def __getitem__(self, idx):
textprocessor = TextProcessor(VOCAB_SIZE=self.VOCAB_SIZE)
utils = Utils()
video_file = self.train_dir_list[
idx] # get video file corresponding to the id, idx
output_text = self.utils.output_text(
self.train_corpus,
video_file) # get the text contained in the video file
#### generate input 2, from the output_text
sentence_to_index = textprocessor.sentence_to_indices(
utils.tagger_input(utils.clean_text(output_text)),
self.word_to_index)
X_2 = textprocessor.get_output(sentence_to_index, self.NUMBER_OF_WORDS)
#### generate output, from the output_text
sentence_to_index = textprocessor.sentence_to_indices(
utils.tagger_output(utils.clean_text(output_text)),
self.word_to_index)
y = textprocessor.get_output(sentence_to_index, self.NUMBER_OF_WORDS)
video_path = self.train_dir + video_file
# generate input 1
X_1 = utils.video_to_frames(video_path, self.number_of_frames,
self.device, self.INPUT_SIZE, self.model,
self.transform)
#X_1 = pre_data[idx]
return (X_1, torch.tensor(X_2)), torch.tensor(y)
