Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/brightmart/albert_zh
/ functions
Functions
427 in github.com/brightmart/albert_zh
⨍
Functions
427
◇
Types & classes
49
Function
predict_input_fn
()
similarity.py:242
Function
preprocess_text
preprocess data by removing extra space and normalize data.
tokenization_google.py:86
Function
printable_text
Returns text encoded in a way suitable for print or `tf.logging`.
tokenization.py:98
Function
reshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
modeling_google_fast.py:1133
Function
reshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
bert_utils.py:62
Function
reshape_from_matrix
Reshapes a rank 2 tensor back to its original rank >= 2 tensor.
modeling_google.py:1046
Function
reshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
modeling_google_fast.py:1119
Function
reshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
bert_utils.py:49
Function
reshape_to_matrix
Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).
modeling_google.py:1032
Function
test_factorized_embedding
test of Factorized embedding parameterization :return:
test_changes.py:35
Function
test_share_parameters
test of share parameters across all layers: how many parameter after share parameter across layers of transformer. :return:
test_changes.py:44
Method
to_json_string
Serializes this instance to a JSON string.
modeling_google_fast.py:121
Method
to_json_string
Serializes this instance to a JSON string.
modeling.py:102
Method
to_json_string
Serializes this instance to a JSON string.
modeling_google.py:121
Method
tokenize
Tokenizes a piece of text.
tokenization.py:198
Method
tokenize
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
Method
tokenize
(self, text)
tokenization_google.py:255
Method
tokenize
Tokenizes a piece of text.
tokenization_google.py:293
Method
tokenize
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
Function
tpu_scaffold
()
run_pretraining_google_fast.py:198
Function
tpu_scaffold
()
run_pretraining.py:160
Function
tpu_scaffold
()
run_classifier_clue.py:605
Function
tpu_scaffold
()
run_pretraining_google.py:198
Function
tpu_scaffold
()
run_classifier.py:501
Function
tpu_scaffold
()
run_classifier_sp_google.py:718
Function
validate_case_matches_checkpoint
Checks whether the casing config is consistent with the checkpoint name.
tokenization.py:28
Function
validate_case_matches_checkpoint
Checks whether the casing config is consistent with the checkpoint name.
tokenization_google.py:35
← previous
401–427 of 427, ranked by callers