Functions — github.com/SiavashShams/ssamba

hub / github.com/SiavashShams/ssamba / functions

Functions171 in github.com/SiavashShams/ssamba

⨍ Functions 171◇ Types & classes 17

↓ 27 callersMethodupdate

(self, val, n=1)

src/utilities/util.py:249

↓ 15 callersMethodreset

(self)

src/utilities/util.py:243

↓ 6 callersFunctionvalidate

(audio_model, val_loader, args, epoch)

src/traintest.py:312

↓ 5 callersFunctiond_prime

(auc)

src/utilities/stats.py:6

↓ 4 callersFunctioncomputeMatchmap

(I, A)

src/utilities/util.py:69

↓ 4 callersFunctionmatchmapSim

(M, simtype)

src/utilities/util.py:81

↓ 3 callersFunctionwalk

(path, name)

src/prep_data/librispeech/prep_librispeech.py:6

↓ 2 callersMethod__init__

(self, label_dim=527, fshape=128, tshape=2, fstride=128, tstride=2, input_fd

src/models/both_models.py:726

↓ 2 callersMethod__init__

( self, label_dim=527, fshape=128, tshape=2, fstride=128, tstr

src/finetune/voxceleb1/ssast/ast_models.py:82

↓ 2 callersMethod__init__

( self, label_dim=527, fshape=128, tshape=2, fstride=128, tstr

src/finetune/iemocap/ssast/ast_models.py:82

↓ 2 callersFunction_print

(msg)

src/utilities/util.py:285

↓ 2 callersMethod_wav2fbank

(self, filename, filename2=None)

src/dataloader.py:99

↓ 2 callersFunctionbasic_get_imposter_indices

(N)

src/utilities/util.py:169

↓ 2 callersFunctioncalculate_stats

Calculate statistics including mAP, AUC, etc. Args: output: 2d array, (samples_num, classes_num) target: 2d array, (samples_num, clas

src/utilities/stats.py:11

↓ 2 callersFunctioncreate_json

(directory, output_filename)

src/prep_data/prep_audioset.py:11

↓ 2 callersMethodgen_maskid_frame

(self, sequence_len=512, mask_size=100)

src/models/both_models.py:278

↓ 2 callersMethodgen_maskid_frame

(self, sequence_len=512, mask_size=100)

src/models/both_models.py:911

↓ 2 callersMethodgen_maskid_frame

(self, sequence_len=512, mask_size=100)

src/finetune/voxceleb1/ssast/ast_models.py:650

↓ 2 callersMethodgen_maskid_frame

(self, sequence_len=512, mask_size=100)

src/finetune/iemocap/ssast/ast_models.py:650

↓ 2 callersMethodgen_maskid_patch

(self, sequence_len=512, mask_size=100, cluster=3)

src/models/both_models.py:254

↓ 2 callersMethodgen_maskid_patch

(self, sequence_len=512, mask_size=100, cluster=3)

src/models/both_models.py:887

↓ 2 callersMethodgen_maskid_patch

(self, sequence_len=512, mask_size=100, cluster=3)

src/finetune/voxceleb1/ssast/ast_models.py:626

↓ 2 callersMethodgen_maskid_patch

(self, sequence_len=512, mask_size=100, cluster=3)

src/finetune/iemocap/ssast/ast_models.py:626

↓ 2 callersFunctionget_immediate_files

(a_dir)

src/prep_data/esc50/prep_esc50.py:13

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/models/both_models.py:245

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/models/both_models.py:878

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/finetune/voxceleb1/ssast/ast_models.py:374

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/finetune/voxceleb1/ssast/ast_models.py:617

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/finetune/iemocap/ssast/ast_models.py:374

↓ 2 callersMethodget_shape

(self, fstride, tstride, input_fdim, input_tdim, fshape, tshape)

src/finetune/iemocap/ssast/ast_models.py:617

↓ 2 callersMethodmpc

(self, x, mask_patch, cluster, show_mask=False)

src/models/both_models.py:467

↓ 2 callersMethodmpc

(self, x, mask_patch, cluster, show_mask=False)

src/models/both_models.py:987

↓ 2 callersFunctiontrain

(audio_model, train_loader, test_loader, args)

src/traintest.py:18

↓ 2 callersFunctiontrainmask

(audio_model, train_loader, test_loader, args)

src/traintest_mask.py:14

↓ 1 callersMethod__init__

(self, mode="global", dim=2, eps=1e-10)

src/finetune/voxceleb1/ssast/audio.py:28

↓ 1 callersMethod__init__

(self, mode="global", dim=2, eps=1e-10)

src/finetune/iemocap/ssast/audio.py:28

↓ 1 callersFunction_save_progress

()

src/traintest.py:37

↓ 1 callersFunction_save_progress

()

src/traintest_mask.py:33

↓ 1 callersFunctioncombine_json

(file_list, name='audioset_librispeech960')

src/prep_data/mix_pretraining_data.py:13

↓ 1 callersFunctioncombine_json

(file_list, name='librispeech_tr960')

src/prep_data/librispeech/prep_librispeech.py:35

↓ 1 callersFunctionconcatenate_audios

(fold, audio_base_path, desired_length, segment_duration)

src/prep_data/urban8k/prep_urban8k.py:22

↓ 1 callersMethodfinetuningavgtok

(self, x)

src/models/both_models.py:335

↓ 1 callersMethodfinetuningavgtok

(self, x)

src/models/both_models.py:939

↓ 1 callersMethodfinetuningavgtok_1sec

(self, x)

src/models/both_models.py:282

↓ 1 callersMethodfinetuningavgtok_1sec

(self, x)

src/models/both_models.py:915

↓ 1 callersMethodfinetuningcls

(self, x)

src/models/both_models.py:398

↓ 1 callersMethodfinetuningcls

(self, x)

src/models/both_models.py:961

↓ 1 callersMethodget_downsample_rates

(self, key: str = None)

src/finetune/voxceleb1/ssast/expert.py:121

↓ 1 callersMethodget_downsample_rates

(self, key: str = None)

src/finetune/iemocap/ssast/expert.py:121

↓ 1 callersFunctionget_immediate_files

(a_dir)

src/finetune/speechcommands_v1/prep_sc.py:38

↓ 1 callersFunctionget_immediate_files

(a_dir)

src/finetune/speechcommands_v2/prep_sc.py:38

↓ 1 callersFunctionget_immediate_files

(a_dir)

src/finetune/esc50/prep_esc50.py:35

↓ 1 callersFunctionget_immediate_subdirectories

(a_dir)

src/finetune/speechcommands_v1/prep_sc.py:36

↓ 1 callersFunctionget_immediate_subdirectories

(a_dir)

src/finetune/speechcommands_v2/prep_sc.py:36

↓ 1 callersFunctionget_position_angle_vec

(position)

src/models/both_models.py:54

↓ 1 callersFunctionget_position_angle_vec

(position)

src/finetune/voxceleb1/ssast/ast_models.py:66

↓ 1 callersFunctionget_position_angle_vec

(position)

src/finetune/iemocap/ssast/ast_models.py:66

↓ 1 callersFunctionmake_index_dict

(label_csv)

src/dataloader.py:23

↓ 1 callersFunctionmake_name_dict

(label_csv)

src/dataloader.py:33

↓ 1 callersMethodmpg

(self, input, mask_patch, cluster)

src/models/both_models.py:608

↓ 1 callersMethodmpg

(self, input, mask_patch, cluster)

src/models/both_models.py:1087

↓ 1 callersFunctionone_imposter_index

(i, N)

src/utilities/util.py:163

↓ 1 callersFunctionpreprocess_audio_files

(directory)

src/prep_data/preprocess_audioset.py:11

↓ 1 callersFunctionpreprocess_librispeech

(input_directories, output_base_directory)

src/prep_data/preprocess_librispeech.py:40

↓ 1 callersFunctionprocess_audio_file

(input_filepath, output_directory, processed_files_log, error_files_log)

src/prep_data/preprocess_librispeech.py:10

↓ 1 callersFunctionremove_error_files

(log_file_path)

src/prep_data/prep_audioset.py:22

↓ 1 callersFunctionvalidate_ensemble

(args, epoch)

src/traintest.py:362

↓ 1 callersFunctionvalidate_wa

(audio_model, val_loader, args, start_epoch, end_epoch)

src/traintest.py:380

↓ 1 callersFunctionvalidatemask

(audio_model, val_loader, args, epoch)

src/traintest_mask.py:202

Method__getitem__

returns: image, audio, nframes where image is a FloatTensor of size (3, H, W) audio is a FloatTensor of size (N_freq, N_frame

src/dataloader.py:155

Method__init__

Dataset that manages audio recordings :param audio_conf: Dictionary containing the audio loading and preprocessing settings :

src/dataloader.py:59

Method__init__

(self)

src/utilities/util.py:240

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

src/models/both_models.py:36

Method__init__

(self, label_dim=527, fshape=128, tshape=2, fstride=128, tstride=2, input_fd

src/models/both_models.py:64

Method__init__

( self, ckpt: str, model_size: str, window_secs: float = 1.0, )

src/finetune/voxceleb1/ssast/expert.py:24

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

src/finetune/voxceleb1/ssast/ast_models.py:45

Method__init__

(self, label_dim=527, fshape=128, tshape=2, fstride=128, tstride=2, input_fd

src/finetune/voxceleb1/ssast/ast_models.py:430

Method__init__

( self, mode="fbank", num_mel_bins=128, decode_wav=False, apply_cmvn=F

src/finetune/voxceleb1/ssast/audio.py:56

Method__init__

( self, ckpt: str, model_size: str, window_secs: float = 1.0, )

src/finetune/iemocap/ssast/expert.py:24

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

src/finetune/iemocap/ssast/ast_models.py:45

Method__init__

(self, label_dim=527, fshape=128, tshape=2, fstride=128, tstride=2, input_fd

src/finetune/iemocap/ssast/ast_models.py:430

Method__init__

( self, mode="fbank", num_mel_bins=128, decode_wav=False, apply_cmvn=F

src/finetune/iemocap/ssast/audio.py:56

Method__len__

(self)

src/dataloader.py:220

Method_load_file

(self, filepath)

src/finetune/voxceleb1/ssast/audio.py:81

Method_load_file

(self, filepath)

src/finetune/iemocap/ssast/audio.py:81

Functionadjust_learning_rate

Sets the learning rate to the initial LR decayed by 10 every lr_decay epochs

src/utilities/util.py:255

Functionadjust_learning_rate2

Sets the learning rate to the initial LR decayed by 10 every lr_decay epochs

src/utilities/util.py:262

Functionamba_patch250_base

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:68

Functionamba_patch250_base

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:68

Functionamba_patch250_small

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:81

Functionamba_patch250_small

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:81

Functionamba_patch250_tiny

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:94

Functionamba_patch250_tiny

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:94

Functionamba_patch300_base

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:72

Functionamba_patch300_base

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:72

Functionamba_patch300_small

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:85

Functionamba_patch300_small

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:85

Functionamba_patch300_tiny

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:98

Functionamba_patch300_tiny

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/iemocap/ssast/hubconf.py:98

Functionamba_patch400_base

(refresh: bool = False, window_secs: float = 10.0, **kwargs)

src/finetune/voxceleb1/ssast/hubconf.py:76

next →1–100 of 171, ranked by callers