Tutorials on training the Skip-thoughts vectors for features extraction of sentence.

ipython  # Launch iPython.

In [0]:

# Imports.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import os.path
import scipy.spatial.distance as sd
from skip_thoughts import configuration
from skip_thoughts import encoder_manager

In [1]:
# Set paths to the model.
VOCAB_FILE = "/path/to/vocab.txt"
EMBEDDING_MATRIX_FILE = "/path/to/embeddings.npy"
CHECKPOINT_PATH = "/path/to/model.ckpt-9999"
# The following directory should contain files rt-polarity.neg and
# rt-polarity.pos.

In [2]:
# Set up the encoder. Here we are using a single unidirectional model.
# To use a bidirectional model as well, call load_model() again with
# configuration.model_config(bidirectional_encoder=True) and paths to the
# bidirectional model's files. The encoder will use the concatenation of
# all loaded models.
encoder = encoder_manager.EncoderManager()
encoder.load_model(configuration.model_config(),
                   vocabulary_file=VOCAB_FILE,
                   embedding_matrix_file=EMBEDDING_MATRIX_FILE,
                   checkpoint_path=CHECKPOINT_PATH)

In [3]:
# Load the movie review dataset.
data = [' This is my first attempt  to the tensorflow version skip_thought_vectors ... ']

In [4]:
# Generate Skip-Thought Vectors for each sentence in the dataset.
encodings = encoder.encode(data)
print(encodings)
print(encodings[0])