- 添加pos_tagger API， pipeline跑通

- 修复processor的bug
- 更新core/的若干组件, 去除batch的冗余参数
- CRF有个打字错误？已修复
- 更新pos tag 训练脚本

fastNLP/api/api.py

@@ -1,14 +1,18 @@
 
 import torch
 
+from fastNLP.core.dataset import DataSet
+from fastNLP.core.instance import Instance
+from fastNLP.core.predictor import Predictor
+
 
 class API:
     def __init__(self):
         self.pipeline = None
         self.model = None
 
-    def predict(self):
-        pass
+    def predict(self, *args, **kwargs):
+        raise NotImplementedError
 
     def load(self, name):
         _dict = torch.load(name)
@@ -19,3 +23,47 @@ class API:
         _dict = {'pipeline': self.pipeline,
                  'model': self.model}
         torch.save(_dict, path)
+
+
+class POS_tagger(API):
+    """FastNLP API for Part-Of-Speech tagging.
+
+    """
+
+    def __init__(self):
+        super(POS_tagger, self).__init__()
+
+    def predict(self, query):
+        """
+
+        :param query: list of list of str. Each string is a token(word).
+        :return answer: list of list of str. Each string is a tag.
+        """
+        self.load("/home/zyfeng/fastnlp_0.2.0/reproduction/pos_tag_model/model_pp.pkl")
+
+        data = DataSet()
+        for example in query:
+            data.append(Instance(words=example))
+
+        data = self.pipeline(data)
+
+        predictor = Predictor()
+        outputs = predictor.predict(self.model, data)
+
+        answers = []
+        for out in outputs:
+            out = out.numpy()
+            for sent in out:
+                answers.append([self.tag_vocab.to_word(tag) for tag in sent])
+        return answers
+
+    def load(self, name):
+        _dict = torch.load(name)
+        self.pipeline = _dict['pipeline']
+        self.model = _dict['model']
+        self.tag_vocab = _dict["tag_vocab"]
+
+
+if __name__ == "__main__":
+    tagger = POS_tagger()
+    print(tagger.predict([["我", "是", "学生", "。"], ["我", "是", "学生", "。"]]))

fastNLP/api/pipeline.py

@@ -11,7 +11,7 @@ class Pipeline:
         self.pipeline = []
         if isinstance(processors, list):
             for proc in processors:
-                assert isinstance(proc, Processor), "Must be a Processor, not {}.".format(type(processor))
+                assert isinstance(proc, Processor), "Must be a Processor, not {}.".format(type(proc))
             self.pipeline = processors
 
     def add_processor(self, processor):
@@ -21,7 +21,7 @@ class Pipeline:
     def process(self, dataset):
         assert len(self.pipeline) != 0, "You need to add some processor first."
 
-        for proc_name, proc in self.pipeline:
+        for proc in self.pipeline:
             dataset = proc(dataset)
 
         return dataset

fastNLP/core/batch.py

@@ -9,7 +9,7 @@ class Batch(object):
 
     """
 
-    def __init__(self, dataset, batch_size, sampler, use_cuda, sort_in_batch=False, sort_key=None):
+    def __init__(self, dataset, batch_size, sampler, use_cuda):
         """
 
         :param dataset: a DataSet object
@@ -22,8 +22,6 @@ class Batch(object):
         self.batch_size = batch_size
         self.sampler = sampler
         self.use_cuda = use_cuda
-        self.sort_in_batch = sort_in_batch
-        self.sort_key = sort_key if sort_key is not None else 'word_seq'
         self.idx_list = None
         self.curidx = 0
 

fastNLP/core/dataset.py

@@ -119,7 +119,7 @@ class DataSet(object):
                 assert isinstance(val, bool)
                 self.field_arrays[name].is_target = val
             else:
-                raise KeyError
+                raise KeyError("{} is not a valid field name.".format(name))
         return self
 
     def set_need_tensor(self, **kwargs):

fastNLP/core/metrics.py

@@ -43,12 +43,11 @@ class SeqLabelEvaluator(Evaluator):
         :return accuracy:
         """
         truth = [item["truth"] for item in truth]
-        total_correct, total_count= 0., 0.
+        total_correct, total_count = 0., 0.
         for x, y in zip(predict, truth):
-            x = torch.Tensor(x)
+            x = torch.tensor(x)
             y = y.to(x)  # make sure they are in the same device
-            mask = x.ge(1).float()
-            # correct = torch.sum(x * mask.float() == (y * mask.long()).float())
+            mask = x.ge(1).long()
             correct = torch.sum(x * mask == y * mask)
             correct -= torch.sum(x.le(0))
             total_correct += float(correct)

fastNLP/core/tester.py

@@ -74,7 +74,7 @@ class Tester(object):
         output_list = []
         truth_list = []
 
-        data_iterator = Batch(dev_data, self.batch_size, sampler=RandomSampler(), use_cuda=self.use_cuda, sort_in_batch=True, sort_key='word_seq')
+        data_iterator = Batch(dev_data, self.batch_size, sampler=RandomSampler(), use_cuda=self.use_cuda)
 
         with torch.no_grad():
             for batch_x, batch_y in data_iterator:

fastNLP/core/trainer.py

@@ -11,6 +11,7 @@ from fastNLP.core.metrics import Evaluator
 from fastNLP.core.optimizer import Optimizer
 from fastNLP.core.sampler import RandomSampler
 from fastNLP.core.tester import SeqLabelTester, ClassificationTester, SNLITester
+from fastNLP.core.tester import Tester
 from fastNLP.saver.logger import create_logger
 from fastNLP.saver.model_saver import ModelSaver
 
@@ -144,7 +145,7 @@ class Trainer(object):
 
             # prepare mini-batch iterator
             data_iterator = Batch(train_data, batch_size=self.batch_size, sampler=RandomSampler(),
-                                  use_cuda=self.use_cuda, sort_in_batch=True, sort_key='word_seq')
+                                  use_cuda=self.use_cuda)
             logger.info("prepared data iterator")
 
             # one forward and backward pass
@@ -230,7 +231,6 @@ class Trainer(object):
     def update(self):
         """Perform weight update on a model.
 
-        For PyTorch, just call optimizer to update.
         """
         self._optimizer.step()
 
@@ -319,7 +319,7 @@ class Trainer(object):
         ModelSaver(os.path.join(self.pickle_path, model_name)).save_pytorch(network)
 
     def _create_validator(self, valid_args):
-        raise NotImplementedError
+        return Tester(**valid_args)
 
     def set_validator(self, validor):
         self.validator = validor

fastNLP/models/sequence_modeling.py

@@ -116,11 +116,11 @@ class AdvSeqLabel(SeqLabeling):
         num_classes = args["num_classes"]
 
         self.Embedding = encoder.embedding.Embedding(vocab_size, word_emb_dim, init_emb=emb)
-        self.Rnn = encoder.lstm.LSTM(word_emb_dim, hidden_dim, num_layers=3, dropout=0.3, bidirectional=True)
+        self.Rnn = encoder.lstm.LSTM(word_emb_dim, hidden_dim, num_layers=3, dropout=0.5, bidirectional=True)
         self.Linear1 = encoder.Linear(hidden_dim * 2, hidden_dim * 2 // 3)
         self.batch_norm = torch.nn.BatchNorm1d(hidden_dim * 2 // 3)
         self.relu = torch.nn.ReLU()
-        self.drop = torch.nn.Dropout(0.3)
+        self.drop = torch.nn.Dropout(0.5)
         self.Linear2 = encoder.Linear(hidden_dim * 2 // 3, num_classes)
 
         self.Crf = decoder.CRF.ConditionalRandomField(num_classes)
@@ -135,7 +135,7 @@ class AdvSeqLabel(SeqLabeling):
         """
         word_seq = word_seq.long()
         word_seq_origin_len = word_seq_origin_len.long()
-        truth = truth.long()
+        truth = truth.long() if truth is not None else None
         self.mask = self.make_mask(word_seq, word_seq_origin_len)
 
         batch_size = word_seq.size(0)

fastNLP/modules/decoder/CRF.py

@@ -128,7 +128,7 @@ class ConditionalRandomField(nn.Module):
         vpath = data.new_zeros((seq_len, batch_size, n_tags), dtype=torch.long)
         vscore = data[0]
         if self.include_start_end_trans:
-            vscore += self.start_scores.view(1. -1)
+            vscore += self.start_scores.view(1, -1)
         for i in range(1, seq_len):
             prev_score = vscore.view(batch_size, n_tags, 1)
             cur_score = data[i].view(batch_size, 1, n_tags)

reproduction/pos_tag_model/pos_tag.cfg

@@ -1,6 +1,6 @@
 [train]
-epochs = 20
-batch_size = 32
+epochs = 5
+batch_size = 64
 pickle_path = "./save/"
 validate = false
 save_best_dev = true

reproduction/pos_tag_model/train_pos_tag.py

@@ -1,3 +1,4 @@
+import copy
 import os
 
 import torch
@@ -6,6 +7,7 @@ from fastNLP.api.pipeline import Pipeline
 from fastNLP.api.processor import VocabProcessor, IndexerProcessor, SeqLenProcessor
 from fastNLP.core.dataset import DataSet
 from fastNLP.core.instance import Instance
+from fastNLP.core.metrics import SeqLabelEvaluator
 from fastNLP.core.optimizer import Optimizer
 from fastNLP.core.trainer import Trainer
 from fastNLP.loader.config_loader import ConfigLoader, ConfigSection
@@ -13,9 +15,12 @@ from fastNLP.loader.dataset_loader import PeopleDailyCorpusLoader
 from fastNLP.models.sequence_modeling import AdvSeqLabel
 
 cfgfile = './pos_tag.cfg'
+# datadir = "/home/zyfeng/data/"
+# data_name = "POS_PD_1998.txt"
 datadir = "/home/zyfeng/fastnlp_0.2.0/test/data_for_tests/"
 data_name = "people_daily_raw.txt"
 
+
 pos_tag_data_path = os.path.join(datadir, data_name)
 pickle_path = "save"
 data_infer_path = os.path.join(datadir, "infer.utf8")
@@ -54,6 +59,9 @@ def train():
     seq_len_proc = SeqLenProcessor("word_seq", "word_seq_origin_len")
     seq_len_proc(dataset)
 
+    dev_set = copy.deepcopy(dataset)
+    dev_set.set_is_target(truth=True)
+
     print("processors defined")
     # dataset.set_is_target(tag_ids=True)
     model_param["vocab_size"] = len(word_vocab_proc.get_vocab())
@@ -66,14 +74,15 @@ def train():
     # call trainer to train
     trainer = Trainer(epochs=train_param["epochs"],
                       batch_size=train_param["batch_size"],
-                      validate=False,
+                      validate=True,
                       optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
+                      evaluator=SeqLabelEvaluator()
                       )
-    trainer.train(model, dataset)
+    trainer.train(model, dataset, dev_set)
 
     # save model & pipeline
-    pp = Pipeline([word_vocab_proc, word_indexer, seq_len_proc])
-    save_dict = {"pipeline": pp, "model": model}
+    pp = Pipeline([word_indexer, seq_len_proc])
+    save_dict = {"pipeline": pp, "model": model, "tag_vocab": tag_vocab_proc.get_vocab()}
     torch.save(save_dict, "model_pp.pkl")