remove useless import

demo/ernie-classification/README.md

 # ERNIE Classification
 
 本示例如果使用PaddleHub Finetune API快速的完成Transformer类模型ERNIE或BERT完成文本分类任务。
-
-

demo/ernie-classification/ernie_tiny_demo.py

+import paddle.fluid as fluid
+import paddlehub as hub
+
+module = hub.Module(name="ernie")
+inputs, outputs, program = module.context(trainable=True, max_seq_len=128)
+
+reader = hub.reader.ClassifyReader(
+    dataset=hub.dataset.ChnSentiCorp(),
+    vocab_path=module.get_vocab_path(),
+    max_seq_len=128)
+
+with fluid.program_guard(program):
+    label = fluid.layers.data(name="label", shape=[1], dtype='int64')
+
+    pooled_output = outputs["pooled_output"]
+
+    feed_list = [
+        inputs["input_ids"].name, inputs["position_ids"].name,
+        inputs["segment_ids"].name, inputs["input_mask"].name, label.name
+    ]
+
+    cls_task = hub.create_text_classification_task(
+        pooled_output, label, num_classes=reader.get_num_labels())
+
+    strategy = hub.BERTFinetuneStrategy(
+        weight_decay=0.01,
+        learning_rate=5e-5,
+        warmup_strategy="linear_warmup_decay",
+    )
+
+    config = hub.RunConfig(
+        use_cuda=True, num_epoch=3, batch_size=32, strategy=strategy)
+
+    hub.finetune_and_eval(
+        task=cls_task, data_reader=reader, feed_list=feed_list, config=config)

demo/ernie-classification/question_answering.py

@@ -13,16 +13,8 @@
 # limitations under the License.
 """Finetuning on classification task """
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
-import time
 import argparse
-import numpy as np
 
-import paddle
 import paddle.fluid as fluid
 import paddlehub as hub
 
@@ -46,9 +38,8 @@ if __name__ == '__main__':
         trainable=True, max_seq_len=args.max_seq_len)
 
     # Step2: Download dataset and use ClassifyReader to read dataset
-    dataset = hub.dataset.NLPCC_DBQA()
     reader = hub.reader.ClassifyReader(
-        dataset=dataset,
+        dataset=hub.dataset.NLPCC_DBQA(),
         vocab_path=module.get_vocab_path(),
         max_seq_len=args.max_seq_len)
     num_labels = len(reader.get_labels())

demo/ernie-classification/question_matching.py

@@ -13,16 +13,8 @@
 # limitations under the License.
 """Finetuning on classification task """
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
-import time
 import argparse
-import numpy as np
 
-import paddle
 import paddle.fluid as fluid
 import paddlehub as hub
 
@@ -46,9 +38,8 @@ if __name__ == '__main__':
         trainable=True, max_seq_len=args.max_seq_len)
 
     # Step2: Download dataset and use ClassifyReader to read dataset
-    dataset = hub.dataset.LCQMC()
     reader = hub.reader.ClassifyReader(
-        dataset=dataset,
+        dataset=hub.dataset.LCQMC(),
         vocab_path=module.get_vocab_path(),
         max_seq_len=args.max_seq_len)
     num_labels = len(reader.get_labels())

demo/ernie-classification/sentiment_cls.py

@@ -13,16 +13,8 @@
 # limitations under the License.
 """Finetuning on classification task """
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
-import time
 import argparse
-import numpy as np
 
-import paddle
 import paddle.fluid as fluid
 import paddlehub as hub
 
@@ -46,12 +38,10 @@ if __name__ == '__main__':
         trainable=True, max_seq_len=args.max_seq_len)
 
     # Step2: Download dataset and use ClassifyReader to read dataset
-    dataset = hub.dataset.ChnSentiCorp()
     reader = hub.reader.ClassifyReader(
-        dataset=dataset,
+        dataset=hub.dataset.ChnSentiCorp(),
         vocab_path=module.get_vocab_path(),
         max_seq_len=args.max_seq_len)
-    num_labels = len(reader.get_labels())
 
     # Step3: construct transfer learning network
     with fluid.program_guard(program):
@@ -69,7 +59,7 @@ if __name__ == '__main__':
         ]
         # Define a classfication finetune task by PaddleHub's API
         cls_task = hub.create_text_classification_task(
-            pooled_output, label, num_classes=num_labels)
+            pooled_output, label, num_classes=reader.get_num_labels())
 
         # Step4: Select finetune strategy, setup config and finetune
         strategy = hub.BERTFinetuneStrategy(

demo/ernie-seq-labeling/sequence_labeling.py

@@ -13,15 +13,6 @@
 # limitations under the License.
 """Finetuning on sequence labeling task."""
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
-import time
-import argparse
-import numpy as np
-
 import paddle
 import paddle.fluid as fluid
 import paddlehub as hub
@@ -46,9 +37,8 @@ if __name__ == '__main__':
         trainable=True, max_seq_len=args.max_seq_len)
 
     # Step2: Download dataset and use SequenceLabelReader to read dataset
-    dataset = hub.dataset.MSRA_NER()
     reader = hub.reader.SequenceLabelReader(
-        dataset=dataset,
+        dataset=hub.dataset.MSRA_NER(),
         vocab_path=module.get_vocab_path(),
         max_seq_len=args.max_seq_len)
 
@@ -60,7 +50,6 @@ if __name__ == '__main__':
             name="label", shape=[args.max_seq_len, 1], dtype='int64')
         seq_len = fluid.layers.data(name="seq_len", shape=[1], dtype='int64')
 
-        # Use "pooled_output" for classification tasks on an entire sentence.
         # Use "sequence_output" for token-level output.
         sequence_output = outputs["sequence_output"]
 
@@ -93,6 +82,7 @@ if __name__ == '__main__':
             batch_size=args.batch_size,
             checkpoint_dir=args.checkpoint_dir,
             strategy=strategy)
+
         # Finetune and evaluate model by PaddleHub's API
         # will finish training, evaluation, testing, save model automatically
         hub.finetune_and_eval(

paddlehub/reader/nlp_reader.py

@@ -80,6 +80,9 @@ class BaseReader(object):
         """Gets the list of labels for this data set."""
         return self.dataset.get_labels()
 
+    def get_num_labels(self):
+        return len(self.dataset.get_labels())
+
     def get_train_progress(self):
         """Gets progress for training phase."""
         return self.current_example, self.current_epoch