pytorch做seq2seq注意力模型的翻譯

以下是對pytorch 1.0版本 的seq2seq+注意力模型做法語--英語翻譯的理解（這個代碼在pytorch0.4上也可以正常跑）：

# -*- coding: utf-8 -*-
"""
Translation with a Sequence to Sequence Network and Attention
*************************************************************
**Author**: `Sean Robertson <https://github.com/spro/practical-pytorch>`_

In this project we will be teaching a neural network to translate from
French to English.

::

    [KEY: > input, = target, < output]

    > il est en train de peindre un tableau .
    = he is painting a picture .
    < he is painting a picture .

    > pourquoi ne pas essayer ce vin delicieux ?
    = why not try that delicious wine ?
    < why not try that delicious wine ?

    > elle n est pas poete mais romanciere .
    = she is not a poet but a novelist .
    < she not not a poet but a novelist .

    > vous etes trop maigre .
    = you re too skinny .
    < you re all alone .

... to varying degrees of success.

This is made possible by the simple but powerful idea of the `sequence
to sequence network <http://arxiv.org/abs/1409.3215>`__, in which two
recurrent neural networks work together to transform one sequence to
another. An encoder network condenses an input sequence into a vector,
and a decoder network unfolds that vector into a new sequence.

.. figure:: /_static/img/seq-seq-images/seq2seq.png
   :alt:

To improve upon this model we'll use an `attention
mechanism <https://arxiv.org/abs/1409.0473>`__, which lets the decoder
learn to focus over a specific range of the input sequence.

**Recommended Reading:**

I assume you have at least installed PyTorch, know Python, and
understand Tensors:

-  https://pytorch.org/ For installation instructions
-  :doc:`/beginner/deep_learning_60min_blitz` to get started with PyTorch in general
-  :doc:`/beginner/pytorch_with_examples` for a wide and deep overview
-  :doc:`/beginner/former_torchies_tutorial` if you are former Lua Torch user


It would also be useful to know about Sequence to Sequence networks and
how they work:

-  `Learning Phrase Representations using RNN Encoder-Decoder for
   Statistical Machine Translation <http://arxiv.org/abs/1406.1078>`__
-  `Sequence to Sequence Learning with Neural
   Networks <http://arxiv.org/abs/1409.3215>`__
-  `Neural Machine Translation by Jointly Learning to Align and
   Translate <https://arxiv.org/abs/1409.0473>`__
-  `A Neural Conversational Model <http://arxiv.org/abs/1506.05869>`__

You will also find the previous tutorials on
:doc:`/intermediate/char_rnn_classification_tutorial`
and :doc:`/intermediate/char_rnn_generation_tutorial`
helpful as those concepts are very similar to the Encoder and Decoder
models, respectively.

And for more, read the papers that introduced these topics:

-  `Learning Phrase Representations using RNN Encoder-Decoder for
   Statistical Machine Translation <http://arxiv.org/abs/1406.1078>`__
-  `Sequence to Sequence Learning with Neural
   Networks <http://arxiv.org/abs/1409.3215>`__
-  `Neural Machine Translation by Jointly Learning to Align and
   Translate <https://arxiv.org/abs/1409.0473>`__
-  `A Neural Conversational Model <http://arxiv.org/abs/1506.05869>`__


**Requirements**
"""
from __future__ import unicode_literals, print_function, division
from io import open
import unicodedata
import string
import re
import random

import torch
import torch.nn as nn
from torch import optim
import torch.nn.functional as F

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

######################################################################
# Loading data files
# ==================
#
# The data for this project is a set of many thousands of English to
# French translation pairs.
#
# `This question on Open Data Stack
# Exchange <http://opendata.stackexchange.com/questions/3888/dataset-of-sentences-translated-into-many-languages>`__
# pointed me to the open translation site http://tatoeba.org/ which has
# downloads available at http://tatoeba.org/eng/downloads - and better
# yet, someone did the extra work of splitting language pairs into
# individual text files here: http://www.manythings.org/anki/
#
# The English to French pairs are too big to include in the repo, so
# download to ``data/eng-fra.txt`` before continuing. The file is a tab
# separated list of translation pairs:
#
# ::
#
#     I am cold.    J'ai froid.
#
# .. Note::
#    Download the data from
#    `here <https://download.pytorch.org/tutorial/data.zip>`_
#    and extract it to the current directory.

######################################################################
# Similar to the character encoding used in the character-level RNN
# tutorials, we will be representing each word in a language as a one-hot
# vector, or giant vector of zeros except for a single one (at the index
# of the word). Compared to the dozens of characters that might exist in a
# language, there are many many more words, so the encoding vector is much
# larger. We will however cheat a bit and trim the data to only use a few
# thousand words per language.
#
# .. figure:: /_static/img/seq-seq-images/word-encoding.png
#    :alt:
#
#


######################################################################
# We'll need a unique index per word to use as the inputs and targets of
# the networks later. To keep track of all this we will use a helper class
# called ``Lang`` which has word → index (``word2index``) and index → word
# (``index2word``) dictionaries, as well as a count of each word
# ``word2count`` to use to later replace rare words.
#

SOS_token = 0
EOS_token = 1


# 每個單詞需要對應唯一的索引作為稍后的網絡輸入和目標.為了追蹤這些索引
# 則使用一個幫助類 Lang ，類中有 詞 → 索引 (word2index) 和 索引 → 詞
# (index2word) 的字典, 以及每個詞word2count 用來替換稀疏詞匯.


# 此處創建的Lang 對象來表示源/目標語言，它包含三部分：word2index、
# index2word 和word2count，分別表示單詞到id、id 到單詞和單詞的詞頻。
# word2count的作用是用於過濾一些低頻詞（把它變成unknown）

class Lang:
    def __init__(self, name):
        self.name = name
        self.word2index = {}
        self.word2count = {}
        self.index2word = {0: "SOS", 1: "EOS"}
        self.n_words = 2  # Count SOS and EOS

    def addSentence(self, sentence):
        for word in sentence.split(' '):
            self.addWord(word)  # 用於添加單詞

    def addWord(self, word):
        if word not in self.word2index:  # 是不是新的詞
            # 如果不在word2index里，則需要新的定義字典
            self.word2index[word] = self.n_words
            self.word2count[word] = 1
            self.index2word[self.n_words] = word
            self.n_words += 1  # 相當於每次index+1
        else:
            self.word2count[word] += 1  # 計算每次詞的個數


######################################################################
# The files are all in Unicode, to simplify we will turn Unicode
# characters to ASCII, make everything lowercase, and trim most
# punctuation.
#

# Turn a Unicode string to plain ASCII, thanks to
# http://stackoverflow.com/a/518232/2809427

# 此處是為了將Unicode字符串轉換為純ASCII
# 原文件是Unicode編碼
def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
    )


# Lowercase, trim, and remove non-letter characters

# 小寫,修剪和刪除非字母字符
def normalizeString(s):
    s = unicodeToAscii(s.lower().strip())
    s = re.sub(r"([.!?])", r" \1", s)
    s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
    return s


######################################################################
# To read the data file we will split the file into lines, and then split
# lines into pairs. The files are all English → Other Language, so if we
# want to translate from Other Language → English I added the ``reverse``
# flag to reverse the pairs.
#


# 要讀取數據文件,我們將把文件分成行,然后將行成對分開. 這些文件
# 都是英文→其他語言,所以如果我們想從其他語言翻譯→英文,我們添加了
# 翻轉標志 reverse來翻轉詞語對.
def readLangs(lang1, lang2, reverse=False):
    print("Reading lines...")

    # Read the file and split into lines
    # 讀取文件並按行分開
    lines = open('data/%s-%s.txt' % (lang1, lang2), encoding='utf-8'). \
        read().strip().split('\n')

    # Split every line into pairs and normalize
    # 將每一行分成兩列並進行標准化
    pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]

    # Reverse pairs, make Lang instances
    # 翻轉對,Lang實例化
    if reverse:
        pairs = [list(reversed(p)) for p in pairs]
        input_lang = Lang(lang2)
        output_lang = Lang(lang1)
    else:
        input_lang = Lang(lang1)
        output_lang = Lang(lang2)

    return input_lang, output_lang, pairs


######################################################################
# Since there are a *lot* of example sentences and we want to train
# something quickly, we'll trim the data set to only relatively short and
# simple sentences. Here the maximum length is 10 words (that includes
# ending punctuation) and we're filtering to sentences that translate to
# the form "I am" or "He is" etc. (accounting for apostrophes replaced
# earlier).
#

# 由於例句較多,為了方便快速訓練,則會將數據集裁剪為相對簡短的句子.
# 這里的單詞的最大長度是10詞(包括結束標點符號),
# 保留”I am” 和”He is” 開頭的數據

MAX_LENGTH = 10

eng_prefixes = (
    "i am ", "i m ",
    "he is", "he s ",
    "she is", "she s",
    "you are", "you re ",
    "we are", "we re ",
    "they are", "they re "
)


def filterPair(p):
    return len(p[0].split(' ')) < MAX_LENGTH and \
           len(p[1].split(' ')) < MAX_LENGTH and \
           p[1].startswith(eng_prefixes)
    # 是否滿足長度


def filterPairs(pairs):
    return [pair for pair in pairs if filterPair(pair)]


######################################################################
# The full process for preparing the data is:
#
# -  Read text file and split into lines, split lines into pairs
# -  Normalize text, filter by length and content
# -  Make word lists from sentences in pairs
#

def prepareData(lang1, lang2, reverse=False):
    input_lang, output_lang, pairs = readLangs(lang1, lang2, reverse)
    # 讀入數據lang1,lang2,並翻轉
    print("Read %s sentence pairs" % len(pairs))
    # 一共讀入了多少對
    pairs = filterPairs(pairs)
    # 符合條件的配對有多少對
    print("Trimmed to %s sentence pairs" % len(pairs))
    print("Counting words...")
    for pair in pairs:
        input_lang.addSentence(pair[0])
        output_lang.addSentence(pair[1])
    print("Counted words:")
    print(input_lang.name, input_lang.n_words)
    print(output_lang.name, output_lang.n_words)
    return input_lang, output_lang, pairs


# 對數據進行預處理
input_lang, output_lang, pairs = prepareData('eng', 'fra', True)
print(random.choice(pairs))  # 隨機展示一對


######################################################################
# The Seq2Seq Model
# =================
#
# A Recurrent Neural Network, or RNN, is a network that operates on a
# sequence and uses its own output as input for subsequent steps.
#
# A `Sequence to Sequence network <http://arxiv.org/abs/1409.3215>`__, or
# seq2seq network, or `Encoder Decoder
# network <https://arxiv.org/pdf/1406.1078v3.pdf>`__, is a model
# consisting of two RNNs called the encoder and decoder. The encoder reads
# an input sequence and outputs a single vector, and the decoder reads
# that vector to produce an output sequence.
#
# .. figure:: /_static/img/seq-seq-images/seq2seq.png
#    :alt:
#
# Unlike sequence prediction with a single RNN, where every input
# corresponds to an output, the seq2seq model frees us from sequence
# length and order, which makes it ideal for translation between two
# languages.
#
# Consider the sentence "Je ne suis pas le chat noir" → "I am not the
# black cat". Most of the words in the input sentence have a direct
# translation in the output sentence, but are in slightly different
# orders, e.g. "chat noir" and "black cat". Because of the "ne/pas"
# construction there is also one more word in the input sentence. It would
# be difficult to produce a correct translation directly from the sequence
# of input words.
#
# With a seq2seq model the encoder creates a single vector which, in the
# ideal case, encodes the "meaning" of the input sequence into a single
# vector — a single point in some N dimensional space of sentences.
#


######################################################################
# The Encoder
# -----------
#
# The encoder of a seq2seq network is a RNN that outputs some value for
# every word from the input sentence. For every input word the encoder
# outputs a vector and a hidden state, and uses the hidden state for the
# next input word.
#
# .. figure:: /_static/img/seq-seq-images/encoder-network.png
#    :alt:
#
#

class EncoderRNN(nn.Module):
    def __init__(self, input_size, hidden_size):
        super(EncoderRNN, self).__init__()
        self.hidden_size = hidden_size
        # 定義隱藏層
        self.embedding = nn.Embedding(input_size, hidden_size)
        # word embedding的定義可以這么理解，例如nn.Embedding(2, 4)
        # 2表示有2個詞，4表示4維度，其實也就是一個2x4的矩陣，
        # 如果有100個詞，每個詞10維，就可以寫為nn.Embedding(100, 10)
        # 注意這里的詞向量的建立只是初始的詞向量，並沒有經過任何修改優化
        # 需要建立神經網絡通過learning的辦法修改word embedding里面的參數
        # 使得word embedding每一個詞向量能夠表示每一個不同的詞。
        self.gru = nn.GRU(hidden_size, hidden_size)  # 用到了上面提到的GRU模型

    def forward(self, input, hidden):
        embedded = self.embedding(input).view(1, 1, -1)  # -1是指自適應，view相當於reshape函數
        output = embedded
        output, hidden = self.gru(output, hidden)
        return output, hidden

    def initHidden(self):  # 初始化
        return torch.zeros(1, 1, self.hidden_size, device=device)


######################################################################
# The Decoder
# -----------
#
# The decoder is another RNN that takes the encoder output vector(s) and
# outputs a sequence of words to create the translation.
#


######################################################################
# Simple Decoder
# ^^^^^^^^^^^^^^
#
# In the simplest seq2seq decoder we use only last output of the encoder.
# This last output is sometimes called the *context vector* as it encodes
# context from the entire sequence. This context vector is used as the
# initial hidden state of the decoder.
#
# At every step of decoding, the decoder is given an input token and
# hidden state. The initial input token is the start-of-string ``<SOS>``
# token, and the first hidden state is the context vector (the encoder's
# last hidden state).
#
# .. figure:: /_static/img/seq-seq-images/decoder-network.png
#    :alt:
#
#

class DecoderRNN(nn.Module):
    # DecoderRNN與encoderRNN結構類似，結合圖片即可搞清邏輯
    def __init__(self, hidden_size, output_size):
        super(DecoderRNN, self).__init__()
        self.hidden_size = hidden_size

        self.embedding = nn.Embedding(output_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size)
        self.out = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        output = self.embedding(input).view(1, 1, -1)  # -1是指自適應，view相當於reshape函數
        output = F.relu(output)
        output, hidden = self.gru(output, hidden)  # 此處使用gru神經網絡
        # 對上述結果使用softmax,就是圖片中左邊倒數第二個
        output = self.softmax(self.out(output[0]))
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)


######################################################################
# I encourage you to train and observe the results of this model, but to
# save space we'll be going straight for the gold and introducing the
# Attention Mechanism.
#


######################################################################
# Attention Decoder
# ^^^^^^^^^^^^^^^^^
#
# If only the context vector is passed betweeen the encoder and decoder,
# that single vector carries the burden of encoding the entire sentence.
#
# Attention allows the decoder network to "focus" on a different part of
# the encoder's outputs for every step of the decoder's own outputs. First
# we calculate a set of *attention weights*. These will be multiplied by
# the encoder output vectors to create a weighted combination. The result
# (called ``attn_applied`` in the code) should contain information about
# that specific part of the input sequence, and thus help the decoder
# choose the right output words.
#
# .. figure:: https://i.imgur.com/1152PYf.png
#    :alt:
#
# Calculating the attention weights is done with another feed-forward
# layer ``attn``, using the decoder's input and hidden state as inputs.
# Because there are sentences of all sizes in the training data, to
# actually create and train this layer we have to choose a maximum
# sentence length (input length, for encoder outputs) that it can apply
# to. Sentences of the maximum length will use all the attention weights,
# while shorter sentences will only use the first few.
#
# .. figure:: /_static/img/seq-seq-images/attention-decoder-network.png
#    :alt:
#
#

class AttnDecoderRNN(nn.Module):
    def __init__(self, hidden_size, output_size, dropout_p=0.1, max_length=MAX_LENGTH):
        super(AttnDecoderRNN, self).__init__()
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.dropout_p = dropout_p
        self.max_length = max_length

        self.embedding = nn.Embedding(self.output_size, self.hidden_size)
        self.attn = nn.Linear(self.hidden_size * 2, self.max_length)
        self.attn_combine = nn.Linear(self.hidden_size * 2, self.hidden_size)
        self.dropout = nn.Dropout(self.dropout_p)
        self.gru = nn.GRU(self.hidden_size, self.hidden_size)
        self.out = nn.Linear(self.hidden_size, self.output_size)

    def forward(self, input, hidden, encoder_outputs):
        # 對於輸入的input內容進行embedding和dropout操作
        # dropout是指隨機丟棄一些神經元
        embedded = self.embedding(input).view(1, 1, -1)
        embedded = self.dropout(embedded)

        # 此處相當於學出來了attention的權重
        # 需要注意的是torch的concatenate函數是torch.cat，是在已有的維度上拼接，
        # 而stack是建立一個新的維度，然后再在該緯度上進行拼接。
        attn_weights = F.softmax(
            self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)

        # 將attention權重作用在encoder_outputs上
        # 對存儲在兩個批batch1和batch2內的矩陣進行批矩陣乘操作。
        # batch1和 batch2都為包含相同數量矩陣的3維張量。
        # 如果batch1是形為b×n×m的張量，batch1是形為b×m×p的張量，
        # 則out和mat的形狀都是n×p
        attn_applied = torch.bmm(attn_weights.unsqueeze(0),
                                 encoder_outputs.unsqueeze(0))
        # 拼接操作，將embedded和attn_Applied拼接起來
        output = torch.cat((embedded[0], attn_applied[0]), 1)
        # 返回一個新的張量，對輸入的制定位置插入維度 1
        output = self.attn_combine(output).unsqueeze(0)

        output = F.relu(output)
        output, hidden = self.gru(output, hidden)

        output = F.log_softmax(self.out(output[0]), dim=1)
        return output, hidden, attn_weights

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)


######################################################################
# .. note:: There are other forms of attention that work around the length
#   limitation by using a relative position approach. Read about "local
#   attention" in `Effective Approaches to Attention-based Neural Machine
#   Translation <https://arxiv.org/abs/1508.04025>`__.
#
# Training
# ========
#
# Preparing Training Data
# -----------------------
#
# To train, for each pair we will need an input tensor (indexes of the
# words in the input sentence) and target tensor (indexes of the words in
# the target sentence). While creating these vectors we will append the
# EOS token to both sequences.
#

def indexesFromSentence(lang, sentence):
    return [lang.word2index[word] for word in sentence.split(' ')]


def tensorFromSentence(lang, sentence):
    # 獲得詞的索引
    indexes = indexesFromSentence(lang, sentence)
    # 將EOS標記添加到兩個序列中
    indexes.append(EOS_token)
    return torch.tensor(indexes, dtype=torch.long, device=device).view(-1, 1)


def tensorsFromPair(pair):
    # 每一對為需要輸入的張量（輸入句子中的詞的索引）和目標張量
    # （目標語句中的詞的索引）
    input_tensor = tensorFromSentence(input_lang, pair[0])
    target_tensor = tensorFromSentence(output_lang, pair[1])
    return (input_tensor, target_tensor)


######################################################################
# Training the Model
# ------------------
#
# To train we run the input sentence through the encoder, and keep track
# of every output and the latest hidden state. Then the decoder is given
# the ``<SOS>`` token as its first input, and the last hidden state of the
# encoder as its first hidden state.
#
# "Teacher forcing" is the concept of using the real target outputs as
# each next input, instead of using the decoder's guess as the next input.
# Using teacher forcing causes it to converge faster but `when the trained
# network is exploited, it may exhibit
# instability <http://minds.jacobs-university.de/sites/default/files/uploads/papers/ESNTutorialRev.pdf>`__.
#
# You can observe outputs of teacher-forced networks that read with
# coherent grammar but wander far from the correct translation -
# intuitively it has learned to represent the output grammar and can "pick
# up" the meaning once the teacher tells it the first few words, but it
# has not properly learned how to create the sentence from the translation
# in the first place.
#
# Because of the freedom PyTorch's autograd gives us, we can randomly
# choose to use teacher forcing or not with a simple if statement. Turn
# ``teacher_forcing_ratio`` up to use more of it.
#

teacher_forcing_ratio = 0.5


# teacher forcing即指使用教師強迫其能夠更快的收斂
# 不過當訓練好的網絡被利用時，容易表現出不穩定性
# teacher_forcing_ratio即指教師訓練比率
# 用於訓練的函數


def train(input_tensor, target_tensor, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion,
          max_length=MAX_LENGTH):
    # encoder即指EncoderRNN(input_lang.n_words, hidden_size)
    # attn_decoder即指 AttnDecoderRNN(hidden_size, output_lang.n_words, dropout_p=0.1)
    # hidden=256
    encoder_hidden = encoder.initHidden()

    # encoder_optimizer 即指optim.SGD(encoder.parameters(), lr=learning_rate)
    # decoder_optimizer 即指optim.SGD(decoder.parameters(), lr=learning_rate)
    # nn.Parameter()是Variable的一種，常被用於模塊參數(module parameter)。
    # Parameters 是 Variable 的子類。Paramenters和Modules一起使用的時候會有一些特殊的屬性，
    # 即：當Paramenters賦值給Module的屬性的時候，他會自動的被加到 Module的 參數列表中
    # (即：會出現在 parameters() 迭代器中)。將Varibale賦值給Module屬性則不會有這樣的影響。
    # 這樣做的原因是：我們有時候會需要緩存一些臨時的狀態(state), 比如：模型中RNN的最后一個隱狀態。
    # 如果沒有Parameter這個類的話，那么這些臨時變量也會注冊成為模型變量。
    encoder_optimizer.zero_grad()
    decoder_optimizer.zero_grad()

    # 得到長度
    input_length = input_tensor.size(0)
    target_length = target_tensor.size(0)

    # 初始化outour值
    encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)

    loss = 0

    # 以下循環是學習過程
    for ei in range(input_length):
        encoder_output, encoder_hidden = encoder(input_tensor[ei], encoder_hidden)
        encoder_outputs[ei] = encoder_output[0, 0]  # 這里為什么取 0,0

    # 定義decoder的Input值
    decoder_input = torch.tensor([[SOS_token]], device=device)

    decoder_hidden = encoder_hidden

    use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False

    if use_teacher_forcing:
        # Teacher forcing: Feed the target as the next input
        # 教師強制: 將目標作為下一個輸入
        # 你觀察教師強迫網絡的輸出,這些網絡是用連貫的語法閱讀的,但卻遠離了正確的翻譯 -
        # 直觀地來看它已經學會了代表輸出語法,並且一旦老師告訴它前幾個單詞,就可以"拾取"它的意思,
        # 但它沒有適當地學會如何從翻譯中創建句子.
        for di in range(target_length):
            # 通過decoder得到輸出值
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)
            # 定義損失函數並計算
            loss += criterion(decoder_output, target_tensor[di])
            decoder_input = target_tensor[di]  # Teacher forcing

    else:
        # Without teacher forcing: use its own predictions as the next input
        # 沒有教師強迫: 使用自己的預測作為下一個輸入
        for di in range(target_length):
            # 通過decoder得到輸出值
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)

            # topk：第k個最小元素,返回第k個最小元素
            # 返回前k個最大元素，注意是前k個，largest=False，返回前k個最小元素
            # 此函數的功能是求取1-D 或N-D Tensor的最低維度的前k個最大的值，返回值為兩個Tuple
            # 其中values是前k個最大值的Tuple，indices是對應的下標，默認返回結果是從大到小排序的。
            topv, topi = decoder_output.topk(1)
            decoder_input = topi.squeeze().detach()  # detach from history as input

            loss += criterion(decoder_output, target_tensor[di])
            if decoder_input.item() == EOS_token:
                break
    # 反向傳播
    loss.backward()

    # 更新參數
    encoder_optimizer.step()
    decoder_optimizer.step()

    return loss.item() / target_length


######################################################################
# This is a helper function to print time elapsed and estimated time
# remaining given the current time and progress %.
#

import time
import math


# 根據當前時間和進度百分比,這是一個幫助功能,用於打印經過的時間和估計的剩余時間.

def asMinutes(s):
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)


def timeSince(since, percent):
    now = time.time()
    s = now - since
    es = s / (percent)
    rs = es - s
    return '%s (- %s)' % (asMinutes(s), asMinutes(rs))


######################################################################
# The whole training process looks like this:
#
# -  Start a timer
# -  Initialize optimizers and criterion
# -  Create set of training pairs
# -  Start empty losses array for plotting
#
# Then we call ``train`` many times and occasionally print the progress (%
# of examples, time so far, estimated time) and average loss.
#

def trainIters(encoder, decoder, n_iters, print_every=1000, plot_every=100, learning_rate=0.01):
    start = time.time()
    plot_losses = []
    print_loss_total = 0  # Reset every print_every
    plot_loss_total = 0  # Reset every plot_every

    encoder_optimizer = optim.SGD(encoder.parameters(), lr=learning_rate)
    decoder_optimizer = optim.SGD(decoder.parameters(), lr=learning_rate)

    # 獲取訓練的一對樣本
    training_pairs = [tensorsFromPair(random.choice(pairs))
                      for i in range(n_iters)]
    # 定義出的損失函數
    criterion = nn.NLLLoss()

    for iter in range(1, n_iters + 1):
        training_pair = training_pairs[iter - 1]
        input_tensor = training_pair[0]
        target_tensor = training_pair[1]

        # 訓練的過程並用於當損失函數
        loss = train(input_tensor, target_tensor, encoder,
                     decoder, encoder_optimizer, decoder_optimizer, criterion)
        print_loss_total += loss
        plot_loss_total += loss

        if iter % print_every == 0:
            print_loss_avg = print_loss_total / print_every
            print_loss_total = 0
            # 打印進度(樣本的百分比,到目前為止的時間,估計的時間)和平均損失.
            print('%s (%d %d%%) %.4f' % (timeSince(start, iter / n_iters),
                                         iter, iter / n_iters * 100, print_loss_avg))

        if iter % plot_every == 0:
            plot_loss_avg = plot_loss_total / plot_every
            plot_losses.append(plot_loss_avg)
            plot_loss_total = 0
    # 繪制圖像
    showPlot(plot_losses)


######################################################################
# Plotting results
# ----------------
#
# Plotting is done with matplotlib, using the array of loss values
# ``plot_losses`` saved while training.
#

import matplotlib.pyplot as plt

plt.switch_backend('agg')
import matplotlib.ticker as ticker
import numpy as np


# 使用matplotlib進行繪圖，使用訓練時保存的損失值plot_losses數組.
def showPlot(points):
    plt.figure()
    fig, ax = plt.subplots()
    # this locator puts ticks at regular intervals
    # 這個定位器會定期發出提示信息
    loc = ticker.MultipleLocator(base=0.2)
    ax.yaxis.set_major_locator(loc)
    plt.plot(points)


######################################################################
# Evaluation
# ==========
#
# Evaluation is mostly the same as training, but there are no targets so
# we simply feed the decoder's predictions back to itself for each step.
# Every time it predicts a word we add it to the output string, and if it
# predicts the EOS token we stop there. We also store the decoder's
# attention outputs for display later.
#

def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):
    with torch.no_grad():
        # 從sentence中得到對應的變量
        input_tensor = tensorFromSentence(input_lang, sentence)
        # 長度
        input_length = input_tensor.size()[0]

        # encoder即指EncoderRNN(input_lang.n_words, hidden_size)
        # attn_decoder即指 AttnDecoderRNN(hidden_size,
        # output_lang.n_words, dropout_p=0.1)
        # hidden=256
        encoder_hidden = encoder.initHidden()

        # 初始化outputs值
        encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)

        # 以下是學習過程
        for ei in range(input_length):
            encoder_output, encoder_hidden = encoder(input_tensor[ei],
                                                     encoder_hidden)
            encoder_outputs[ei] += encoder_output[0, 0]

        # 定義好decoder部分的input值
        decoder_input = torch.tensor([[SOS_token]], device=device)  # SOS

        # 設置好隱藏層
        decoder_hidden = encoder_hidden

        decoded_words = []
        decoder_attentions = torch.zeros(max_length, max_length)

        for di in range(max_length):
            # 得到結果
            decoder_output, decoder_hidden, decoder_attention = decoder(decoder_input, decoder_hidden, encoder_outputs)

            # attention部分的數據
            decoder_attentions[di] = decoder_attention.data
            # 選擇output中的第一個值
            topv, topi = decoder_output.data.topk(1)
            if topi.item() == EOS_token:
                decoded_words.append('<EOS>')
                break
            else:
                decoded_words.append(output_lang.index2word[topi.item()])  # 將output_lang添加到decoded

            decoder_input = topi.squeeze().detach()

        return decoded_words, decoder_attentions[:di + 1]


######################################################################
# We can evaluate random sentences from the training set and print out the
# input, target, and output to make some subjective quality judgements:
#

# 從訓練集中評估隨機的句子並打印出輸入,目標和輸出以作出一些主觀質量判斷
def evaluateRandomly(encoder, decoder, n=10):
    for i in range(n):
        pair = random.choice(pairs)
        print('>', pair[0])
        print('=', pair[1])
        output_words, attentions = evaluate(encoder, decoder, pair[0])
        output_sentence = ' '.join(output_words)
        print('<', output_sentence)
        print('')


######################################################################
# Training and Evaluating
# =======================
#
# With all these helper functions in place (it looks like extra work, but
# it makes it easier to run multiple experiments) we can actually
# initialize a network and start training.
#
# Remember that the input sentences were heavily filtered. For this small
# dataset we can use relatively small networks of 256 hidden nodes and a
# single GRU layer. After about 40 minutes on a MacBook CPU we'll get some
# reasonable results.
#
# .. Note::
#    If you run this notebook you can train, interrupt the kernel,
#    evaluate, and continue training later. Comment out the lines where the
#    encoder and decoder are initialized and run ``trainIters`` again.
#

hidden_size = 256
# 編碼部分
encoder1 = EncoderRNN(input_lang.n_words, hidden_size).to(device)
# 加入了attention機制的解碼部分
attn_decoder1 = AttnDecoderRNN(hidden_size, output_lang.n_words, dropout_p=0.1).to(device)
# 訓練部分
trainIters(encoder1, attn_decoder1, 75000, print_every=5000)

######################################################################
# 隨機生成一組結果
evaluateRandomly(encoder1, attn_decoder1)

######################################################################
# Visualizing Attention
# ---------------------
#
# A useful property of the attention mechanism is its highly interpretable
# outputs. Because it is used to weight specific encoder outputs of the
# input sequence, we can imagine looking where the network is focused most
# at each time step.
#
# You could simply run ``plt.matshow(attentions)`` to see attention output
# displayed as a matrix, with the columns being input steps and rows being
# output steps:
#

output_words, attentions = evaluate(encoder1, attn_decoder1, "je suis trop froid .")
plt.matshow(attentions.numpy())


######################################################################
# For a better viewing experience we will do the extra work of adding axes
# and labels:

def showAttention(input_sentence, output_words, attentions):
    # Set up figure with colorbar
    fig = plt.figure()
    ax = fig.add_subplot(111)
    cax = ax.matshow(attentions.numpy(), cmap='bone')
    fig.colorbar(cax)

    # Set up axes
    ax.set_xticklabels([''] + input_sentence.split(' ') +
                       ['<EOS>'], rotation=90)
    ax.set_yticklabels([''] + output_words)

    # Show label at every tick
    ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
    ax.yaxis.set_major_locator(ticker.MultipleLocator(1))

    plt.show()


def evaluateAndShowAttention(input_sentence):
    output_words, attentions = evaluate(
        encoder1, attn_decoder1, input_sentence)
    print('input =', input_sentence)
    print('output =', ' '.join(output_words))
    showAttention(input_sentence, output_words, attentions)


evaluateAndShowAttention("elle a cinq ans de moins que moi .")
evaluateAndShowAttention("elle est trop petit .")
evaluateAndShowAttention("je ne crains pas de mourir .")
evaluateAndShowAttention("c est un jeune directeur plein de talent .")

######################################################################
# Exercises
# =========
#
# -  Try with a different dataset
#
#    -  Another language pair
#    -  Human → Machine (e.g. IOT commands)
#    -  Chat → Response
#    -  Question → Answer
#
# -  Replace the embeddings with pre-trained word embeddings such as word2vec or
#    GloVe
# -  Try with more layers, more hidden units, and more sentences. Compare
#    the training time and results.
# -  If you use a translation file where pairs have two of the same phrase
#    (``I am test \t I am test``), you can use this as an autoencoder. Try
#    this:
#
#    -  Train as an autoencoder
#    -  Save only the Encoder network
#    -  Train a new Decoder for translation from there
#