Hannes Hapke hanneshapke
hanneshapke
/ bert_data_structure.py
Created
March 9, 2020 18:03
This file contains hidden or 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
| { | |
| 'input_mask': array( | |
| [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]), | |
| 'input_type_ids': array( | |
| [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), | |
| 'input_word_ids': array( | |
| [ 101, 2023, 3319, 3397, 27594, 2545, 2005, 2216, 2040, ..., 2014, 102]), | |
| 'label': array([0]) | |
| } |
hanneshapke
/ mirrored_strategy.py
Created
March 9, 2020 18:01
This file contains hidden or 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
| mirrored_strategy = tf.distribute.MirroredStrategy() | |
| with mirrored_strategy.scope(): | |
| model = get_model(tf_transform_output=tf_transform_output) |
hanneshapke
/ run_fn.py
Created
March 9, 2020 18:00
This file contains hidden or 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
| def run_fn(fn_args: TrainerFnArgs): | |
| tf_transform_output = tft.TFTransformOutput(fn_args.transform_output) | |
| train_dataset = _input_fn( | |
| fn_args.train_files, tf_transform_output, 32) | |
| eval_dataset = _input_fn( | |
| fn_args.eval_files, tf_transform_output, 32) | |
| mirrored_strategy = tf.distribute.MirroredStrategy() | |
| with mirrored_strategy.scope(): | |
| model = get_model(tf_transform_output=tf_transform_output) |
hanneshapke
/ cast_between_tft_tfhub.py
Created
March 9, 2020 18:00
This file contains hidden or 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
| input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32) | |
| input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32) | |
| input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32) |
hanneshapke
/ model_architecture.py
Last active
March 20, 2020 18:43
This file contains hidden or 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
| feature_spec = tf_transform_output.transformed_feature_spec() | |
| feature_spec.pop(_LABEL_KEY) | |
| inputs = {key: tf.keras.layers.Input(shape=(max_seq_length), | |
| name=key, dtype=tf.int32) | |
| for key in feature_spec.keys()} | |
| input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32) | |
| input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32) | |
| input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32) |
hanneshapke
/ input_type_ids.py
Created
March 9, 2020 17:50
This file contains hidden or 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
| input_type_ids = tf.zeros_like(input_mask) |
hanneshapke
/ preprocessing_fn.py
Created
March 9, 2020 17:48
This file contains hidden or 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
| def preprocessing_fn(inputs): | |
| def tokenize_text(text, sequence_length=MAX_SEQ_LEN): | |
| ... | |
| return tf.reshape(tokens, [-1, sequence_length]) | |
| def preprocess_bert_input(text, segment_id=0): | |
| input_word_ids = tokenize_text(text) | |
| ... | |
| return ( |
hanneshapke
/ adding_of_CLS_and_SEP_tokens.py
Created
March 9, 2020 17:47
adding_of_CLS_and_SEP_tokens
This file contains hidden or 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
| CLS_ID = tf.constant(101, dtype=tf.int64) | |
| SEP_ID = tf.constant(102, dtype=tf.int64) | |
| start_tokens = tf.fill([tf.shape(text)[0], 1], CLS_ID) | |
| end_tokens = tf.fill([tf.shape(text)[0], 1], SEP_ID) | |
| tokens = tokens[:, :sequence_length - 2] | |
| tokens = tf.concat([start_tokens, tokens, end_tokens], axis=1) |
hanneshapke
/ call_berttokenizer.py
Created
March 9, 2020 17:45
This file contains hidden or 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
| tokens = bert_tokenizer.tokenize(text) |
hanneshapke
/ partial_setup_of_berttokenizer_part_3.py
Created
March 9, 2020 16:59
This file contains hidden or 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
| bert_tokenizer = text.BertTokenizer( | |
| vocab_lookup_table=vocab_file_path, | |
| token_out_type=tf.int64, | |
| lower_case=do_lower_case | |
| ) |