MCPcopy Create free account

hub / github.com/dayu11/Differentially-Private-Deep-Learning / functions

Functions3,168 in github.com/dayu11/Differentially-Private-Deep-Learning

⨍ Functions 3,168◇ Types & classes 374
↓ 2 callersFunctionbase_lm_architecture
(args)
language/bert/bert_code/fairseq/models/lightconv_lm.py:134
↓ 2 callersFunctionbase_multilingual_architecture
(args)
language/bert/bert_code/fairseq/models/multilingual_transformer.py:178
↓ 2 callersMethodbinarize
(filename, dict, consumer, tokenize=tokenize_line, append_eos=True, reverse_order=False, offs
language/bert/bert_code/fairseq/binarizer.py:25
↓ 2 callersMethodbinarize_alignments
(filename, alignment_parser, consumer, offset=0, end=-1)
language/bert/bert_code/fairseq/binarizer.py:56
↓ 2 callersFunctionbleu_hash
language/bert/bert_code/fairseq/clib/libbleu/libbleu.cpp:55
↓ 2 callersFunctionbleu_trim
left and right trim
language/bert/bert_code/fairseq/clib/libbleu/libbleu.cpp:50
↓ 2 callersMethodbrevity
(self)
language/bert/bert_code/fairseq/bleu.py:116
↓ 2 callersMethodbuild_criterion
Build the :class:`~fairseq.criterions.FairseqCriterion` instance for this task. Args: args (argparse.Namespace):
language/bert/bert_code/fairseq/tasks/fairseq_task.py:182
↓ 2 callersMethodbuild_dataset_for_inference
(self, src_tokens, src_lengths, sort=True)
language/bert/bert_code/fairseq/tasks/mcbert.py:179
↓ 2 callersMethodcdf
(self, t)
language/bert/prv_accountant/prv_accountant/privacy_random_variables.py:69
↓ 2 callersMethodcheck_index
(self, i)
language/bert/bert_code/fairseq/data/indexed_dataset.py:140
↓ 2 callersMethodcheck_index
(self, i)
language/bert/bert_code/fairseq/data/indexed_dataset.py:255
↓ 2 callersFunctioncheckpoint_paths
Retrieves all checkpoints found in `path` directory. Checkpoints are identified by matching filename to the specified pattern. If the pattern
language/bert/bert_code/fairseq/checkpoint_utils.py:180
↓ 2 callersFunctionclean
(text)
language/bert/bert_code/fairseq/models/roberta/alignment_utils.py:26
↓ 2 callersFunctionclean
(text)
language/bert/bert_code/fairseq/models/mcbert/alignment_utils.py:26
↓ 2 callersFunctionclean
(text)
language/bert/bert_code/fairseq/models/electra/alignment_utils.py:26
↓ 2 callersFunctionclip_column
(tsr, clip=1.0, inplace=True)
vision/GEP/models/basis_matching.py:31
↓ 2 callersMethodcls
Helper to get index of cls symbol
language/bert/bert_code/fairseq/data/legacy/masked_lm_dictionary.py:52
↓ 2 callersFunctioncode
(dtype)
language/bert/bert_code/fairseq/data/indexed_dataset.py:95
↓ 2 callersMethodcompute_checkpoint
(self, word_index)
language/bert/bert_code/fairseq/modules/sparse_multihead_attention.py:37
↓ 2 callersFunctioncompute_cross_entropy_loss
Function to compute the cross entropy loss. The default value of ignore_index is the same as the default value for F.cross_entropy in pyt
language/bert/bert_code/fairseq/criterions/legacy_masked_lm.py:15
↓ 2 callersMethodcompute_delta
(self, f_n: DiscretePrivacyRandomVariable, epsilon: float)
language/bert/prv_accountant/prv_accountant/accountant.py:92
↓ 2 callersMethodcompute_epsilon
(self, num_compositions: int)
language/bert/prv_accountant/prv_accountant/other_accountants.py:38
↓ 2 callersFunctioncompute_rdp
Compute RDP of the Sampled Gaussian Mechanism. Args: q: The sampling rate. noise_multiplier: The ratio of the standard deviation of the Gaus
language/bert/bert_code/privacy_tools/rdp_accountant.py:231
↓ 2 callersFunctioncompute_rdp
Compute RDP of the Sampled Gaussian Mechanism. Args: q: The sampling rate. noise_multiplier: The ratio of the standard deviation of the G
vision/RGP/rdp_accountant.py:231
↓ 2 callersMethodcompute_subset_summaries
(self, absolute_max)
language/bert/bert_code/fairseq/modules/sparse_multihead_attention.py:48
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
vision/RGP/models/resnet_cifar.py:10
↓ 2 callersFunctioncopy_strided_to_strided
language/bert/bert_code/fairseq/data/token_block_utils_fast.cpp:18768
↓ 2 callersFunctioncopy_strided_to_strided
language/bert/bert_code/fairseq/data/data_utils_fast.cpp:16331
↓ 2 callersMethoddecode
(self, tokens: torch.LongTensor)
language/bert/bert_code/fairseq/hub_utils.py:150
↓ 2 callersMethoddecode
(self, tokens: torch.LongTensor)
language/bert/bert_code/fairseq/models/roberta/hub_interface.py:64
↓ 2 callersMethoddecode
(self, tokens: torch.LongTensor)
language/bert/bert_code/fairseq/models/mcbert/hub_interface.py:64
↓ 2 callersMethoddecode
(self, tokens: torch.LongTensor)
language/bert/bert_code/fairseq/models/electra/hub_interface.py:64
↓ 2 callersFunctiondeprecation_warning
(message, stacklevel=3)
language/bert/bert_code/fairseq/utils.py:311
↓ 2 callersFunctiondest_path
(prefix, lang)
language/bert/bert_code/preprocess.py:41
↓ 2 callersMethoddetokenize
(self, sentence: str)
language/bert/bert_code/fairseq/hub_utils.py:160
↓ 2 callersFunctiondropSpans
Drop from text the blocks identified in :param spans:, possibly nested.
language/bert/bert_code/preprocess/pretrain/WikiExtractor.py:2036
↓ 2 callersMethodencode
BPE-encode a sentence (or multiple sentences). Every sequence begins with a beginning-of-sentence (`<s>`) symbol. Every sent
language/bert/bert_code/fairseq/models/roberta/hub_interface.py:36
↓ 2 callersMethodencode
BPE-encode a sentence (or multiple sentences). Every sequence begins with a beginning-of-sentence (`<s>`) symbol. Every sent
language/bert/bert_code/fairseq/models/electra/hub_interface.py:36
↓ 2 callersFunctionextend_conv_spec
Extends convolutional spec that is a list of tuples of 2 or 3 parameters (kernel size, dim size and optionally how many layers behind to look
language/bert/bert_code/fairseq/models/fconv.py:544
↓ 2 callersMethodextract
:param out: a memory file.
language/bert/bert_code/preprocess/pretrain/WikiExtractor.py:548
↓ 2 callersMethodextract_features
Similar to *forward* but only return features.
language/bert/bert_code/fairseq/models/fairseq_model.py:53
↓ 2 callersMethodextract_features
(self, tokens: torch.LongTensor, return_all_hiddens: bool = False)
language/bert/bert_code/fairseq/models/roberta/hub_interface.py:77
↓ 2 callersMethodextract_features
(self, tokens: torch.LongTensor, return_all_hiddens: bool = False)
language/bert/bert_code/fairseq/models/mcbert/hub_interface.py:77
↓ 2 callersMethodextract_features
(self, src_tokens, return_all_hiddens=False, padding_mask=None, **unused)
language/bert/bert_code/fairseq/models/mcbert/model.py:354
↓ 2 callersMethodextract_features
(self, tokens: torch.LongTensor, return_all_hiddens: bool = False)
language/bert/bert_code/fairseq/models/electra/hub_interface.py:77
↓ 2 callersFunctionfile_name
(prefix, lang)
language/bert/bert_code/preprocess.py:35
↓ 2 callersFunctionfind_maxp
language/bert/bert_code/fastbpe/fastBPE/fastBPE.hpp:294
↓ 2 callersFunctionformat_stat
(stat)
language/bert/bert_code/fairseq/progress_bar.py:55
↓ 2 callersMethodforward_encoder
(self, encoder_input)
language/bert/bert_code/fairseq/sequence_generator.py:537
↓ 2 callersMethodforward_mask_ins
(self, prev_output_tokens, encoder_out=None)
language/bert/bert_code/fairseq/models/levenshtein_transformer.py:515
↓ 2 callersMethodforward_word_del
(self, prev_output_tokens, encoder_out=None)
language/bert/bert_code/fairseq/models/levenshtein_transformer.py:528
↓ 2 callersMethodforward_word_ins
(self, prev_output_tokens, encoder_out=None)
language/bert/bert_code/fairseq/models/insertion_transformer.py:209
↓ 2 callersMethodforward_word_ins
(self, prev_output_tokens, encoder_out=None)
language/bert/bert_code/fairseq/models/levenshtein_transformer.py:522
↓ 2 callersFunctionfullyQualifiedTemplateTitle
Determine the namespace of the page being included through the template mechanism
language/bert/bert_code/preprocess/pretrain/WikiExtractor.py:1646
↓ 2 callersFunctionget_available_dataset_impl
()
language/bert/bert_code/fairseq/data/indexed_dataset.py:24
↓ 2 callersFunctionget_data_loader
(dataset, batchsize)
vision/GEP/utils.py:14
↓ 2 callersFunctionget_data_loader
(dataset, batchsize)
vision/DP-SGD/utils.py:33
↓ 2 callersMethodget_decoder_langtok
(self, tgt_lang)
language/bert/bert_code/fairseq/tasks/multilingual_translation.py:166
↓ 2 callersMethodget_embedding
Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3
language/bert/bert_code/fairseq/modules/sinusoidal_positional_embedding.py:37
↓ 2 callersMethodget_lr
Get the current learning rate.
language/bert/bert_code/fairseq/trainer.py:696
↓ 2 callersMethodget_normalized_probs
(self, net_output, log_probs, sample=None)
language/bert/bert_code/fairseq/criterions/composite_loss.py:49
↓ 2 callersMethodget_original_text
(self, i)
language/bert/bert_code/fairseq/data/indexed_dataset.py:264
↓ 2 callersFunctionget_pairs
Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).
language/bert/bert_code/fairseq/data/encoders/gpt2_bpe_utils.py:34
↓ 2 callersFunctionget_token_to_word_mapping
(tokens, exclude_list)
language/bert/bert_code/fairseq/utils.py:389
↓ 2 callersFunctionget_training_stats
(trainer)
language/bert/bert_code/train.py:193
↓ 2 callersMethodgrad_denom
(self, sample_sizes, criterion)
language/bert/bert_code/fairseq/tasks/fairseq_task.py:267
↓ 2 callersMethodhas_next
Whether the iterator has been exhausted.
language/bert/bert_code/fairseq/data/iterators.py:45
↓ 2 callersMethodhas_overflow
(grad_norm)
language/bert/bert_code/fairseq/optim/fp16_optimizer.py:50
↓ 2 callersFunctionignoreTag
(tag)
language/bert/bert_code/preprocess/pretrain/WikiExtractor.py:319
↓ 2 callersFunctioninfer_conv_output_dim
(conv_op, input_dim, sample_inchannel)
language/bert/bert_code/fairseq/modules/vggblock.py:22
↓ 2 callersMethodinject_noise
(self, target_tokens)
language/bert/bert_code/fairseq/tasks/translation_lev.py:53
↓ 2 callersFunctionlightconv_wmt_en_de_big
(args)
language/bert/bert_code/fairseq/models/lightconv.py:734
↓ 2 callersMethodload_checkpoint
Load all training state from a checkpoint file.
language/bert/bert_code/fairseq/trainer.py:209
↓ 2 callersFunctionload_checkpoint_to_cpu
Loads a checkpoint to CPU (with upgrading for backward compatibility).
language/bert/bert_code/fairseq/checkpoint_utils.py:134
↓ 2 callersMethodload_dictionary
Load the dictionary from the filename Args: filename (str): the filename
language/bert/bert_code/fairseq/tasks/sentence_prediction.py:61
↓ 2 callersMethodload_state_dict
Copies parameters and buffers from *state_dict* into this module and its descendants. Overrides the method in :class:`nn.Module`. Com
language/bert/bert_code/fairseq/models/fairseq_model.py:61
↓ 2 callersMethodlr_step_update
Update the learning rate after each update.
language/bert/bert_code/fairseq/trainer.py:692
↓ 2 callersFunctionmain
(args, init_distributed=False)
language/bert/bert_code/train.py:23
↓ 2 callersFunctionmake_all
(lang, vocab)
language/bert/bert_code/preprocess.py:225
↓ 2 callersMethodmake_dataset
(type, dictionary)
language/bert/bert_code/fairseq/tasks/sentence_ranking.py:89
↓ 2 callersMethodmax_positions
Maximum output length supported by the encoder.
language/bert/bert_code/fairseq/models/roberta/model.py:331
↓ 2 callersMethodmax_positions
Maximum output length supported by the encoder.
language/bert/bert_code/fairseq/models/mcbert/model.py:367
↓ 2 callersMethodmax_positions
Maximum output length supported by the encoder.
language/bert/bert_code/fairseq/models/electra/model.py:413
↓ 2 callersMethodmerge_file_
(self, another_file)
language/bert/bert_code/fairseq/data/indexed_dataset.py:312
↓ 2 callersMethodmultiply_grads
Multiplies grads by a constant ``c``.
language/bert/bert_code/fairseq/optim/fp16_optimizer.py:121
↓ 2 callersFunctionnorm_block
(is_layer_norm, dim, affine=True)
language/bert/bert_code/fairseq/models/wav2vec.py:244
↓ 2 callersFunctionnormalizeNamespace
(ns)
language/bert/bert_code/preprocess/pretrain/WikiExtractor.py:1679
↓ 2 callersFunctionone_point
(prefix, folder, name, ckp, keyword, metric, agg_fun, miss_dict)
language/bert/bert_code/get_log.py:63
↓ 2 callersFunctiononeminus_beta
(t)
language/bert/prv_accountant/tests/test_privacy_random_variables.py:21
↓ 2 callersFunctionorthogonalize
(matrix)
language/bert/bert_code/fairseq/lrk_utils.py:15
↓ 2 callersFunctionorthogonalize
(matrix)
vision/RGP/models/resnet_cifar.py:27
↓ 2 callersFunctionoutput_or_count
language/bert/bert_code/fastbpe/fastBPE/fastBPE.hpp:96
↓ 2 callersMethodpdf
(self, t)
language/bert/prv_accountant/prv_accountant/privacy_random_variables.py:31
↓ 2 callersMethodprecision
(self)
language/bert/bert_code/fairseq/bleu.py:105
↓ 2 callersMethodprepare
(cls, args, **kargs)
language/bert/bert_code/fairseq/tasks/multilingual_translation.py:123
↓ 2 callersFunctionprintUsage
language/bert/bert_code/fastbpe/fastBPE/main.cc:6
↓ 2 callersFunctionprocess_bpe
language/bert/bert_code/fastbpe/fastBPE/fastBPE.hpp:559
↓ 2 callersFunctionreadCodes
language/bert/bert_code/fastbpe/fastBPE/fastBPE.hpp:479
↓ 2 callersFunctionreadVocab
language/bert/bert_code/fastbpe/fastBPE/fastBPE.hpp:457
← previousnext →501–600 of 3,168, ranked by callers