Merge pull request #205 from zide05/dev0.5.0

Dev0.5.0

docs/source/tutorials/tutorial_4_loss_optimizer.rst

@@ -158,6 +158,7 @@ Vocabulary 的使用
 损失函数
     训练模型需要提供一个损失函数
     ,fastNLP中提供了直接可以导入使用的四种loss，分别为：
+    
     * :class:`~fastNLP.CrossEntropyLoss`：包装了torch.nn.functional.cross_entropy()函数，返回交叉熵损失（可以运用于多分类场景）  
     * :class:`~fastNLP.BCELoss`：包装了torch.nn.functional.binary_cross_entropy()函数，返回二分类的交叉熵  
     * :class:`~fastNLP.L1Loss`：包装了torch.nn.functional.l1_loss()函数，返回L1 损失  
@@ -209,7 +210,7 @@ Vocabulary 的使用
 
         #使用CNNText的时候第一个参数输入一个tuple,作为模型定义embedding的参数
         #还可以传入 kernel_nums, kernel_sizes, padding, dropout的自定义值
-        model_cnn = CNNText((len(vocab),EMBED_DIM), num_classes=3, padding=2, dropout=0.1)
+        model_cnn = CNNText((len(vocab),EMBED_DIM), num_classes=3, dropout=0.1)
 
         #如果在定义trainer的时候没有传入optimizer参数，模型默认的优化器为torch.optim.Adam且learning rate为lr=4e-3
         #这里只使用了optimizer_1作为优化器输入，感兴趣可以尝试optimizer_2或者其他优化器作为输入

docs/source/tutorials/tutorial_5_datasetiter.rst

@@ -192,7 +192,7 @@ sampler
         import time
 
         embed_dim = 100
-        model = CNNText((len(vocab),embed_dim), num_classes=3, padding=2, dropout=0.1)
+        model = CNNText((len(vocab),embed_dim), num_classes=3, dropout=0.1)
 
         def train(epoch, data, devdata):
             optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

fastNLP/embeddings/bert_embedding.py

@@ -27,6 +27,7 @@ class BertEmbedding(ContextualEmbedding):
 
         >>> import torch
         >>> from fastNLP import Vocabulary
+        >>> from fastNLP.embeddings import BertEmbedding
         >>> vocab = Vocabulary().add_word_lst("The whether is good .".split())
         >>> embed = BertEmbedding(vocab, model_dir_or_name='en-base-uncased', requires_grad=False, layers='4,-2,-1')
         >>> words = torch.LongTensor([[vocab.to_index(word) for word in "The whether is good .".split()]])

fastNLP/embeddings/char_embedding.py

@@ -24,6 +24,9 @@ class CNNCharEmbedding(TokenEmbedding):
 
     Example::
 
+        >>> import torch
+        >>> from fastNLP import Vocabulary
+        >>> from fastNLP.embeddings import CNNCharEmbedding
         >>> vocab = Vocabulary().add_word_lst("The whether is good .".split())
         >>> embed = CNNCharEmbedding(vocab, embed_size=50)
         >>> words = torch.LongTensor([[vocab.to_index(word) for word in "The whether is good .".split()]])
@@ -167,6 +170,9 @@ class LSTMCharEmbedding(TokenEmbedding):
 
     Example::
 
+        >>> import torch
+        >>> from fastNLP import Vocabulary
+        >>> from fastNLP.embeddings import LSTMCharEmbedding
         >>> vocab = Vocabulary().add_word_lst("The whether is good .".split())
         >>> embed = LSTMCharEmbedding(vocab, embed_size=50)
         >>> words = torch.LongTensor([[vocab.to_index(word) for word in "The whether is good .".split()]])

fastNLP/embeddings/elmo_embedding.py

@@ -21,6 +21,9 @@ class ElmoEmbedding(ContextualEmbedding):
 
     Example::
     
+        >>> import torch
+        >>> from fastNLP import Vocabulary
+        >>> from fastNLP.embeddings import ElmoEmbedding
         >>> vocab = Vocabulary().add_word_lst("The whether is good .".split())
         >>> # 使用不同层的concat的结果
         >>> embed = ElmoEmbedding(vocab, model_dir_or_name='en', layers='1,2', requires_grad=False)

fastNLP/embeddings/embedding.py

@@ -20,6 +20,7 @@ class Embedding(nn.Module):
     Example::
 
         >>> import numpy as np
+        >>> from fastNLP.embeddings import Embedding
         >>> init_embed = (2000, 100)
         >>> embed = Embedding(init_embed)  # 随机初始化一个具有2000个词，每个词表示为100维的词向量
         >>> init_embed = np.zeros((2000, 100))

fastNLP/embeddings/stack_embedding.py

@@ -17,7 +17,7 @@ class StackEmbedding(TokenEmbedding):
         >>> from fastNLP import Vocabulary
         >>> from fastNLP.embeddings import StaticEmbedding
         >>> vocab =  Vocabulary().add_word_lst("The whether is good .".split())
-        >>> embed_1 = StaticEmbedding(vocab, model_dir_or_name='en-glove-6b-50', requires_grad=True)
+        >>> embed_1 = StaticEmbedding(vocab, model_dir_or_name='en-glove-6b-50d', requires_grad=True)
         >>> embed_2 = StaticEmbedding(vocab, model_dir_or_name='en-word2vec-300', requires_grad=True)
 
     :param embeds: 一个由若干个TokenEmbedding组成的list，要求每一个TokenEmbedding的词表都保持一致
@@ -91,4 +91,4 @@ class StackEmbedding(TokenEmbedding):
         for embed in self.embeds:
             outputs.append(embed(words))
         outputs = self.dropout(torch.cat(outputs, dim=-1))
-        return outputs
+        return outputs

fastNLP/embeddings/static_embedding.py

@@ -22,12 +22,14 @@ class StaticEmbedding(TokenEmbedding):
     当前支持自动下载的预训练vector有以下的几种(待补充);
 
     Example::
-
+        
+        >>> from fastNLP import Vocabulary
+        >>> from fastNLP.embeddings import StaticEmbedding
         >>> vocab = Vocabulary().add_word_lst("The whether is good .".split())
-        >>> embed = StaticEmbedding(vocab, model_dir_or_name='en-glove-50')
+        >>> embed = StaticEmbedding(vocab, model_dir_or_name='en-glove-50d')
 
         >>> vocab = Vocabulary().add_word_lst(["The", 'the', "THE"])
-        >>> embed = StaticEmbedding(vocab, model_dir_or_name="en-glove-50", lower=True)
+        >>> embed = StaticEmbedding(vocab, model_dir_or_name="en-glove-50d", lower=True)
         >>> # "the", "The", "THE"它们共用一个vector，且将使用"the"在预训练词表中寻找它们的初始化表示。
 
         >>> vocab = Vocabulary().add_word_lst(["The", "the", "THE"])