-
Notifications
You must be signed in to change notification settings - Fork 60
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
12 changed files
with
1,142 additions
and
1,113 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,11 @@ | ||
| name = "bert_classifier" | ||
| hidden_size = 768 | ||
| clas_strategy = "cls_time" | ||
| dropout = 0.1 | ||
| num_classes = 2 | ||
|
|
||
| # This hyperparams is used in bert_with_hypertuning_main.py example | ||
| hyperparams = { | ||
| "optimizer.warmup_steps": {"start": 10000, "end": 20000, "dtype": int}, | ||
| "optimizer.static_lr": {"start": 1e-3, "end": 1e-2, "dtype": float} | ||
| } | ||
| name = "bert_classifier" | ||
| hidden_size = 768 | ||
| clas_strategy = "cls_time" | ||
| dropout = 0.1 | ||
| num_classes = 2 | ||
|
|
||
| # This hyperparams is used in bert_with_hypertuning_main.py example | ||
| hyperparams = { | ||
| "optimizer.warmup_steps": {"start": 10000, "end": 20000, "dtype": int}, | ||
| "optimizer.static_lr": {"start": 1e-3, "end": 1e-2, "dtype": float} | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,68 +1,68 @@ | ||
| pickle_data_dir = "data/IMDB" | ||
| max_seq_length = 64 | ||
| num_classes = 2 | ||
| num_train_data = 25000 | ||
|
|
||
| # used for bert executor example | ||
| max_batch_tokens = 128 | ||
|
|
||
| train_batch_size = 32 | ||
| max_train_epoch = 5 | ||
| display_steps = 50 # Print training loss every display_steps; -1 to disable | ||
|
|
||
| # tbx config | ||
| tbx_logging_steps = 5 # log the metrics for tbX visualization | ||
| tbx_log_dir = "runs/" | ||
| exp_number = 1 # experiment number | ||
|
|
||
| eval_steps = 100 # Eval on the dev set every eval_steps; -1 to disable | ||
| # Proportion of training to perform linear learning rate warmup for. | ||
| # E.g., 0.1 = 10% of training. | ||
| warmup_proportion = 0.1 | ||
| eval_batch_size = 8 | ||
| test_batch_size = 8 | ||
|
|
||
| feature_types = { | ||
| # Reading features from pickled data file. | ||
| # E.g., Reading feature "input_ids" as dtype `int64`; | ||
| # "FixedLenFeature" indicates its length is fixed for all data instances; | ||
| # and the sequence length is limited by `max_seq_length`. | ||
| "input_ids": ["int64", "stacked_tensor", max_seq_length], | ||
| "input_mask": ["int64", "stacked_tensor", max_seq_length], | ||
| "segment_ids": ["int64", "stacked_tensor", max_seq_length], | ||
| "label_ids": ["int64", "stacked_tensor"] | ||
| } | ||
|
|
||
| train_hparam = { | ||
| "allow_smaller_final_batch": False, | ||
| "batch_size": train_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/train.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": True, | ||
| "shuffle_buffer_size": None | ||
| } | ||
|
|
||
| eval_hparam = { | ||
| "allow_smaller_final_batch": True, | ||
| "batch_size": eval_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/eval.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": False | ||
| } | ||
|
|
||
| test_hparam = { | ||
| "allow_smaller_final_batch": True, | ||
| "batch_size": test_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/predict.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": False | ||
| } | ||
| pickle_data_dir = "data/IMDB" | ||
| max_seq_length = 64 | ||
| num_classes = 2 | ||
| num_train_data = 25000 | ||
|
|
||
| # used for bert executor example | ||
| max_batch_tokens = 128 | ||
|
|
||
| train_batch_size = 32 | ||
| max_train_epoch = 5 | ||
| display_steps = 50 # Print training loss every display_steps; -1 to disable | ||
|
|
||
| # tbx config | ||
| tbx_logging_steps = 5 # log the metrics for tbX visualization | ||
| tbx_log_dir = "runs/" | ||
| exp_number = 1 # experiment number | ||
|
|
||
| eval_steps = 100 # Eval on the dev set every eval_steps; -1 to disable | ||
| # Proportion of training to perform linear learning rate warmup for. | ||
| # E.g., 0.1 = 10% of training. | ||
| warmup_proportion = 0.1 | ||
| eval_batch_size = 8 | ||
| test_batch_size = 8 | ||
|
|
||
| feature_types = { | ||
| # Reading features from pickled data file. | ||
| # E.g., Reading feature "input_ids" as dtype `int64`; | ||
| # "FixedLenFeature" indicates its length is fixed for all data instances; | ||
| # and the sequence length is limited by `max_seq_length`. | ||
| "input_ids": ["int64", "stacked_tensor", max_seq_length], | ||
| "input_mask": ["int64", "stacked_tensor", max_seq_length], | ||
| "segment_ids": ["int64", "stacked_tensor", max_seq_length], | ||
| "label_ids": ["int64", "stacked_tensor"] | ||
| } | ||
|
|
||
| train_hparam = { | ||
| "allow_smaller_final_batch": False, | ||
| "batch_size": train_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/train.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": True, | ||
| "shuffle_buffer_size": None | ||
| } | ||
|
|
||
| eval_hparam = { | ||
| "allow_smaller_final_batch": True, | ||
| "batch_size": eval_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/eval.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": False | ||
| } | ||
|
|
||
| test_hparam = { | ||
| "allow_smaller_final_batch": True, | ||
| "batch_size": test_batch_size, | ||
| "dataset": { | ||
| "data_name": "data", | ||
| "feature_types": feature_types, | ||
| "files": "{}/predict.pkl".format(pickle_data_dir) | ||
| }, | ||
| "shuffle": False | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,18 +1,34 @@ | ||
| import os | ||
| import sys | ||
|
|
||
| def main(arguments): | ||
| import subprocess | ||
| if not os.path.exists("data/IMDB_raw"): | ||
| subprocess.run("mkdir data/IMDB_raw", shell=True) | ||
| # pylint: disable=line-too-long | ||
| subprocess.run( | ||
| 'wget -P data/IMDB_raw/ https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz', | ||
| shell=True) | ||
| subprocess.run( | ||
| 'tar xzvf data/IMDB_raw/aclImdb_v1.tar.gz -C data/IMDB_raw/ && rm data/IMDB_raw/aclImdb_v1.tar.gz', | ||
| shell=True) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| sys.exit(main(sys.argv[1:])) | ||
| # Copyright 2020 The Forte Authors. All Rights Reserved. | ||
| # | ||
| # Licensed under the Apache License, Version 2.0 (the "License"); | ||
| # you may not use this file except in compliance with the License. | ||
| # You may obtain a copy of the License at | ||
| # | ||
| # http://www.apache.org/licenses/LICENSE-2.0 | ||
| # | ||
| # Unless required by applicable law or agreed to in writing, software | ||
| # distributed under the License is distributed on an "AS IS" BASIS, | ||
| # 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. | ||
|
|
||
|
|
||
| import os | ||
| import sys | ||
| import subprocess | ||
|
|
||
|
|
||
| def main(): | ||
| if not os.path.exists("data/IMDB_raw"): | ||
| subprocess.run("mkdir data/IMDB_raw", shell=True, check=True) | ||
| # pylint: disable=line-too-long | ||
| subprocess.run( | ||
| 'wget -P data/IMDB_raw/ https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz', | ||
| shell=True, check=True) | ||
| subprocess.run( | ||
| 'tar xzvf data/IMDB_raw/aclImdb_v1.tar.gz -C data/IMDB_raw/ && rm data/IMDB_raw/aclImdb_v1.tar.gz', | ||
| shell=True, check=True) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| sys.exit(main()) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,28 +1,31 @@ | ||
| # Copyright 2020 The Forte Authors. All Rights Reserved. | ||
| # | ||
| # Licensed under the Apache License, Version 2.0 (the "License"); | ||
| # you may not use this file except in compliance with the License. | ||
| # You may obtain a copy of the License at | ||
| # | ||
| # http://www.apache.org/licenses/LICENSE-2.0 | ||
| # | ||
| # Unless required by applicable law or agreed to in writing, software | ||
| # distributed under the License is distributed on an "AS IS" BASIS, | ||
| # 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. | ||
|
|
||
| import os | ||
|
|
||
| from forte.models.imdb_text_classifier.model import IMDBClassifier | ||
| import config_data | ||
| import config_classifier | ||
|
|
||
| def main(argv=None): | ||
| model = IMDBClassifier(config_data, config_classifier) | ||
| if not os.path.isfile("data/IMDB/train.pkl"): | ||
| model.prepare_data("data/IMDB") | ||
| model.run(do_train=True, do_eval=True, do_test=False) | ||
|
|
||
| if __name__ == "__main__": | ||
| main() | ||
| # Copyright 2020 The Forte Authors. All Rights Reserved. | ||
| # | ||
| # Licensed under the Apache License, Version 2.0 (the "License"); | ||
| # you may not use this file except in compliance with the License. | ||
| # You may obtain a copy of the License at | ||
| # | ||
| # http://www.apache.org/licenses/LICENSE-2.0 | ||
| # | ||
| # Unless required by applicable law or agreed to in writing, software | ||
| # distributed under the License is distributed on an "AS IS" BASIS, | ||
| # 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. | ||
|
|
||
|
|
||
| import os | ||
|
|
||
| from forte.models.imdb_text_classifier.model import IMDBClassifier | ||
| import config_data | ||
| import config_classifier | ||
|
|
||
|
|
||
| def main(): | ||
| model = IMDBClassifier(config_data, config_classifier) | ||
| if not os.path.isfile("data/IMDB/train.pkl"): | ||
| model.prepare_data("data/IMDB") | ||
| model.run(do_train=True, do_eval=True, do_test=False) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| main() |
Oops, something went wrong.