文本分類實戰（六）—— RCNN模型

1 大綱概述

　　文本分類這個系列將會有十篇左右，包括基於word2vec預訓練的文本分類，與及基於最新的預訓練模型（ELMo，BERT等）的文本分類。總共有以下系列：

　　word2vec預訓練詞向量

　　textCNN 模型

　　charCNN 模型

　　Bi-LSTM 模型

　　Bi-LSTM + Attention 模型

　　RCNN 模型

　　Adversarial LSTM 模型

　　Transformer 模型

　　ELMo 預訓練模型

　　BERT 預訓練模型

　　jupyter notebook代碼均在textClassifier倉庫中，python代碼在NLP-Project中的text_classfier中。

 

2 數據集

　　數據集為IMDB 電影影評，總共有三個數據文件，在/data/rawData目錄下，包括unlabeledTrainData.tsv，labeledTrainData.tsv，testData.tsv。在進行文本分類時需要有標簽的數據（labeledTrainData），數據預處理如文本分類實戰（一）—— word2vec預訓練詞向量中一樣，預處理后的文件為/data/preprocess/labeledTrain.csv。

 

3 RCNN 模型結構

　　RCNN模型來源於論文Recurrent Convolutional Neural Networks for Text Classification。模型結構圖如下：

　　

　　RCNN 整體的模型構建流程如下：

　　1）利用Bi-LSTM獲得上下文的信息，類似於語言模型。

　　2）將Bi-LSTM獲得的隱層輸出和詞向量拼接[fwOutput, wordEmbedding, bwOutput]。

　　3）將拼接后的向量非線性映射到低維。

　　4）向量中的每一個位置的值都取所有時序上的最大值，得到最終的特征向量，該過程類似於max-pool。

　　5）softmax分類。

 

4 參數配置

import os
import csv
import time
import datetime
import random
import json

import warnings
from collections import Counter
from math import sqrt

import gensim
import pandas as pd
import numpy as np
import tensorflow as tf
from sklearn.metrics import roc_auc_score, accuracy_score, precision_score, recall_score
warnings.filterwarnings("ignore")

 

# 配置參數

class TrainingConfig(object):
    epoches = 10
    evaluateEvery = 100
    checkpointEvery = 100
    learningRate = 0.001
    
class ModelConfig(object):
    embeddingSize = 200
    
    hiddenSizes = [128]  # LSTM結構的神經元個數
    
    dropoutKeepProb = 0.5
    l2RegLambda = 0.0
    
    outputSize = 128  # 從高維映射到低維的神經元個數
    
class Config(object):
    sequenceLength = 200  # 取了所有序列長度的均值
    batchSize = 128
    
    dataSource = "../data/preProcess/labeledTrain.csv"
    
    stopWordSource = "../data/english"
    
    numClasses = 1  # 二分類設置為1，多分類設置為類別的數目
    
    rate = 0.8  # 訓練集的比例
    
    training = TrainingConfig()
    
    model = ModelConfig()

    
# 實例化配置參數對象
config = Config()

 

5 生成訓練數據

　　1）將數據加載進來，將句子分割成詞表示，並去除低頻詞和停用詞。

　　2）將詞映射成索引表示，構建詞匯-索引映射表，並保存成json的數據格式，之后做inference時可以用到。（注意，有的詞可能不在word2vec的預訓練詞向量中，這種詞直接用UNK表示）

　　3）從預訓練的詞向量模型中讀取出詞向量，作為初始化值輸入到模型中。

　　4）將數據集分割成訓練集和測試集

# 數據預處理的類，生成訓練集和測試集

class Dataset(object):
    def __init__(self, config):
        self.config = config
        self._dataSource = config.dataSource
        self._stopWordSource = config.stopWordSource  
        
        self._sequenceLength = config.sequenceLength  # 每條輸入的序列處理為定長
        self._embeddingSize = config.model.embeddingSize
        self._batchSize = config.batchSize
        self._rate = config.rate
        
        self._stopWordDict = {}
        
        self.trainReviews = []
        self.trainLabels = []
        
        self.evalReviews = []
        self.evalLabels = []
        
        self.wordEmbedding =None
        
        self.labelList = []
        
    def _readData(self, filePath):
        """
        從csv文件中讀取數據集
        """
        
        df = pd.read_csv(filePath)
        
        if self.config.numClasses == 1:
            labels = df["sentiment"].tolist()
        elif self.config.numClasses > 1:
            labels = df["rate"].tolist()
            
        review = df["review"].tolist()
        reviews = [line.strip().split() for line in review]

        return reviews, labels
    
    def _labelToIndex(self, labels, label2idx):
        """
        將標簽轉換成索引表示
        """
        labelIds = [label2idx[label] for label in labels]
        return labelIds
    
    def _wordToIndex(self, reviews, word2idx):
        """
        將詞轉換成索引
        """
        reviewIds = [[word2idx.get(item, word2idx["UNK"]) for item in review] for review in reviews]
        return reviewIds
        
    def _genTrainEvalData(self, x, y, word2idx, rate):
        """
        生成訓練集和驗證集
        """
        reviews = []
        for review in x:
            if len(review) >= self._sequenceLength:
                reviews.append(review[:self._sequenceLength])
            else:
                reviews.append(review + [word2idx["PAD"]] * (self._sequenceLength - len(review)))
            
        trainIndex = int(len(x) * rate)
        
        trainReviews = np.asarray(reviews[:trainIndex], dtype="int64")
        trainLabels = np.array(y[:trainIndex], dtype="float32")
        
        evalReviews = np.asarray(reviews[trainIndex:], dtype="int64")
        evalLabels = np.array(y[trainIndex:], dtype="float32")

        return trainReviews, trainLabels, evalReviews, evalLabels
        
    def _genVocabulary(self, reviews, labels):
        """
        生成詞向量和詞匯-索引映射字典，可以用全數據集
        """
        
        allWords = [word for review in reviews for word in review]
        
        # 去掉停用詞
        subWords = [word for word in allWords if word not in self.stopWordDict]
        
        wordCount = Counter(subWords)  # 統計詞頻
        sortWordCount = sorted(wordCount.items(), key=lambda x: x[1], reverse=True)
        
        # 去除低頻詞
        words = [item[0] for item in sortWordCount if item[1] >= 5]
        
        vocab, wordEmbedding = self._getWordEmbedding(words)
        self.wordEmbedding = wordEmbedding
        
        word2idx = dict(zip(vocab, list(range(len(vocab)))))
        
        uniqueLabel = list(set(labels))
        label2idx = dict(zip(uniqueLabel, list(range(len(uniqueLabel)))))
        self.labelList = list(range(len(uniqueLabel)))
        
        # 將詞匯-索引映射表保存為json數據，之后做inference時直接加載來處理數據
        with open("../data/wordJson/word2idx.json", "w", encoding="utf-8") as f:
            json.dump(word2idx, f)
        
        with open("../data/wordJson/label2idx.json", "w", encoding="utf-8") as f:
            json.dump(label2idx, f)
        
        return word2idx, label2idx
            
    def _getWordEmbedding(self, words):
        """
        按照我們的數據集中的單詞取出預訓練好的word2vec中的詞向量
        """
        
        wordVec = gensim.models.KeyedVectors.load_word2vec_format("../word2vec/word2Vec.bin", binary=True)
        vocab = []
        wordEmbedding = []
        
        # 添加 "pad" 和 "UNK", 
        vocab.append("PAD")
        vocab.append("UNK")
        wordEmbedding.append(np.zeros(self._embeddingSize))
        wordEmbedding.append(np.random.randn(self._embeddingSize))
        
        for word in words:
            try:
                vector = wordVec.wv[word]
                vocab.append(word)
                wordEmbedding.append(vector)
            except:
                print(word + "不存在於詞向量中")
                
        return vocab, np.array(wordEmbedding)
    
    def _readStopWord(self, stopWordPath):
        """
        讀取停用詞
        """
        
        with open(stopWordPath, "r") as f:
            stopWords = f.read()
            stopWordList = stopWords.splitlines()
            # 將停用詞用列表的形式生成，之后查找停用詞時會比較快
            self.stopWordDict = dict(zip(stopWordList, list(range(len(stopWordList)))))
            
    def dataGen(self):
        """
        初始化訓練集和驗證集
        """
        
        # 初始化停用詞
        self._readStopWord(self._stopWordSource)
        
        # 初始化數據集
        reviews, labels = self._readData(self._dataSource)
        
        # 初始化詞匯-索引映射表和詞向量矩陣
        word2idx, label2idx = self._genVocabulary(reviews, labels)
        
        # 將標簽和句子數值化
        labelIds = self._labelToIndex(labels, label2idx)
        reviewIds = self._wordToIndex(reviews, word2idx)
        
        # 初始化訓練集和測試集
        trainReviews, trainLabels, evalReviews, evalLabels = self._genTrainEvalData(reviewIds, labelIds, word2idx, self._rate)
        self.trainReviews = trainReviews
        self.trainLabels = trainLabels
        
        self.evalReviews = evalReviews
        self.evalLabels = evalLabels
        
        
data = Dataset(config)
data.dataGen()

 

6 生成batch數據集

　　采用生成器的形式向模型輸入batch數據集，（生成器可以避免將所有的數據加入到內存中）

# 輸出batch數據集

def nextBatch(x, y, batchSize):
        """
        生成batch數據集，用生成器的方式輸出
        """
    
        perm = np.arange(len(x))
        np.random.shuffle(perm)
        x = x[perm]
        y = y[perm]
        
        numBatches = len(x) // batchSize

        for i in range(numBatches):
            start = i * batchSize
            end = start + batchSize
            batchX = np.array(x[start: end], dtype="int64")
            batchY = np.array(y[start: end], dtype="float32")
            
            yield batchX, batchY

 

7 RCNN 模型

 

"""
構建模型，模型的架構如下：
1，利用Bi-LSTM獲得上下文的信息
2，將Bi-LSTM獲得的隱層輸出和詞向量拼接[fwOutput;wordEmbedding;bwOutput]
3，將2所得的詞表示映射到低維
4，hidden_size上每個位置的值都取時間步上最大的值，類似於max-pool
5，softmax分類
"""

class RCNN(object):
    """
    RCNN 用於文本分類
    """
    def __init__(self, config, wordEmbedding):

        # 定義模型的輸入
        self.inputX = tf.placeholder(tf.int32, [None, config.sequenceLength], name="inputX")
        self.inputY = tf.placeholder(tf.int32, [None], name="inputY")
        
        self.dropoutKeepProb = tf.placeholder(tf.float32, name="dropoutKeepProb")
        
        # 定義l2損失
        l2Loss = tf.constant(0.0)
        
        # 詞嵌入層
        with tf.name_scope("embedding"):

            # 利用預訓練的詞向量初始化詞嵌入矩陣
            self.W = tf.Variable(tf.cast(wordEmbedding, dtype=tf.float32, name="word2vec") ,name="W")
            # 利用詞嵌入矩陣將輸入的數據中的詞轉換成詞向量，維度[batch_size, sequence_length, embedding_size]
            self.embeddedWords = tf.nn.embedding_lookup(self.W, self.inputX)
            # 復制一份embedding input
            self.embeddedWords_ = self.embeddedWords
            
        # 定義兩層雙向LSTM的模型結構

#         with tf.name_scope("Bi-LSTM"):
#             fwHiddenLayers = []
#             bwHiddenLayers = []
#             for idx, hiddenSize in enumerate(config.model.hiddenSizes):

#                 with tf.name_scope("Bi-LSTM-" + str(idx)):
#                     # 定義前向LSTM結構
#                     lstmFwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
#                                                                  output_keep_prob=self.dropoutKeepProb)
#                     # 定義反向LSTM結構
#                     lstmBwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
#                                                                  output_keep_prob=self.dropoutKeepProb)

#                 fwHiddenLayers.append(lstmFwCell)
#                 bwHiddenLayers.append(lstmBwCell)

#             # 實現多層的LSTM結構， state_is_tuple=True，則狀態會以元祖的形式組合(h, c)，否則列向拼接
#             fwMultiLstm = tf.nn.rnn_cell.MultiRNNCell(cells=fwHiddenLayers, state_is_tuple=True)
#             bwMultiLstm = tf.nn.rnn_cell.MultiRNNCell(cells=bwHiddenLayers, state_is_tuple=True)

#             # 采用動態rnn，可以動態的輸入序列的長度，若沒有輸入，則取序列的全長
#             # outputs是一個元祖(output_fw, output_bw)，其中兩個元素的維度都是[batch_size, max_time, hidden_size],fw和bw的hidden_size一樣
#             # self.current_state 是最終的狀態，二元組(state_fw, state_bw)，state_fw=[batch_size, s]，s是一個元祖(h, c)
#             outputs, self.current_state = tf.nn.bidirectional_dynamic_rnn(fwMultiLstm, bwMultiLstm, self.embeddedWords, dtype=tf.float32)
#             fwOutput, bwOutput = outputs

        with tf.name_scope("Bi-LSTM"):
            for idx, hiddenSize in enumerate(config.model.hiddenSizes):
                with tf.name_scope("Bi-LSTM" + str(idx)):
                    # 定義前向LSTM結構
                    lstmFwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
                                                                 output_keep_prob=self.dropoutKeepProb)
                    # 定義反向LSTM結構
                    lstmBwCell = tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.LSTMCell(num_units=hiddenSize, state_is_tuple=True),
                                                                 output_keep_prob=self.dropoutKeepProb)


                    # 采用動態rnn，可以動態的輸入序列的長度，若沒有輸入，則取序列的全長
                    # outputs是一個元祖(output_fw, output_bw)，其中兩個元素的維度都是[batch_size, max_time, hidden_size],fw和bw的hidden_size一樣
                    # self.current_state 是最終的狀態，二元組(state_fw, state_bw)，state_fw=[batch_size, s]，s是一個元祖(h, c)
                    outputs_, self.current_state = tf.nn.bidirectional_dynamic_rnn(lstmFwCell, lstmBwCell, 
                                                                                  self.embeddedWords_, dtype=tf.float32,
                                                                                  scope="bi-lstm" + str(idx))
        
                    # 對outputs中的fw和bw的結果拼接 [batch_size, time_step, hidden_size * 2], 傳入到下一層Bi-LSTM中
                    self.embeddedWords_ = tf.concat(outputs_, 2)
                
        # 將最后一層Bi-LSTM輸出的結果分割成前向和后向的輸出
        fwOutput, bwOutput = tf.split(self.embeddedWords_, 2, -1)
            
        with tf.name_scope("context"):
            shape = [tf.shape(fwOutput)[0], 1, tf.shape(fwOutput)[2]]
            self.contextLeft = tf.concat([tf.zeros(shape), fwOutput[:, :-1]], axis=1, name="contextLeft")
            self.contextRight = tf.concat([bwOutput[:, 1:], tf.zeros(shape)], axis=1, name="contextRight")
            
        # 將前向，后向的輸出和最早的詞向量拼接在一起得到最終的詞表征
        with tf.name_scope("wordRepresentation"):
            self.wordRepre = tf.concat([self.contextLeft, self.embeddedWords, self.contextRight], axis=2)
            wordSize = config.model.hiddenSizes[-1] * 2 + config.model.embeddingSize 
        
        with tf.name_scope("textRepresentation"):
            outputSize = config.model.outputSize
            textW = tf.Variable(tf.random_uniform([wordSize, outputSize], -1.0, 1.0), name="W2")
            textB = tf.Variable(tf.constant(0.1, shape=[outputSize]), name="b2")
            
            # tf.einsum可以指定維度的消除運算
            self.textRepre = tf.tanh(tf.einsum('aij,jk->aik', self.wordRepre, textW) + textB)
            
        # 做max-pool的操作，將時間步的維度消失
        output = tf.reduce_max(self.textRepre, axis=1)
        
        # 全連接層的輸出
        with tf.name_scope("output"):
            outputW = tf.get_variable(
                "outputW",
                shape=[outputSize, config.numClasses],
                initializer=tf.contrib.layers.xavier_initializer())
            
            outputB= tf.Variable(tf.constant(0.1, shape=[config.numClasses]), name="outputB")
            l2Loss += tf.nn.l2_loss(outputW)
            l2Loss += tf.nn.l2_loss(outputB)
            self.logits = tf.nn.xw_plus_b(output, outputW, outputB, name="logits")
            
            if config.numClasses == 1:
                self.predictions = tf.cast(tf.greater_equal(self.logits, 0.0), tf.float32, name="predictions")
            elif config.numClasses > 1:
                self.predictions = tf.argmax(self.logits, axis=-1, name="predictions")
        
        # 計算二元交叉熵損失
        with tf.name_scope("loss"):
            
            if config.numClasses == 1:
                losses = tf.nn.sigmoid_cross_entropy_with_logits(logits=self.logits, labels=tf.cast(tf.reshape(self.inputY, [-1, 1]), 
                                                                                                    dtype=tf.float32))
            elif config.numClasses > 1:
                losses = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=self.logits, labels=self.inputY)
                
            self.loss = tf.reduce_mean(losses) + config.model.l2RegLambda * l2Loss

 

8 定義計算metrics的函數

 

"""
定義各類性能指標
"""

def mean(item: list) -> float:
    """
    計算列表中元素的平均值
    :param item: 列表對象
    :return:
    """
    res = sum(item) / len(item) if len(item) > 0 else 0
    return res


def accuracy(pred_y, true_y):
    """
    計算二類和多類的准確率
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :return:
    """
    if isinstance(pred_y[0], list):
        pred_y = [item[0] for item in pred_y]
    corr = 0
    for i in range(len(pred_y)):
        if pred_y[i] == true_y[i]:
            corr += 1
    acc = corr / len(pred_y) if len(pred_y) > 0 else 0
    return acc


def binary_precision(pred_y, true_y, positive=1):
    """
    二類的精確率計算
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param positive: 正例的索引表示
    :return:
    """
    corr = 0
    pred_corr = 0
    for i in range(len(pred_y)):
        if pred_y[i] == positive:
            pred_corr += 1
            if pred_y[i] == true_y[i]:
                corr += 1

    prec = corr / pred_corr if pred_corr > 0 else 0
    return prec


def binary_recall(pred_y, true_y, positive=1):
    """
    二類的召回率
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param positive: 正例的索引表示
    :return:
    """
    corr = 0
    true_corr = 0
    for i in range(len(pred_y)):
        if true_y[i] == positive:
            true_corr += 1
            if pred_y[i] == true_y[i]:
                corr += 1

    rec = corr / true_corr if true_corr > 0 else 0
    return rec


def binary_f_beta(pred_y, true_y, beta=1.0, positive=1):
    """
    二類的f beta值
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param beta: beta值
    :param positive: 正例的索引表示
    :return:
    """
    precision = binary_precision(pred_y, true_y, positive)
    recall = binary_recall(pred_y, true_y, positive)
    try:
        f_b = (1 + beta * beta) * precision * recall / (beta * beta * precision + recall)
    except:
        f_b = 0
    return f_b


def multi_precision(pred_y, true_y, labels):
    """
    多類的精確率
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param labels: 標簽列表
    :return:
    """
    if isinstance(pred_y[0], list):
        pred_y = [item[0] for item in pred_y]

    precisions = [binary_precision(pred_y, true_y, label) for label in labels]
    prec = mean(precisions)
    return prec


def multi_recall(pred_y, true_y, labels):
    """
    多類的召回率
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param labels: 標簽列表
    :return:
    """
    if isinstance(pred_y[0], list):
        pred_y = [item[0] for item in pred_y]

    recalls = [binary_recall(pred_y, true_y, label) for label in labels]
    rec = mean(recalls)
    return rec


def multi_f_beta(pred_y, true_y, labels, beta=1.0):
    """
    多類的f beta值
    :param pred_y: 預測結果
    :param true_y: 真實結果
    :param labels: 標簽列表
    :param beta: beta值
    :return:
    """
    if isinstance(pred_y[0], list):
        pred_y = [item[0] for item in pred_y]

    f_betas = [binary_f_beta(pred_y, true_y, beta, label) for label in labels]
    f_beta = mean(f_betas)
    return f_beta


def get_binary_metrics(pred_y, true_y, f_beta=1.0):
    """
    得到二分類的性能指標
    :param pred_y:
    :param true_y:
    :param f_beta:
    :return:
    """
    acc = accuracy(pred_y, true_y)
    recall = binary_recall(pred_y, true_y)
    precision = binary_precision(pred_y, true_y)
    f_beta = binary_f_beta(pred_y, true_y, f_beta)
    return acc, recall, precision, f_beta


def get_multi_metrics(pred_y, true_y, labels, f_beta=1.0):
    """
    得到多分類的性能指標
    :param pred_y:
    :param true_y:
    :param labels:
    :param f_beta:
    :return:
    """
    acc = accuracy(pred_y, true_y)
    recall = multi_recall(pred_y, true_y, labels)
    precision = multi_precision(pred_y, true_y, labels)
    f_beta = multi_f_beta(pred_y, true_y, labels, f_beta)
    return acc, recall, precision, f_beta

 

 

9 訓練模型

　　在訓練時，我們定義了tensorBoard的輸出，並定義了兩種模型保存的方法。　

# 訓練模型

# 生成訓練集和驗證集
trainReviews = data.trainReviews
trainLabels = data.trainLabels
evalReviews = data.evalReviews
evalLabels = data.evalLabels

wordEmbedding = data.wordEmbedding
labelList = data.labelList

# 定義計算圖
with tf.Graph().as_default():

    session_conf = tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)
    session_conf.gpu_options.allow_growth=True
    session_conf.gpu_options.per_process_gpu_memory_fraction = 0.9  # 配置gpu占用率  

    sess = tf.Session(config=session_conf)
    
    # 定義會話
    with sess.as_default():
        lstm = RCNN(config, wordEmbedding)
        
        globalStep = tf.Variable(0, name="globalStep", trainable=False)
        # 定義優化函數，傳入學習速率參數
        optimizer = tf.train.AdamOptimizer(config.training.learningRate)
        # 計算梯度,得到梯度和變量
        gradsAndVars = optimizer.compute_gradients(lstm.loss)
        # 將梯度應用到變量下，生成訓練器
        trainOp = optimizer.apply_gradients(gradsAndVars, global_step=globalStep)
        
        # 用summary繪制tensorBoard
        gradSummaries = []
        for g, v in gradsAndVars:
            if g is not None:
                tf.summary.histogram("{}/grad/hist".format(v.name), g)
                tf.summary.scalar("{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g))
        
        outDir = os.path.abspath(os.path.join(os.path.curdir, "summarys"))
        print("Writing to {}\n".format(outDir))
        
        lossSummary = tf.summary.scalar("loss", lstm.loss)
        summaryOp = tf.summary.merge_all()
        
        trainSummaryDir = os.path.join(outDir, "train")
        trainSummaryWriter = tf.summary.FileWriter(trainSummaryDir, sess.graph)
        
        evalSummaryDir = os.path.join(outDir, "eval")
        evalSummaryWriter = tf.summary.FileWriter(evalSummaryDir, sess.graph)
        
        
        # 初始化所有變量
        saver = tf.train.Saver(tf.global_variables(), max_to_keep=5)
        
       # 保存模型的一種方式，保存為pb文件
        savedModelPath = "../model/RCNN/savedModel"
        if os.path.exists(savedModelPath):
            os.rmdir(savedModelPath)
        builder = tf.saved_model.builder.SavedModelBuilder(savedModelPath)
            
        sess.run(tf.global_variables_initializer())

        def trainStep(batchX, batchY):
            """
            訓練函數
            """   
            feed_dict = {
              lstm.inputX: batchX,
              lstm.inputY: batchY,
              lstm.dropoutKeepProb: config.model.dropoutKeepProb
            }
            _, summary, step, loss, predictions = sess.run(
                [trainOp, summaryOp, globalStep, lstm.loss, lstm.predictions],
                feed_dict)
            
            if config.numClasses == 1:
                acc, recall, prec, f_beta = get_binary_metrics(pred_y=predictions, true_y=batchY)

                
            elif config.numClasses > 1:
                acc, recall, prec, f_beta = get_multi_metrics(pred_y=predictions, true_y=batchY,
                                                              labels=labelList)
                
            trainSummaryWriter.add_summary(summary, step)
            
            return loss, acc, prec, recall, f_beta

        def devStep(batchX, batchY):
            """
            驗證函數
            """
            feed_dict = {
              lstm.inputX: batchX,
              lstm.inputY: batchY,
              lstm.dropoutKeepProb: 1.0
            }
            summary, step, loss, predictions = sess.run(
                [summaryOp, globalStep, lstm.loss, lstm.predictions],
                feed_dict)
            
            if config.numClasses == 1:
            
                acc, precision, recall, f_beta = get_binary_metrics(pred_y=predictions, true_y=batchY)
            elif config.numClasses > 1:
                acc, precision, recall, f_beta = get_multi_metrics(pred_y=predictions, true_y=batchY, labels=labelList)
            
            evalSummaryWriter.add_summary(summary, step)
            
            return loss, acc, precision, recall, f_beta
        
        for i in range(config.training.epoches):
            # 訓練模型
            print("start training model")
            for batchTrain in nextBatch(trainReviews, trainLabels, config.batchSize):
                loss, acc, prec, recall, f_beta = trainStep(batchTrain[0], batchTrain[1])
                
                currentStep = tf.train.global_step(sess, globalStep) 
                print("train: step: {}, loss: {}, acc: {}, recall: {}, precision: {}, f_beta: {}".format(
                    currentStep, loss, acc, recall, prec, f_beta))
                if currentStep % config.training.evaluateEvery == 0:
                    print("\nEvaluation:")
                    
                    losses = []
                    accs = []
                    f_betas = []
                    precisions = []
                    recalls = []
                    
                    for batchEval in nextBatch(evalReviews, evalLabels, config.batchSize):
                        loss, acc, precision, recall, f_beta = devStep(batchEval[0], batchEval[1])
                        losses.append(loss)
                        accs.append(acc)
                        f_betas.append(f_beta)
                        precisions.append(precision)
                        recalls.append(recall)
                        
                    time_str = datetime.datetime.now().isoformat()
                    print("{}, step: {}, loss: {}, acc: {},precision: {}, recall: {}, f_beta: {}".format(time_str, currentStep, mean(losses), 
                                                                                                       mean(accs), mean(precisions),
                                                                                                       mean(recalls), mean(f_betas)))
                    
                if currentStep % config.training.checkpointEvery == 0:
                    # 保存模型的另一種方法，保存checkpoint文件
                    path = saver.save(sess, "../model/RCNN/model/my-model", global_step=currentStep)
                    print("Saved model checkpoint to {}\n".format(path))
                    
        inputs = {"inputX": tf.saved_model.utils.build_tensor_info(lstm.inputX),
                  "keepProb": tf.saved_model.utils.build_tensor_info(lstm.dropoutKeepProb)}

        outputs = {"predictions": tf.saved_model.utils.build_tensor_info(lstm.binaryPreds)}

        prediction_signature = tf.saved_model.signature_def_utils.build_signature_def(inputs=inputs, outputs=outputs,
                                                                                      method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME)
        legacy_init_op = tf.group(tf.tables_initializer(), name="legacy_init_op")
        builder.add_meta_graph_and_variables(sess, [tf.saved_model.tag_constants.SERVING],
                                            signature_def_map={"predict": prediction_signature}, legacy_init_op=legacy_init_op)

        builder.save()

 

10 預測代碼

x = "this movie is full of references like mad max ii the wild one and many others the ladybug´s face it´s a clear reference or tribute to peter lorre this movie is a masterpiece we´ll talk much more about in the future"

# 注：下面兩個詞典要保證和當前加載的模型對應的詞典是一致的
with open("../data/wordJson/word2idx.json", "r", encoding="utf-8") as f:
    word2idx = json.load(f)
        
with open("../data/wordJson/label2idx.json", "r", encoding="utf-8") as f:
    label2idx = json.load(f)
idx2label = {value: key for key, value in label2idx.items()}
    
xIds = [word2idx.get(item, word2idx["UNK"]) for item in x.split(" ")]
if len(xIds) >= config.sequenceLength:
    xIds = xIds[:config.sequenceLength]
else:
    xIds = xIds + [word2idx["PAD"]] * (config.sequenceLength - len(xIds))

graph = tf.Graph()
with graph.as_default():
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.333)
    session_conf = tf.ConfigProto(allow_soft_placement=True, log_device_placement=False, gpu_options=gpu_options)
    sess = tf.Session(config=session_conf)

    with sess.as_default():
        checkpoint_file = tf.train.latest_checkpoint("../model/RCNN/model/")
        saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
        saver.restore(sess, checkpoint_file)

        # 獲得需要喂給模型的參數，輸出的結果依賴的輸入值
        inputX = graph.get_operation_by_name("inputX").outputs[0]
        dropoutKeepProb = graph.get_operation_by_name("dropoutKeepProb").outputs[0]

        # 獲得輸出的結果
        predictions = graph.get_tensor_by_name("output/predictions:0")

        pred = sess.run(predictions, feed_dict={inputX: [xIds], dropoutKeepProb: 1.0})[0]
        
pred = [idx2label[item] for item in pred]     
print(pred)