chatbot_hybrid_frontend.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import torch
from torch.jit import script, trace
import torch.nn as nn
import torch.nn.functional as F
import re
import os
import unicodedata
import numpy as np


USE_CUDA = torch.cuda.is_available()
device = torch.device("cuda" if USE_CUDA else "cpu")

# Constants
MAX_LENGTH = 10  # Maximum sentence length

# Default word tokens
PAD_token = 0  # Used for padding short sentences
SOS_token = 1  # Start-of-sentence token
EOS_token = 2  # End-of-sentence token


###################################################
# DEFINE ENCODER
###################################################
class EncoderRNN(nn.Module):
    def __init__(self, hidden_size, embedding, n_layers=1, dropout=0):
        super(EncoderRNN, self).__init__()
        self.n_layers = n_layers
        self.hidden_size = hidden_size
        self.embedding = embedding

        # Initialize GRU; the input_size and hidden_size params are both set to 'hidden_size'
        #   because our input size is a word embedding with number of features == hidden_size
        self.gru = nn.GRU(hidden_size, hidden_size, n_layers,
                          dropout=(0 if n_layers == 1 else dropout), bidirectional=True)

    def forward(self, input_seq, input_lengths, hidden=None):
        # Convert word indexes to embeddings
        embedded = self.embedding(input_seq)
        # Pack padded batch of sequences for RNN module
        packed = torch.nn.utils.rnn.pack_padded_sequence(embedded, input_lengths)
        # Forward pass through GRU
        outputs, hidden = self.gru(packed, hidden)
        # Unpack padding
        outputs, _ = torch.nn.utils.rnn.pad_packed_sequence(outputs)
        # Sum bidirectional GRU outputs
        outputs = outputs[:, :, :self.hidden_size] + outputs[:, : ,self.hidden_size:]
        # Return output and final hidden state
        return outputs, hidden



###################################################
# DEFINE DECODER'S ATTENTION MODULE
###################################################
# Luong attention layer
class Attn(torch.nn.Module):
    def __init__(self, method, hidden_size):
        super(Attn, self).__init__()
        self.method = method
        self.hidden_size = hidden_size
        if self.method == 'general':
            self.attn = torch.nn.Linear(self.hidden_size, hidden_size)
        elif self.method == 'concat':
            self.attn = torch.nn.Linear(self.hidden_size * 2, hidden_size)
            self.v = torch.nn.Parameter(torch.FloatTensor(hidden_size))

    def dot_score(self, hidden, encoder_output):
        return torch.sum(hidden * encoder_output, dim=2)

    def general_score(self, hidden, encoder_output):
        energy = self.attn(encoder_output)
        return torch.sum(hidden * energy, dim=2)

    def concat_score(self, hidden, encoder_output):
        energy = self.attn(torch.cat((hidden.expand(encoder_output.size(0), -1, -1), encoder_output), 2)).tanh()
        return torch.sum(self.v * energy, dim=2)

    def forward(self, hidden, encoder_outputs):
        # Calculate the attention weights (energies) based on the given method
        if self.method == 'general':
            attn_energies = self.general_score(hidden, encoder_outputs)
        elif self.method == 'concat':
            attn_energies = self.concat_score(hidden, encoder_outputs)
        elif self.method == 'dot':
            attn_energies = self.dot_score(hidden, encoder_outputs)

        # Transpose max_length and batch_size dimensions
        attn_energies = attn_energies.t()

        # Return the softmax normalized probability scores (with added dimension)
        return F.softmax(attn_energies, dim=1).unsqueeze(1)



###################################################
# DEFINE DECODER
###################################################
class LuongAttnDecoderRNN(nn.Module):
    def __init__(self, attn_model, embedding, hidden_size, output_size, n_layers=1, dropout=0.1):
        super(LuongAttnDecoderRNN, self).__init__()

        # Keep for reference
        self.attn_model = attn_model
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.n_layers = n_layers
        self.dropout = dropout

        # Define layers
        self.embedding = embedding
        self.embedding_dropout = nn.Dropout(dropout)
        self.gru = nn.GRU(hidden_size, hidden_size, n_layers, dropout=(0 if n_layers == 1 else dropout))
        self.concat = nn.Linear(hidden_size * 2, hidden_size)
        self.out = nn.Linear(hidden_size, output_size)

        self.attn = Attn(attn_model, hidden_size)

    def forward(self, input_seq, last_hidden, encoder_outputs):
        # Note: we run this one step (word) at a time
        # Get embedding of current input word
        embedded = self.embedding(input_seq)
        embedded = self.embedding_dropout(embedded)
        # Forward through unidirectional GRU
        rnn_output, hidden = self.gru(embedded, last_hidden)
        # Calculate attention weights from the current GRU output
        attn_weights = self.attn(rnn_output, encoder_outputs)
        # Multiply attention weights to encoder outputs to get new "weighted sum" context vector
        context = attn_weights.bmm(encoder_outputs.transpose(0, 1))
        # Concatenate weighted context vector and GRU output using Luong eq. 5
        rnn_output = rnn_output.squeeze(0)
        context = context.squeeze(1)
        concat_input = torch.cat((rnn_output, context), 1)
        concat_output = torch.tanh(self.concat(concat_input))
        # Predict next word using Luong eq. 6
        output = self.out(concat_output)
        output = F.softmax(output, dim=1)
        # Return output and final hidden state
        return output, hidden



###################################################
# DATA HANDLING
###################################################
class Voc:
    def __init__(self, name):
        self.name = name
        self.trimmed = False
        self.word2index = {}
        self.word2count = {}
        self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
        self.num_words = 3  # Count SOS, EOS, PAD

    def addSentence(self, sentence):
        for word in sentence.split(' '):
            self.addWord(word)

    def addWord(self, word):
        if word not in self.word2index:
            self.word2index[word] = self.num_words
            self.word2count[word] = 1
            self.index2word[self.num_words] = word
            self.num_words += 1
        else:
            self.word2count[word] += 1

    # Remove words below a certain count threshold
    def trim(self, min_count):
        if self.trimmed:
            return
        self.trimmed = True

        keep_words = []

        for k, v in self.word2count.items():
            if v >= min_count:
                keep_words.append(k)

        print('keep_words {} / {} = {:.4f}'.format(
            len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index)
        ))

        # Reinitialize dictionaries
        self.word2index = {}
        self.word2count = {}
        self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
        self.num_words = 3 # Count default tokens

        for word in keep_words:
            self.addWord(word)


# Lowercase and remove non-letter characters
def normalizeString(s):
    s = s.lower()
    s = re.sub(r"([.!?])", r" \1", s)
    s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
    return s

# Takes string sentence, returns sentence of word indexes
def indexesFromSentence(voc, sentence):
    return [voc.word2index[word] for word in sentence.split(' ')] + [EOS_token]


###################################################
# DECODE DRIVER
###################################################
class GreedySearchDecoder(torch.jit.ScriptModule):
    def __init__(self, encoder, decoder):
        super(GreedySearchDecoder, self).__init__()
        self.encoder = encoder
        self.decoder = decoder

    @torch.jit.script_method
    def forward(self, input_seq, input_length, max_length):
        # Forward input through encoder model
        # print("input_seq:", input_seq, input_seq.size(), input_seq.dtype)
        # print("input_length:", input_length, input_length.size(), input_length.dtype)
        encoder_outputs, encoder_hidden = self.encoder(input_seq, input_length)
        # Prepare encoder's final hidden layer to be first hidden input to the decoder
        decoder_hidden = encoder_hidden[:decoder.n_layers]
        # Initialize decoder input with SOS_token
        decoder_input = torch.LongTensor([[SOS_token]])
        decoder_input = decoder_input.to(device)
        # Initialize tensors to append decoded words to
        all_tokens = torch.zeros([0]).long()
        all_scores = torch.zeros([0])
        all_tokens = all_tokens.to(device)
        all_scores = all_scores.to(device)
        # Iteratively decode one word token at a time
        for _ in range(max_length):
            # print("decoder_input:", decoder_input, decoder_input.size(), decoder_input.dtype)
            # print("decoder_hidden:", decoder_hidden.size(), decoder_hidden.dtype)
            # print("encoder_outputs:", encoder_outputs.size(), encoder_outputs.dtype)
            # Forward pass through decoder
            decoder_output, decoder_hidden = self.decoder(decoder_input, decoder_hidden, encoder_outputs)
            # Obtain most likely word token and its softmax score
            decoder_scores, decoder_input = torch.max(decoder_output, dim=1)
            # Record token and score
            all_tokens = torch.cat((all_tokens, decoder_input), dim=0)
            all_scores = torch.cat((all_scores, decoder_scores), dim=0)
            # Prepare current token to be next decoder input (add a dimension)
            decoder_input = torch.unsqueeze(decoder_input, 0)
        # Return collections of word tokens and scores
        return all_tokens, all_scores


###################################################
# EVALUATE INPUTS
###################################################
def evaluate(encoder, decoder, searcher, voc, sentence, max_length=MAX_LENGTH):
    ### Format input sentence as a batch
    # words -> indexes
    indexes_batch = [indexesFromSentence(voc, sentence)]
    # Create lengths tensor
    lengths = torch.tensor([len(indexes) for indexes in indexes_batch])
    # Transpose dimensions of batch to match models' expectations
    input_batch = torch.LongTensor(indexes_batch).transpose(0, 1)
    # Use appropriate device
    input_batch = input_batch.to(device)
    lengths = lengths.to(device)
    # Decode sentence with searcher
    tokens, scores = searcher(input_batch, lengths, max_length)
    # indexes -> words
    decoded_words = [voc.index2word[token.item()] for token in tokens]
    return decoded_words


def evaluateInput(encoder, decoder, searcher, voc):
    input_sentence = ''
    while(1):
        try:
            # Get input sentence
            input_sentence = input('> ')
            # Check if it is quit case
            if input_sentence == 'q' or input_sentence == 'quit': break
            # Normalize sentence
            input_sentence = normalizeString(input_sentence)
            # Evaluate sentence
            output_words = evaluate(encoder, decoder, searcher, voc, input_sentence)
            # Format and print response sentence
            output_words[:] = [x for x in output_words if not (x == 'EOS' or x == 'PAD')]
            print('Bot:', ' '.join(output_words))

        except KeyError:
            print("Error: Encountered unknown word.")

# Normalize input sentence and call evaluate()
def evaluateExample(sentence, encoder, decoder, searcher, voc):
    print("> " + sentence)
    # Normalize sentence
    input_sentence = normalizeString(sentence)
    # Evaluate sentence
    output_words = evaluate(encoder, decoder, searcher, voc, input_sentence)
    output_sentence = ' '.join(output_words)
    print('bot:', output_sentence)


###################################################
# LOAD MODEL
###################################################
save_dir = os.path.join("data", "save")
corpus_name = "cornell movie-dialogs corpus"

# Configure models
model_name = 'cb_model'
attn_model = 'dot'
#attn_model = 'general'
#attn_model = 'concat'
hidden_size = 500
encoder_n_layers = 2
decoder_n_layers = 2
dropout = 0.1
batch_size = 64

# Set checkpoint to load from
checkpoint_iter = 4000
loadFilename = os.path.join(save_dir, model_name, corpus_name,
                            '{}-{}_{}'.format(encoder_n_layers, decoder_n_layers, hidden_size),
                            '{}_checkpoint.tar'.format(checkpoint_iter))


# Load model
# If loading on same machine the model was trained on
checkpoint = torch.load(loadFilename)
# If loading a model trained on GPU to CPU
#checkpoint = torch.load(loadFilename, map_location=torch.device('cpu'))
encoder_sd = checkpoint['en']
decoder_sd = checkpoint['de']
encoder_optimizer_sd = checkpoint['en_opt']
decoder_optimizer_sd = checkpoint['de_opt']
embedding_sd = checkpoint['embedding']
voc = Voc(corpus_name)
voc.__dict__ = checkpoint['voc_dict']


print('Building encoder and decoder ...')
# Initialize word embeddings
embedding = nn.Embedding(voc.num_words, hidden_size)
embedding.load_state_dict(embedding_sd)
# Initialize encoder & decoder models
encoder = EncoderRNN(hidden_size, embedding, encoder_n_layers, dropout)
decoder = LuongAttnDecoderRNN(attn_model, embedding, hidden_size, voc.num_words, decoder_n_layers, dropout)
# Load trained model params
encoder.load_state_dict(encoder_sd)
decoder.load_state_dict(decoder_sd)
# Use appropriate device
encoder = encoder.to(device)
decoder = decoder.to(device)
# Set dropout layers to eval mode
encoder.eval()
decoder.eval()
print('Models built and ready to go!')


################################################################
# CONVERT MODEL TO TORCH SCRIPT
################################################################
### Convert encoder model
test_seq = torch.LongTensor(MAX_LENGTH, 1).random_(0, voc.num_words)
test_seq_length = torch.LongTensor([test_seq.size()[0]])
# print("\n\n", "test_seq:", test_seq, test_seq.size(), test_seq.dtype)
# print("test_seq_length:", test_seq_length, test_seq_length.size(), test_seq_length.dtype)
traced_encoder = torch.jit.trace(encoder, (test_seq, test_seq_length))

### Convert decoder model
# Generate artificial encoder output
test_encoder_outputs, test_encoder_hidden = traced_encoder(test_seq, test_seq_length)
test_decoder_hidden = test_encoder_hidden[:decoder.n_layers]
test_decoder_input = torch.LongTensor(1, 1).random_(0, voc.num_words)
# print("test_decoder_input:", test_decoder_input, test_decoder_input.size(), test_decoder_input.dtype)
# print("test_decoder_hidden:", test_decoder_hidden.size(), test_decoder_hidden.dtype)
# print("test_encoder_outputs:", test_encoder_outputs.size(), test_encoder_outputs.dtype)
traced_decoder = torch.jit.trace(decoder, (test_decoder_input, test_decoder_hidden, test_encoder_outputs))


# Print graphs
print('encoder graph', traced_encoder.__getattr__('forward').graph)
print('decoder graph', traced_decoder.__getattr__('forward').graph)


# Initialize search module
#searcher = GreedySearchDecoder(encoder, decoder)
searcher = GreedySearchDecoder(traced_encoder, traced_decoder)

# Evaluate examples
sentences = ["hello", "what's up?", "who are you?", "where are we?", "where are you from?"]
for s in sentences:
    evaluateExample(s, traced_encoder, traced_decoder, searcher, voc)