MCPcopy Create free account

hub / github.com/brightmart/albert_zh / functions

Functions427 in github.com/brightmart/albert_zh

Functionpredict_input_fn
()
similarity.py:242
Functionpreprocess_text
preprocess data by removing extra space and normalize data.
tokenization_google.py:86
Functionprintable_text
Returns text encoded in a way suitable for print or `tf.logging`.
tokenization.py:98
Functionreshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
modeling_google_fast.py:1133
Functionreshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
bert_utils.py:62
Functionreshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
modeling_google.py:1046
Functionreshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
modeling_google_fast.py:1119
Functionreshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
bert_utils.py:49
Functionreshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
modeling_google.py:1032
Functiontest_factorized_embedding
test of Factorized embedding parameterization :return:
test_changes.py:35
Functiontest_share_parameters
test of share parameters across all layers: how many parameter after share parameter across layers of transformer. :return:
test_changes.py:44
Methodto_json_string
Serializes this instance to a JSON string.
modeling_google_fast.py:121
Methodto_json_string
Serializes this instance to a JSON string.
modeling.py:102
Methodto_json_string
Serializes this instance to a JSON string.
modeling_google.py:121
Methodtokenize
Tokenizes a piece of text.
tokenization.py:198
Methodtokenize
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca
tokenization.py:310
Methodtokenize
(self, text)
tokenization_google.py:255
Methodtokenize
Tokenizes a piece of text.
tokenization_google.py:293
Methodtokenize
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca
tokenization_google.py:405
Functiontpu_scaffold
()
run_pretraining_google_fast.py:198
Functiontpu_scaffold
()
run_pretraining.py:160
Functiontpu_scaffold
()
run_classifier_clue.py:605
Functiontpu_scaffold
()
run_pretraining_google.py:198
Functiontpu_scaffold
()
run_classifier.py:501
Functiontpu_scaffold
()
run_classifier_sp_google.py:718
Functionvalidate_case_matches_checkpoint
Checks whether the casing config is consistent with the checkpoint name.
tokenization.py:28
Functionvalidate_case_matches_checkpoint
Checks whether the casing config is consistent with the checkpoint name.
tokenization_google.py:35
← previous401–427 of 427, ranked by callers