preprocessors.py 文件源码

def preprocess_batch(self, captions_label_encoded):
        captions = keras_seq.pad_sequences(captions_label_encoded,
                                           padding='post')
        # Because the number of timesteps/words resulted by the model is
        # maxlen(captions) + 1 (because the first "word" is the image).
        captions_extended1 = keras_seq.pad_sequences(captions,
                                                maxlen=captions.shape[-1] + 1,
                                                padding='post')
        captions_one_hot = map(self._tokenizer.sequences_to_matrix,
                               np.expand_dims(captions_extended1, -1))
        captions_one_hot = np.array(captions_one_hot, dtype='int')

        # Decrease/shift word index by 1.
        # Shifting `captions_one_hot` makes the padding word
        # (index=0, encoded=[1, 0, ...]) encoded all zeros ([0, 0, ...]),
        # so its cross entropy loss will be zero.
        captions_decreased = captions.copy()
        captions_decreased[captions_decreased > 0] -= 1
        captions_one_hot_shifted = captions_one_hot[:, :, 1:]

        captions_input = captions_decreased
        captions_output = captions_one_hot_shifted
        return captions_input, captions_output