diff --git a/demo/autofinetune_image_classification/img_cls.py b/demo/autofinetune_image_classification/img_cls.py index c1194de2f52877b23924a91610e50284c1e3734a..ba61db1a9d584cde8952ac1f839137c2d604625c 100644 --- a/demo/autofinetune_image_classification/img_cls.py +++ b/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"]) diff --git a/demo/autofinetune_text_classification/text_cls.py b/demo/autofinetune_text_classification/text_cls.py index a08ef35b9468dc7ca76e8b4b9f570c62cc96c58c..198523430b0a07b1afebbc1ef9078b8c41472965 100644 --- a/demo/autofinetune_text_classification/text_cls.py +++ b/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"]) diff --git a/demo/image_classification/img_classifier.py b/demo/image_classification/img_classifier.py index 40e170a564ddcc9c54a6d6aff08e898466da5320..f79323be30f79509dcf4a0588383a724e2cbbcc5 100644 --- a/demo/image_classification/img_classifier.py +++ b/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() diff --git a/demo/image_classification/predict.py b/demo/image_classification/predict.py index bc2192686b049f95fbfdd9bef6da92598404848c..ac6bc802e2dc3d2b2c54bfcb59a0e58c3161354f 100644 --- a/demo/image_classification/predict.py +++ b/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, diff --git a/demo/multi_label_classification/multi_label_classifier.py b/demo/multi_label_classification/multi_label_classifier.py index f958902fe4cade75e5a624e7c84225e4344aae78..76645d2f88fb390e3b36ea3e2c86809d17451284 100644 --- a/demo/multi_label_classification/multi_label_classifier.py +++ b/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() diff --git a/demo/multi_label_classification/predict.py b/demo/multi_label_classification/predict.py index bcc11592232d1f946c945d0d6ca6eff87cde7090..bcd849061e5a663933a83c9a39b2d0d5cf2f8705 100644 --- a/demo/multi_label_classification/predict.py +++ b/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, diff --git a/demo/qa_classification/classifier.py b/demo/qa_classification/classifier.py index 4c1fad8030e567b7dcb4c1576209d1ac06ee65e6..70f22a70938017ca270f0d3577a1574053c0fa9f 100644 --- a/demo/qa_classification/classifier.py +++ b/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() diff --git a/demo/qa_classification/predict.py b/demo/qa_classification/predict.py index fd8ab5a48047eebdc45776e6aeb9be8839a7c3ee..170319d2ee55f0c8060d42fb3f18ec920152ccc7 100644 --- a/demo/qa_classification/predict.py +++ b/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, diff --git a/demo/reading_comprehension/predict.py b/demo/reading_comprehension/predict.py index a9f8c2f998fb0a29ea76473f412142806ea36b3b..2cc96f62acea550e3ffa9d9e0bb12bfbb9d3ce7b 100644 --- a/demo/reading_comprehension/predict.py +++ b/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, diff --git a/demo/reading_comprehension/reading_comprehension.py b/demo/reading_comprehension/reading_comprehension.py index 11fe241d8aff97591979e2dcde16f74a7ef67367..d4793823d2147ecb6f8badb776d4cb827b541a8d 100644 --- a/demo/reading_comprehension/reading_comprehension.py +++ b/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() diff --git a/demo/regression/predict.py b/demo/regression/predict.py index 0adfc3886a54f60b7282fbc0584793f7b1c06a5d..b9e73d995f9c63fd847bda46561bd35c66a31f2a 100644 --- a/demo/regression/predict.py +++ b/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, diff --git a/demo/regression/regression.py b/demo/regression/regression.py index e2c1c0bf5da280b9c7a701a6c393a6ddd8bea145..0979e1c639ca728c46151ad151aaaa9bd389ecc1 100644 --- a/demo/regression/regression.py +++ b/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() diff --git a/demo/senta/predict.py b/demo/senta/predict.py index a1d800889fe72876a733629e2f822efd53fecfd4..f287c576d95588aedf4baf5e8563a2d09f6f61b6 100644 --- a/demo/senta/predict.py +++ b/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, diff --git a/demo/senta/senta_finetune.py b/demo/senta/senta_finetune.py index 18b0a092dc25a2bbcd3313a9e6a66cd3976d303f..cba8326e5aa04ca71a05862a5de8524350b26ac8 100644 --- a/demo/senta/senta_finetune.py +++ b/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() diff --git a/demo/sequence_labeling/predict.py b/demo/sequence_labeling/predict.py index fb189b42b83319bcee2823d71ca25bb94e52ec18..54deb81d41f848719b7d1263b56b0cdadefa7de4 100644 --- a/demo/sequence_labeling/predict.py +++ b/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 diff --git a/demo/sequence_labeling/sequence_label.py b/demo/sequence_labeling/sequence_label.py index a2b283e857c39ff60912a5df5560ddc08f5f4a1c..958f9839b9fa1ea4655dec20e56165eaf7883da1 100644 --- a/demo/sequence_labeling/sequence_label.py +++ b/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() diff --git a/demo/text_classification/predict.py b/demo/text_classification/predict.py index 81dcd41ecf193a7329a003827351f3b843118de8..3a63e63b1078d537e502aad0613cccd712186b72 100644 --- a/demo/text_classification/predict.py +++ b/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, diff --git a/demo/text_classification/predict_predefine_net.py b/demo/text_classification/predict_predefine_net.py index e53cf2b8712f1160abb99e985ca85fb5a4174127..3255270310527b81c3eb272d8331ff7ce3dfd3b3 100644 --- a/demo/text_classification/predict_predefine_net.py +++ b/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, diff --git a/demo/text_classification/text_cls.py b/demo/text_classification/text_cls.py index e221cdc7e9fbc0c63162c9a43e9751ddc6ac223a..b68925ba282775b0c57ceb6b249bc53ac258c55e 100644 --- a/demo/text_classification/text_cls.py +++ b/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() diff --git a/demo/text_classification/text_cls_predefine_net.py b/demo/text_classification/text_cls_predefine_net.py index 23746c03e2563ca2696ff0351cb93d73ae17de1f..4194bb4264bf86631fc9f550cc9b59f421be021d 100644 --- a/demo/text_classification/text_cls_predefine_net.py +++ b/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()