Merge branch 'release/v1.7' of https://github.com/Steffy-zxf/PaddleHub into release/v1.7

demo/autofinetune_image_classification/img_cls.py

@@ -18,7 +18,7 @@ parser.add_argument(
     default="mobilenet",
     help="Module used as feature extractor.")
 
-# the name of hyperparameters to be searched should keep with hparam.py
+# the name of hyper-parameters to be searched should keep with hparam.py
 parser.add_argument(
     "--batch_size",
     type=int,
@@ -27,7 +27,7 @@ parser.add_argument(
 parser.add_argument(
     "--learning_rate", type=float, default=1e-4, help="learning_rate.")
 
-# saved_params_dir and model_path are needed by auto finetune
+# saved_params_dir and model_path are needed by auto fine-tune
 parser.add_argument(
     "--saved_params_dir",
     type=str,
@@ -76,7 +76,7 @@ def finetune(args):
     img = input_dict["image"]
     feed_list = [img.name]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.DefaultFinetuneStrategy(learning_rate=args.learning_rate)
     config = hub.RunConfig(
         use_cuda=True,
@@ -100,7 +100,7 @@ def finetune(args):
             task.load_parameters(args.model_path)
             logger.info("PaddleHub has loaded model from %s" % args.model_path)
 
-    # Finetune by PaddleHub's API
+    # Fine-tune by PaddleHub's API
     task.finetune()
     # Evaluate by PaddleHub's API
     run_states = task.eval()
@@ -114,7 +114,7 @@ def finetune(args):
         shutil.copytree(best_model_dir, args.saved_params_dir)
         shutil.rmtree(config.checkpoint_dir)
 
-    # acc on dev will be used by auto finetune
+    # acc on dev will be used by auto fine-tune
     hub.report_final_result(eval_avg_score["acc"])
 
 

demo/autofinetune_text_classification/text_cls.py

@@ -13,7 +13,7 @@ from paddlehub.common.logger import logger
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--epochs", type=int, default=3, help="epochs.")
 
-# the name of hyperparameters to be searched should keep with hparam.py
+# the name of hyper-parameters to be searched should keep with hparam.py
 parser.add_argument("--batch_size", type=int, default=32, help="batch_size.")
 parser.add_argument(
     "--learning_rate", type=float, default=5e-5, help="learning_rate.")
@@ -33,7 +33,7 @@ parser.add_argument(
     default=None,
     help="Directory to model checkpoint")
 
-# saved_params_dir and model_path are needed by auto finetune
+# saved_params_dir and model_path are needed by auto fine-tune
 parser.add_argument(
     "--saved_params_dir",
     type=str,
@@ -82,14 +82,14 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_prop,
         learning_rate=args.learning_rate,
         weight_decay=args.weight_decay,
         lr_scheduler="linear_decay")
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         checkpoint_dir=args.checkpoint_dir,
         use_cuda=True,
@@ -98,7 +98,7 @@ if __name__ == '__main__':
         enable_memory_optim=True,
         strategy=strategy)
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=pooled_output,
@@ -125,5 +125,5 @@ if __name__ == '__main__':
         shutil.copytree(best_model_dir, args.saved_params_dir)
         shutil.rmtree(config.checkpoint_dir)
 
-    # acc on dev will be used by auto finetune
+    # acc on dev will be used by auto fine-tune
     hub.report_final_result(eval_avg_score["acc"])

demo/image_classification/img_classifier.py

@@ -14,7 +14,7 @@ parser.add_argument("--use_gpu",            type=ast.literal_eval,  default=True
 parser.add_argument("--checkpoint_dir",     type=str,               default="paddlehub_finetune_ckpt",  help="Path to save log data.")
 parser.add_argument("--batch_size",         type=int,               default=16,                         help="Total examples' number in batch for training.")
 parser.add_argument("--module",             type=str,               default="resnet50",                 help="Module used as feature extractor.")
-parser.add_argument("--dataset",            type=str,               default="flowers",                  help="Dataset to finetune.")
+parser.add_argument("--dataset",            type=str,               default="flowers",                  help="Dataset to fine-tune.")
 parser.add_argument("--use_data_parallel",  type=ast.literal_eval,  default=True,                      help="Whether use data parallel.")
 # yapf: enable.
 
@@ -60,7 +60,7 @@ def finetune(args):
     # Setup feed list for data feeder
     feed_list = [input_dict["image"].name]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -69,7 +69,7 @@ def finetune(args):
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
 
-    # Define a reading comprehension finetune task by PaddleHub's API
+    # Define a image classification task by PaddleHub Fine-tune API
     task = hub.ImageClassifierTask(
         data_reader=data_reader,
         feed_list=feed_list,
@@ -77,7 +77,7 @@ def finetune(args):
         num_classes=dataset.num_labels,
         config=config)
 
-    # Finetune by PaddleHub's API
+    # Fine-tune by PaddleHub's API
     task.finetune_and_eval()
 
 

demo/image_classification/predict.py

@@ -13,7 +13,7 @@ parser.add_argument("--use_gpu",            type=ast.literal_eval,  default=True
 parser.add_argument("--checkpoint_dir",     type=str,               default="paddlehub_finetune_ckpt",  help="Path to save log data.")
 parser.add_argument("--batch_size",         type=int,               default=16,                         help="Total examples' number in batch for training.")
 parser.add_argument("--module",             type=str,               default="resnet50",                 help="Module used as a feature extractor.")
-parser.add_argument("--dataset",            type=str,               default="flowers",                  help="Dataset to finetune.")
+parser.add_argument("--dataset",            type=str,               default="flowers",                  help="Dataset to fine-tune.")
 # yapf: enable.
 
 module_map = {
@@ -58,7 +58,7 @@ def predict(args):
     # Setup feed list for data feeder
     feed_list = [input_dict["image"].name]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -66,7 +66,7 @@ def predict(args):
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
 
-    # Define a reading comprehension finetune task by PaddleHub's API
+    # Define a image classification task by PaddleHub Fine-tune API
     task = hub.ImageClassifierTask(
         data_reader=data_reader,
         feed_list=feed_list,

demo/multi_label_classification/multi_label_classifier.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -23,7 +23,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.1, help="Warmup proportion params for warmup strategy")
@@ -56,13 +56,13 @@ if __name__ == '__main__':
     # Use "pooled_output" for classification tasks on an entire sentence.
     pooled_output = outputs["pooled_output"]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_cuda=args.use_gpu,
         num_epoch=args.num_epoch,
@@ -70,7 +70,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     multi_label_cls_task = hub.MultiLabelClassifierTask(
         data_reader=reader,
         feature=pooled_output,
@@ -78,6 +78,6 @@ if __name__ == '__main__':
         num_classes=dataset.num_labels,
         config=config)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     multi_label_cls_task.finetune_and_eval()

demo/multi_label_classification/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -35,7 +35,7 @@ parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
 parser.add_argument("--max_seq_len", type=int, default=128, help="Number of words of the longest seqence.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 args = parser.parse_args()
 # yapf: enable.
 
@@ -65,7 +65,7 @@ if __name__ == '__main__':
     # Use "sequence_output" for token-level output.
     pooled_output = outputs["pooled_output"]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -73,7 +73,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     multi_label_cls_task = hub.MultiLabelClassifierTask(
         data_reader=reader,
         feature=pooled_output,

demo/qa_classification/classifier.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -23,7 +23,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.0, help="Warmup proportion params for warmup strategy")
@@ -61,13 +61,13 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -76,7 +76,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=pooled_output,
@@ -84,6 +84,6 @@ if __name__ == '__main__':
         num_classes=dataset.num_labels,
         config=config)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     cls_task.finetune_and_eval()

demo/qa_classification/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -33,7 +33,7 @@ parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
 parser.add_argument("--max_seq_len", type=int, default=128, help="Number of words of the longest seqence.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 args = parser.parse_args()
 # yapf: enable.
 
@@ -63,7 +63,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -71,7 +71,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=pooled_output,

demo/reading_comprehension/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -28,7 +28,7 @@ hub.common.logger.logger.setLevel("INFO")
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=1, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint.")
 parser.add_argument("--max_seq_len", type=int, default=384, help="Number of words of the longest seqence.")
 parser.add_argument("--batch_size", type=int, default=8, help="Total examples' number in batch for training.")
@@ -64,7 +64,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -72,7 +72,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a reading comprehension finetune task by PaddleHub's API
+    # Define a reading comprehension fine-tune task by PaddleHub's API
     reading_comprehension_task = hub.ReadingComprehensionTask(
         data_reader=reader,
         feature=seq_output,

demo/reading_comprehension/reading_comprehension.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -25,7 +25,7 @@ hub.common.logger.logger.setLevel("INFO")
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=1, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=3e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.0, help="Warmup proportion params for warmup strategy")
@@ -64,13 +64,13 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate,
         warmup_proportion=args.warmup_proportion)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         eval_interval=300,
         use_data_parallel=args.use_data_parallel,
@@ -80,7 +80,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a reading comprehension finetune task by PaddleHub's API
+    # Define a reading comprehension fine-tune task by PaddleHub's API
     reading_comprehension_task = hub.ReadingComprehensionTask(
         data_reader=reader,
         feature=seq_output,
@@ -89,5 +89,5 @@ if __name__ == '__main__':
         sub_task="squad",
     )
 
-    # Finetune by PaddleHub's API
+    # Fine-tune by PaddleHub's API
     reading_comprehension_task.finetune_and_eval()

demo/regression/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -33,7 +33,7 @@ parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
 parser.add_argument("--max_seq_len", type=int, default=512, help="Number of words of the longest seqence.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 args = parser.parse_args()
 # yapf: enable.
 
@@ -64,7 +64,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -72,7 +72,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a regression finetune task by PaddleHub's API
+    # Define a regression fine-tune task by PaddleHub's API
     reg_task = hub.RegressionTask(
         data_reader=reader,
         feature=pooled_output,

demo/regression/regression.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -23,7 +23,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.1, help="Warmup proportion params for warmup strategy")
@@ -62,13 +62,13 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         eval_interval=300,
         use_data_parallel=args.use_data_parallel,
@@ -78,13 +78,13 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a regression finetune task by PaddleHub's API
+    # Define a regression fine-tune task by PaddleHub's API
     reg_task = hub.RegressionTask(
         data_reader=reader,
         feature=pooled_output,
         feed_list=feed_list,
         config=config)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     reg_task.finetune_and_eval()

demo/senta/predict.py

@@ -16,7 +16,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str,                 default=None, help="Directory to model checkpoint")
-parser.add_argument("--use_gpu",        type=ast.literal_eval,    default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu",        type=ast.literal_eval,    default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--batch_size",     type=int,                 default=1,    help="Total examples' number in batch when the program predicts.")
 args = parser.parse_args()
 # yapf: enable.
@@ -37,7 +37,7 @@ if __name__ == '__main__':
     # Must feed all the tensor of senta's module need
     feed_list = [inputs["words"].name]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -45,7 +45,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=sent_feature,

demo/senta/senta_finetune.py

@@ -8,7 +8,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size", type=int, default=32, help="Total examples' number in batch for training.")
 args = parser.parse_args()
@@ -30,7 +30,7 @@ if __name__ == '__main__':
     # Must feed all the tensor of senta's module need
     feed_list = [inputs["words"].name]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_cuda=args.use_gpu,
         use_pyreader=False,
@@ -40,7 +40,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=sent_feature,
@@ -48,6 +48,6 @@ if __name__ == '__main__':
         num_classes=dataset.num_labels,
         config=config)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     cls_task.finetune_and_eval()

demo/sequence_labeling/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on sequence labeling task """
+"""Fine-tuning on sequence labeling task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -27,14 +27,13 @@ import time
 import paddle
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.finetune.evaluate import chunk_eval, calculate_f1
 
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--max_seq_len", type=int, default=512, help="Number of words of the longest seqence.")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 args = parser.parse_args()
 # yapf: enable.
 
@@ -67,7 +66,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=False,
         use_cuda=args.use_gpu,
@@ -75,7 +74,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
 
-    # Define a sequence labeling finetune task by PaddleHub's API
+    # Define a sequence labeling fine-tune task by PaddleHub's API
     # if add crf, the network use crf as decoder
     seq_label_task = hub.SequenceLabelTask(
         data_reader=reader,
@@ -84,7 +83,7 @@ if __name__ == '__main__':
         max_seq_len=args.max_seq_len,
         num_classes=dataset.num_labels,
         config=config,
-        add_crf=True)
+        add_crf=False)
 
     # Data to be predicted
     # If using python 2, prefix "u" is necessary

demo/sequence_labeling/sequence_label.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on sequence labeling task."""
+"""Fine-tuning on sequence labeling task."""
 
 import argparse
 import ast
@@ -23,7 +23,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.1, help="Warmup proportion params for warmup strategy")
@@ -60,13 +60,13 @@ if __name__ == '__main__':
         inputs["segment_ids"].name, inputs["input_mask"].name
     ]
 
-    # Select a finetune strategy
+    # Select a fine-tune strategy
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -75,7 +75,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a sequence labeling finetune task by PaddleHub's API
+    # Define a sequence labeling fine-tune task by PaddleHub's API
     # If add crf, the network use crf as decoder
     seq_label_task = hub.SequenceLabelTask(
         data_reader=reader,
@@ -84,8 +84,8 @@ if __name__ == '__main__':
         max_seq_len=args.max_seq_len,
         num_classes=dataset.num_labels,
         config=config,
-        add_crf=True)
+        add_crf=False)
 
-    # Finetune and evaluate model by PaddleHub's API
+    # Fine-tune and evaluate model by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     seq_label_task.finetune_and_eval()

demo/ssd/ssd_demo.py

 #coding:utf-8
 import os
 import paddlehub as hub
+import cv2
 
 if __name__ == "__main__":
     ssd = hub.Module(name="ssd_mobilenet_v1_pascal")
 
     test_img_path = os.path.join("test", "test_img_bird.jpg")
 
-    # get the input keys for signature 'object_detection'
-    data_format = ssd.processor.data_format(sign_name='object_detection')
-    key = list(data_format.keys())[0]
-
-    # set input dict
-    input_dict = {key: [test_img_path]}
-
     # execute predict and print the result
-    results = ssd.object_detection(data=input_dict)
+    results = ssd.object_detection(images=[cv2.imread(test_img_path)])
     for result in results:
-        hub.logger.info(result)
+        print(result)

demo/text_classification/predict.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -32,7 +32,7 @@ parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
 parser.add_argument("--max_seq_len", type=int, default=512, help="Number of words of the longest seqence.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--use_data_parallel", type=ast.literal_eval, default=False, help="Whether use data parallel.")
 args = parser.parse_args()
 # yapf: enable.
@@ -70,7 +70,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -78,7 +78,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=pooled_output,

demo/text_classification/predict_predefine_net.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 from __future__ import absolute_import
 from __future__ import division
@@ -32,7 +32,7 @@ parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--checkpoint_dir", type=str, default=None, help="Directory to model checkpoint")
 parser.add_argument("--batch_size",     type=int,   default=1, help="Total examples' number in batch for training.")
 parser.add_argument("--max_seq_len", type=int, default=512, help="Number of words of the longest seqence.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=False, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--use_data_parallel", type=ast.literal_eval, default=False, help="Whether use data parallel.")
 parser.add_argument("--network", type=str, default='bilstm', help="Pre-defined network which was connected after Transformer model, such as ERNIE, BERT ,RoBERTa and ELECTRA.")
 args = parser.parse_args()
@@ -71,7 +71,7 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -79,7 +79,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=hub.AdamWeightDecayStrategy())
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     # network choice: bilstm, bow, cnn, dpcnn, gru, lstm (PaddleHub pre-defined network)
     # If you wanna add network after ERNIE/BERT/RoBERTa/ELECTRA module,
     # you must use the outputs["sequence_output"] as the token_feature of TextClassifierTask,

demo/text_classification/text_cls.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -21,7 +21,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.1, help="Warmup proportion params for warmup strategy")
@@ -68,13 +68,13 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -83,7 +83,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     cls_task = hub.TextClassifierTask(
         data_reader=reader,
         feature=pooled_output,
@@ -92,6 +92,6 @@ if __name__ == '__main__':
         config=config,
         metrics_choices=metrics_choices)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     cls_task.finetune_and_eval()

demo/text_classification/text_cls_predefine_net.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Finetuning on classification task """
+"""Fine-tuning on classification task """
 
 import argparse
 import ast
@@ -21,7 +21,7 @@ import paddlehub as hub
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--num_epoch", type=int, default=3, help="Number of epoches for fine-tuning.")
-parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for finetuning, input should be True or False")
+parser.add_argument("--use_gpu", type=ast.literal_eval, default=True, help="Whether use GPU for fine-tuning, input should be True or False")
 parser.add_argument("--learning_rate", type=float, default=5e-5, help="Learning rate used to train with warmup.")
 parser.add_argument("--weight_decay", type=float, default=0.01, help="Weight decay rate for L2 regularizer.")
 parser.add_argument("--warmup_proportion", type=float, default=0.1, help="Warmup proportion params for warmup strategy")
@@ -69,13 +69,13 @@ if __name__ == '__main__':
         inputs["input_mask"].name,
     ]
 
-    # Select finetune strategy, setup config and finetune
+    # Select fine-tune strategy, setup config and fine-tune
     strategy = hub.AdamWeightDecayStrategy(
         warmup_proportion=args.warmup_proportion,
         weight_decay=args.weight_decay,
         learning_rate=args.learning_rate)
 
-    # Setup runing config for PaddleHub Finetune API
+    # Setup RunConfig for PaddleHub Fine-tune API
     config = hub.RunConfig(
         use_data_parallel=args.use_data_parallel,
         use_cuda=args.use_gpu,
@@ -84,7 +84,7 @@ if __name__ == '__main__':
         checkpoint_dir=args.checkpoint_dir,
         strategy=strategy)
 
-    # Define a classfication finetune task by PaddleHub's API
+    # Define a classfication fine-tune task by PaddleHub's API
     # network choice: bilstm, bow, cnn, dpcnn, gru, lstm (PaddleHub pre-defined network)
     # If you wanna add network after ERNIE/BERT/RoBERTa/ELECTRA module,
     # you must use the outputs["sequence_output"] as the token_feature of TextClassifierTask,
@@ -98,6 +98,6 @@ if __name__ == '__main__':
         config=config,
         metrics_choices=metrics_choices)
 
-    # Finetune and evaluate by PaddleHub's API
+    # Fine-tune and evaluate by PaddleHub's API
     # will finish training, evaluation, testing, save model automatically
     cls_task.finetune_and_eval()

paddlehub/__init__.py

@@ -22,6 +22,8 @@ if six.PY2:
     reload(sys)  # noqa
     sys.setdefaultencoding("UTF-8")
 
+from .version import hub_version as __version__
+
 from . import module
 from . import common
 from . import io

paddlehub/version.py

@@ -13,5 +13,5 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 """ PaddleHub version string """
-hub_version = "1.6.2"
+hub_version = "1.7.0"
 module_proto_version = "1.0.0"

requirements.txt

 pre-commit
 protobuf >= 3.6.0
 yapf == 0.26.0
-pyyaml
-Pillow
 six >= 1.10.0
-chardet == 3.0.4
-requests
 flask >= 1.1.0
 flake8
 visualdl == 2.0.0a0
-cma == 2.7.0
+cma >= 2.7.0
 sentencepiece
-nltk
 colorlog
 opencv-python
 
-# numpy no longer support python2 in version 1.17 and above
-numpy ; python_version >= "3"
-numpy < 1.17.0 ; python_version < "3"
-
 # pandas no longer support python2 in version 0.25 and above
 pandas ; python_version >= "3"
-pandas < 0.25.0 ; python_version < "3"
 
 # gunicorn not support windows
 gunicorn >= 19.10.0; sys_platform != "win32"