models的文档结构和别名

docs/source/fastNLP.models.base_model.rst

@@ -1,7 +0,0 @@
-fastNLP.models.base\_model
-==========================
-
-.. automodule:: fastNLP.models.base_model
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.bert.rst

@@ -1,7 +0,0 @@
-fastNLP.models.bert
-===================
-
-.. automodule:: fastNLP.models.bert
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.enas_controller.rst

@@ -1,7 +0,0 @@
-fastNLP.models.enas\_controller module
-======================================
-
-.. automodule:: fastNLP.models.enas_controller
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.enas_model.rst

@@ -1,7 +0,0 @@
-fastNLP.models.enas\_model
-==========================
-
-.. automodule:: fastNLP.models.enas_model
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.enas_trainer.rst

@@ -1,7 +0,0 @@
-fastNLP.models.enas\_trainer
-============================
-
-.. automodule:: fastNLP.models.enas_trainer
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.enas_utils.rst

@@ -1,7 +0,0 @@
-fastNLP.models.enas\_utils
-==========================
-
-.. automodule:: fastNLP.models.enas_utils
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs/source/fastNLP.models.rst

@@ -11,14 +11,8 @@ fastNLP.models
 
 .. toctree::
 
-   fastNLP.models.base_model
-   fastNLP.models.bert
    fastNLP.models.biaffine_parser
    fastNLP.models.cnn_text_classification
-   fastNLP.models.enas_controller
-   fastNLP.models.enas_model
-   fastNLP.models.enas_trainer
-   fastNLP.models.enas_utils
    fastNLP.models.sequence_labeling
    fastNLP.models.snli
    fastNLP.models.star_transformer

fastNLP/models/biaffine_parser.py

@@ -130,6 +130,8 @@ def _find_cycle(vertices, edges):
 
 class GraphParser(BaseModel):
     """
+    别名：:class:`fastNLP.models.GraphParser`  :class:`fastNLP.models.baffine_parser.GraphParser`
+
     基于图的parser base class, 支持贪婪解码和最大生成树解码
     """
     

fastNLP/models/cnn_text_classification.py

@@ -25,14 +25,14 @@ class CNNText(torch.nn.Module):
     :param int,tuple(int) kernel_sizes: 输出channel的kernel大小。
     :param float dropout: Dropout的大小
     """
-    
+
     def __init__(self, init_embed,
                  num_classes,
                  kernel_nums=(30, 40, 50),
                  kernel_sizes=(1, 3, 5),
                  dropout=0.5):
         super(CNNText, self).__init__()
-        
+
         # no support for pre-trained embedding currently
         self.embed = embedding.Embedding(init_embed)
         self.conv_pool = encoder.ConvMaxpool(
@@ -41,7 +41,7 @@ class CNNText(torch.nn.Module):
             kernel_sizes=kernel_sizes)
         self.dropout = nn.Dropout(dropout)
         self.fc = nn.Linear(sum(kernel_nums), num_classes)
-    
+
     def forward(self, words, seq_len=None):
         """
 
@@ -58,7 +58,7 @@ class CNNText(torch.nn.Module):
         x = self.dropout(x)
         x = self.fc(x)  # [N,C] -> [N, N_class]
         return {C.OUTPUT: x}
-    
+
     def predict(self, words, seq_len=None):
         """
         :param torch.LongTensor words: [batch_size, seq_len]，句子中word的index

fastNLP/models/sequence_labeling.py

@@ -1,10 +1,10 @@
 """
-    本模块实现了两种序列标注模型
+    本模块实现了几种序列标注模型
 """
 __all__ = [
     "SeqLabeling",
     "AdvSeqLabel",
-    "BiLSTMCRF"
+    # "BiLSTMCRF"
 ]
 
 import torch
@@ -25,7 +25,10 @@ from ..modules import ConditionalRandomField
 class BiLSTMCRF(BaseModel):
     """
     结构为BiLSTM + FC + Dropout + CRF.
-    TODO 补充文档
+
+    .. todo::
+        继续补充文档
+
     :param embed: tuple:
     :param num_classes:
     :param num_layers:

fastNLP/models/snli.py

@@ -15,7 +15,10 @@ from ..core.utils import seq_len_to_mask
 
 
 class ESIM(BaseModel):
-    """ESIM model的一个PyTorch实现
+    """
+    别名：:class:`fastNLP.models.ESIM`  :class:`fastNLP.models.snli.ESIM`
+
+    ESIM model的一个PyTorch实现
     论文参见： https://arxiv.org/pdf/1609.06038.pdf
 
     :param fastNLP.TokenEmbedding init_embedding: 初始化的TokenEmbedding

fastNLP/models/star_transformer.py

@@ -34,7 +34,7 @@ class StarTransEnc(nn.Module):
     :param emb_dropout: 词嵌入的dropout概率.
     :param dropout: 模型除词嵌入外的dropout概率.
     """
-    
+
     def __init__(self, init_embed,
                  hidden_size,
                  num_layers,
@@ -54,7 +54,7 @@ class StarTransEnc(nn.Module):
                                        head_dim=head_dim,
                                        dropout=dropout,
                                        max_len=max_len)
-    
+
     def forward(self, x, mask):
         """
         :param FloatTensor x: [batch, length, hidden] 输入的序列
@@ -79,7 +79,7 @@ class _Cls(nn.Module):
             nn.Dropout(dropout),
             nn.Linear(hid_dim, num_cls),
         )
-    
+
     def forward(self, x):
         h = self.fc(x)
         return h
@@ -95,7 +95,7 @@ class _NLICls(nn.Module):
             nn.Dropout(dropout),
             nn.Linear(hid_dim, num_cls),
         )
-    
+
     def forward(self, x1, x2):
         x = torch.cat([x1, x2, torch.abs(x1 - x2), x1 * x2], 1)
         h = self.fc(x)
@@ -121,7 +121,7 @@ class STSeqLabel(nn.Module):
     :param emb_dropout: 词嵌入的dropout概率. Default: 0.1
     :param dropout: 模型除词嵌入外的dropout概率. Default: 0.1
     """
-    
+
     def __init__(self, init_embed, num_cls,
                  hidden_size=300,
                  num_layers=4,
@@ -141,7 +141,7 @@ class STSeqLabel(nn.Module):
                                 emb_dropout=emb_dropout,
                                 dropout=dropout)
         self.cls = _Cls(hidden_size, num_cls, cls_hidden_size)
-    
+
     def forward(self, words, seq_len):
         """
 
@@ -154,7 +154,7 @@ class STSeqLabel(nn.Module):
         output = self.cls(nodes)
         output = output.transpose(1, 2)  # make hidden to be dim 1
         return {Const.OUTPUT: output}  # [bsz, n_cls, seq_len]
-    
+
     def predict(self, words, seq_len):
         """
 
@@ -186,7 +186,7 @@ class STSeqCls(nn.Module):
     :param emb_dropout: 词嵌入的dropout概率. Default: 0.1
     :param dropout: 模型除词嵌入外的dropout概率. Default: 0.1
     """
-    
+
     def __init__(self, init_embed, num_cls,
                  hidden_size=300,
                  num_layers=4,
@@ -206,7 +206,7 @@ class STSeqCls(nn.Module):
                                 emb_dropout=emb_dropout,
                                 dropout=dropout)
         self.cls = _Cls(hidden_size, num_cls, cls_hidden_size, dropout=dropout)
-    
+
     def forward(self, words, seq_len):
         """
 
@@ -219,7 +219,7 @@ class STSeqCls(nn.Module):
         y = 0.5 * (relay + nodes.max(1)[0])
         output = self.cls(y)  # [bsz, n_cls]
         return {Const.OUTPUT: output}
-    
+
     def predict(self, words, seq_len):
         """
 
@@ -251,7 +251,7 @@ class STNLICls(nn.Module):
     :param emb_dropout: 词嵌入的dropout概率. Default: 0.1
     :param dropout: 模型除词嵌入外的dropout概率. Default: 0.1
     """
-    
+
     def __init__(self, init_embed, num_cls,
                  hidden_size=300,
                  num_layers=4,
@@ -271,7 +271,7 @@ class STNLICls(nn.Module):
                                 emb_dropout=emb_dropout,
                                 dropout=dropout)
         self.cls = _NLICls(hidden_size, num_cls, cls_hidden_size)
-    
+
     def forward(self, words1, words2, seq_len1, seq_len2):
         """
 
@@ -283,16 +283,16 @@ class STNLICls(nn.Module):
         """
         mask1 = seq_len_to_mask(seq_len1)
         mask2 = seq_len_to_mask(seq_len2)
-        
+
         def enc(seq, mask):
             nodes, relay = self.enc(seq, mask)
             return 0.5 * (relay + nodes.max(1)[0])
-        
+
         y1 = enc(words1, mask1)
         y2 = enc(words2, mask2)
         output = self.cls(y1, y2)  # [bsz, n_cls]
         return {Const.OUTPUT: output}
-    
+
     def predict(self, words1, words2, seq_len1, seq_len2):
         """