,
batch_size = batch_size,
epochs = 1,
validation_data = list(x_test, y_test)
)
})
## user system elapsed
## 348.976 123.077 152.197
scores <- model %>% evaluate(
x_test, y_test,
batch_size = batch_size
)
cat('Test score:', scores[[1]])
## Test score: 0.3529011
cat('Test accuracy', scores[[2]])
## Test accuracy 0.84492