Вложение слов с помощью Keras с использованием R - PullRequest
Новая
       13

Вложение слов с помощью Keras с использованием R

1 голос
/ 09 июня 2019

Я пытаюсь использовать Keras с R (R версия 3.5.0) для генерации вложений слов для набора данных Amazon Fine Foods Reviews (используя это руководство: https://blogs.rstudio.com/tensorflow/posts/2017-12-22-word-embeddings-with-keras/).

Но у меня естьследующая ошибка при обучении модели: 

Error in py_call_impl(callable, dots$args, dots$keywords) : 
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[   3],
    [  71],
    [   7],
    ...,
    [  58],
    [ 182],
    [   3]],

   [[  60],
    [1040],
    [2197],
    ...,
    [  45],
    [  ...

Detailed traceback: 
File "/Users/me/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/python/keras/engine/training.py", line 1426, in fit_generator
initial_epoch=initial_epoch)
File "/Users/me/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 191, in model_iteration
batch_outs = batch_function(*batch_data)
File "/Users/me/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/python/keras/engine/training.py", line 1175, in train_on_batch

Вот мой сценарий: (я ничего не изменил из учебника) 

#getting data
download.file("https://snap.stanford.edu/data/finefoods.txt.gz", "finefoods.txt.gz")

library(readr)
library(stringr)
reviews <- read_lines("finefoods.txt.gz") 
reviews <- reviews[str_sub(reviews, 1, 12) == "review/text:"]
reviews <- str_sub(reviews, start = 14)
reviews <- iconv(reviews, to = "UTF-8")

head(reviews, 2)

#Preprocessing
library(keras)
tokenizer <- text_tokenizer(num_words = 20000)
tokenizer %>% fit_text_tokenizer(reviews)

#Skip-Gram Model
library(reticulate)
library(purrr)
skipgrams_generator <- function(text, tokenizer, window_size, negative_samples) {
  gen <- texts_to_sequences_generator(tokenizer, sample(text))
  function() {
    skip <- generator_next(gen) %>%
      skipgrams(
        vocabulary_size = tokenizer$num_words, 
        window_size = window_size, 
        negative_samples = 1
      )
    x <- transpose(skip$couples) %>% map(. %>% unlist %>% as.matrix(ncol = 1))
    y <- skip$labels %>% as.matrix(ncol = 1)
    list(x, y)
  }
}

embedding_size <- 128  # Dimension of the embedding vector.
skip_window <- 5       # How many words to consider left and right.
num_sampled <- 1       # Number of negative examples to sample for each word.

input_target <- layer_input(shape = 1)
input_context <- layer_input(shape = 1)

embedding <- layer_embedding(
  input_dim = tokenizer$num_words + 1, 
  output_dim = embedding_size, 
  input_length = 1, 
  name = "embedding"
)

target_vector <- input_target %>% 
  embedding() %>% 
  layer_flatten()

context_vector <- input_context %>%
  embedding() %>%
  layer_flatten()

dot_product <- layer_dot(list(target_vector, context_vector), axes = 1)
output <- layer_dense(dot_product, units = 1, activation = "sigmoid")

model <- keras_model(list(input_target, input_context), output)
model %>% compile(loss = "binary_crossentropy", optimizer = "adam")

summary(model)

model %>%
  fit_generator(
    skipgrams_generator(reviews, tokenizer, skip_window, negative_samples), 
    steps_per_epoch = 100000, epochs = 5
  )
...