标签：ack active int 建立 字符 obj pytho key span
Pytorch是一个较新的深度学习框架，是一个 Python 优先的深度学习框架，能够在强大的 GPU 加速基础上实现张量和动态神经网络。
卷积神经网络CNN理解参考（https://www.zybuluo.com/hanbingtao/note/485480）
长短时记忆网络LSTM理解参考（https://zybuluo.com/hanbingtao/note/581764）
1、我现在使用的语料是基本规范的数据（例如下），但是加载语料数据的过程中仍然存在着一些需要预处理的地方，像一些数据的大小写、数字的处理以及“\n \t”等一些字符，现在使用torchtext第三方库进行加载数据预处理。
You Should Pay Nine Bucks for This : Because you can hear about suffering Afghan refugees on the news and still be unaffected . ||| 2 Dramas like this make it human . ||| 4
2、torch建立词表、处理语料数据的大小写：
import torchtext.data as data # lower word text_field = data.Field(lower=True)
3、处理语料数据数字等特殊字符：
1 from torchtext import data 2 def clean_str(string): 3 string = re.sub(r"[^A-Za-z0-9(),!?\‘\`]", " ", string) 4 string = re.sub(r"\‘s", " \‘s", string) 5 string = re.sub(r"\‘ve", " \‘ve", string) 6 string = re.sub(r"n\‘t", " n\‘t", string) 7 string = re.sub(r"\‘re", " \‘re", string) 8 string = re.sub(r"\‘d", " \‘d", string) 9 string = re.sub(r"\‘ll", " \‘ll", string) 10 string = re.sub(r",", " , ", string) 11 string = re.sub(r"!", " ! ", string) 12 string = re.sub(r"\(", " \( ", string) 13 string = re.sub(r"\)", " \) ", string) 14 string = re.sub(r"\?", " \? ", string) 15 string = re.sub(r"\s{2,}", " ", string) 16 return string.strip() 17 18 text_field.preprocessing = data.Pipeline(clean_str)
4、需要注意的地方：
1 if shuffle: 2 random.shuffle(examples_train) 3 random.shuffle(examples_dev) 4 random.shuffle(examples_test)
1 class Iterator(object): 2 """Defines an iterator that loads batches of data from a Dataset. 3 4 Attributes: 5 dataset: The Dataset object to load Examples from. 6 batch_size: Batch size. 7 sort_key: A key to use for sorting examples in order to batch together 8 examples with similar lengths and minimize padding. The sort_key 9 provided to the Iterator constructor overrides the sort_key 10 attribute of the Dataset, or defers to it if None. 11 train: Whether the iterator represents a train set. 12 repeat: Whether to repeat the iterator for multiple epochs. 13 shuffle: Whether to shuffle examples between epochs. 14 sort: Whether to sort examples according to self.sort_key. 15 Note that repeat, shuffle, and sort default to train, train, and 16 (not train). 17 device: Device to create batches on. Use -1 for CPU and None for the 18 currently active GPU device. 19 """
1、word embedding简单来说就是语料中每一个单词对应的其相应的词向量，目前训练词向量的方式最使用的应该是word2vec（参考 http://www.cnblogs.com/bamtercelboo/p/7181899.html）
2、上文中已经通过torchtext建立了相关的词汇表，加载词向量有两种方式，一个是加载外部根据语料训练好的预训练词向量，另一个方式是随机初始化词向量，两种方式相互比较的话当时是使用预训练好的词向量效果会好很多，但是自己训练的词向量并不见得会有很好的效果，因为语料数据可能不足，像已经训练好的词向量，像Google News那个词向量，是业界公认的词向量，但是由于数量巨大，如果硬件设施（GPU）不行的话，还是不要去尝试这个了。
3、提供几个下载预训练词向量的地址
word2vec-GoogleNews-vectors(https://github.com/mmihaltz/word2vec-GoogleNews-vectors)
1 # load word embedding 2 def load_my_vecs(path, vocab, freqs): 3 word_vecs = {} 4 with open(path, encoding="utf-8") as f: 5 count = 0 6 lines = f.readlines()[1:] 7 for line in lines: 8 values = line.split(" ") 9 word = values[0] 10 # word = word.lower() 11 count += 1 12 if word in vocab: # whether to judge if in vocab 13 vector = [] 14 for count, val in enumerate(values): 15 if count == 0: 16 continue 17 vector.append(float(val)) 18 word_vecs[word] = vector 19 return word_vecs
1 # solve unknown by avg word embedding 2 def add_unknown_words_by_avg(word_vecs, vocab, k=100): 3 # solve unknown words inplaced by zero list 4 word_vecs_numpy = [] 5 for word in vocab: 6 if word in word_vecs: 7 word_vecs_numpy.append(word_vecs[word]) 8 print(len(word_vecs_numpy)) 9 col = [] 10 for i in range(k): 11 sum = 0.0 12 # for j in range(int(len(word_vecs_numpy) / 4)): 13 for j in range(int(len(word_vecs_numpy))): 14 sum += word_vecs_numpy[j][i] 15 sum = round(sum, 6) 16 col.append(sum) 17 zero = [] 18 for m in range(k): 19 # avg = col[m] / (len(col) * 5) 20 avg = col[m] / (len(word_vecs_numpy)) 21 avg = round(avg, 6) 22 zero.append(float(avg)) 23 24 list_word2vec = [] 25 oov = 0 26 iov = 0 27 for word in vocab: 28 if word not in word_vecs: 29 # word_vecs[word] = np.random.uniform(-0.25, 0.25, k).tolist() 30 # word_vecs[word] = [0.0] * k 31 oov += 1 32 word_vecs[word] = zero 33 list_word2vec.append(word_vecs[word]) 34 else: 35 iov += 1 36 list_word2vec.append(word_vecs[word]) 37 print("oov count", oov) 38 print("iov count", iov) 39 return list_word2vec
1 # solve unknown word by uniform(-0.25,0.25) 2 def add_unknown_words_by_uniform(word_vecs, vocab, k=100): 3 list_word2vec = [] 4 oov = 0 5 iov = 0 6 # uniform = np.random.uniform(-0.25, 0.25, k).round(6).tolist() 7 for word in vocab: 8 if word not in word_vecs: 9 oov += 1 10 word_vecs[word] = np.random.uniform(-0.25, 0.25, k).round(6).tolist() 11 # word_vecs[word] = np.random.uniform(-0.1, 0.1, k).round(6).tolist() 12 # word_vecs[word] = uniform 13 list_word2vec.append(word_vecs[word]) 14 else: 15 iov += 1 16 list_word2vec.append(word_vecs[word]) 17 print("oov count", oov) 18 print("iov count", iov) 19 return list_word2vec
1 if shuffle: 2 random.shuffle(examples_train) 3 random.shuffle(examples_dev) 4 random.shuffle(examples，
标签：ack active int 建立 字符 obj pytho key span
原文地址：http://www.cnblogs.com/bamtercelboo/p/7469005.html
