MCPcopy Create free account

hub / github.com/Hujiazeng/Vach / functions

Functions977 in github.com/Hujiazeng/Vach

⨍ Functions 977◇ Types & classes 165↳ Endpoints 7
↓ 3 callersMethodtrain
(self, train_loader, valid_loader, max_epochs)
talkers/synctalk/nerf_triplane/utils.py:1014
↓ 3 callersMethodtrain
(self, train_loader, valid_loader, max_epochs)
talkers/er_nerf/nerf_triplane/utils.py:972
↓ 2 callersFunctionI
(t,i,n,a)
web/mpegts-1.7.3.min.js:8
↓ 2 callersFunctionJ
(e)
web/mpegts-1.7.3.min.js:1
↓ 2 callersFunctionP
(e)
web/mpegts-1.7.3.min.js:1
↓ 2 callersFunctionT
()
web/mpegts-1.7.3.min.js:1
↓ 2 callersMethod__attempt_reconnect
(self)
ai_module/ASR/funasr_client.py:62
↓ 2 callersMethod__init__
(self, n_out, kernel=3, normalization=torch.nn.BatchNorm3d, activation=torch.nn.ReLU)
talkers/synctalk/data_utils/UNFaceFlow/core/nnutils.py:67
↓ 2 callersMethod__init__
(self)
talkers/synctalk/data_utils/face_tracking/render_land.py:85
↓ 2 callersMethod__init__
(self)
talkers/er_nerf/data_utils/face_tracking/render_land.py:116
↓ 2 callersMethod__init__
(self, opt)
links/synctalk/synctalk_link.py:407
↓ 2 callersFunction__print_size_warning
(ow, oh, w, h)
talkers/synctalk/data_utils/UNFaceFlow/data_test_flow/base_dataset.py:92
↓ 2 callersFunction__scale_width
(img, target_width)
talkers/synctalk/data_utils/UNFaceFlow/data_test_flow/base_dataset.py:71
↓ 2 callersFunction_amp_to_db
(x)
talkers/er_nerf/data_utils/wav2mel.py:88
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
talkers/synctalk/nerf_triplane/utils.py:93
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
talkers/er_nerf/nerf_triplane/utils.py:87
↓ 2 callersFunction_index_from_letter
(letter: str)
talkers/synctalk/nerf_triplane/utils.py:126
↓ 2 callersFunction_index_from_letter
(letter: str)
talkers/er_nerf/nerf_triplane/utils.py:120
↓ 2 callersFunction_normalize
(S)
talkers/er_nerf/data_utils/wav2mel.py:95
↓ 2 callersFunction_stft
(y)
talkers/er_nerf/data_utils/wav2mel.py:45
↓ 2 callersMethodbackward
(ctx, grad)
talkers/synctalk/gridencoder/grid.py:63
↓ 2 callersMethodbackward
(ctx, grad)
talkers/er_nerf/gridencoder/grid.py:63
↓ 2 callersFunctionblend_with_mask_cuda
(src, dst, mask)
talkers/synctalk/nerf_triplane/utils.py:36
↓ 2 callersFunctioncal_col_loss
(pred_img, gt_img, img_mask)
talkers/er_nerf/data_utils/face_tracking/util.py:103
↓ 2 callersFunctioncal_lap_loss
(tensor_list, weight_list)
talkers/er_nerf/data_utils/face_tracking/util.py:57
↓ 2 callersMethodclear_queue
(self)
talkers/synctalk/nerf_triplane/asr.py:363
↓ 2 callersMethodclear_queue
(self)
talkers/er_nerf/nerf_triplane/asr.py:363
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
talkers/synctalk/data_utils/face_parsing/resnet.py:14
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
talkers/er_nerf/data_utils/face_parsing/resnet.py:14
↓ 2 callersMethoddensity
(self, x, enc_a, e=None, enc_x=None)
talkers/synctalk/nerf_triplane/network.py:366
↓ 2 callersMethoddensity
(self, x, enc_a, e=None, enc_x=None)
talkers/er_nerf/nerf_triplane/network.py:281
↓ 2 callersMethodencode_x
(self, xyz, bound)
talkers/synctalk/nerf_triplane/network.py:297
↓ 2 callersMethodencode_x
(self, xyz, bound)
talkers/er_nerf/nerf_triplane/network.py:212
↓ 2 callersFunctioneuler2rot
(euler_angle)
talkers/synctalk/data_utils/face_tracking/util.py:18
↓ 2 callersFunctioneuler2rot
(euler_angle)
talkers/er_nerf/data_utils/face_tracking/util.py:18
↓ 2 callersMethodevaluate
(self, loader, name=None)
talkers/synctalk/nerf_triplane/utils.py:1037
↓ 2 callersMethodevaluate
(self, loader, name=None)
talkers/er_nerf/nerf_triplane/utils.py:995
↓ 2 callersMethodevaluate_one_epoch
(self, loader, name=None)
talkers/synctalk/nerf_triplane/utils.py:1349
↓ 2 callersMethodevaluate_one_epoch
(self, loader, name=None)
talkers/er_nerf/nerf_triplane/utils.py:1300
↓ 2 callersFunctionextract_audio
Real extract audio from video file. Parameters ---------- in_video : str Path to input video file. out_audio : str
talkers/synctalk/data_utils/deepspeech_features/extract_wav.py:36
↓ 2 callersFunctionextract_audio
Real extract audio from video file. Parameters ---------- in_video : str Path to input video file. out_audio : str
talkers/er_nerf/data_utils/deepspeech_features/extract_wav.py:36
↓ 2 callersFunctionextract_features
Real extract audio from video file. Parameters ---------- in_audios : list of str Paths to input audio files. out_files :
talkers/synctalk/data_utils/deepspeech_features/extract_ds_features.py:46
↓ 2 callersFunctionextract_features
Real extract audio from video file. Parameters ---------- in_audios : list of str Paths to input audio files. out_files :
talkers/er_nerf/data_utils/deepspeech_features/extract_ds_features.py:46
↓ 2 callersFunctionf
(e,t,i)
web/mpegts-1.7.3.min.js:1
↓ 2 callersMethodforward
Estimate optical flow between pair of frames
talkers/synctalk/data_utils/UNFaceFlow/core/raft.py:86
↓ 2 callersMethodforward_geo_sub
(self, id_para, exp_para, sub_index)
talkers/synctalk/data_utils/face_tracking/facemodel.py:40
↓ 2 callersMethodforward_geo_sub
(self, id_para, exp_para, sub_index)
talkers/er_nerf/data_utils/face_tracking/facemodel.py:122
↓ 2 callersMethodforward_tex
(self, tex_para)
talkers/er_nerf/data_utils/face_tracking/facemodel.py:150
↓ 2 callersMethodforward_torso
(self, x, poses, c=None)
talkers/synctalk/nerf_triplane/network.py:252
↓ 2 callersMethodforward_torso
(self, x, poses, c=None)
talkers/er_nerf/nerf_triplane/network.py:167
↓ 2 callersFunctiong
(e,t,i,n)
web/mpegts-1.7.3.min.js:1
↓ 2 callersFunctionget_bg_coords
(H, W, device)
talkers/synctalk/nerf_triplane/utils.py:246
↓ 2 callersMethodget_history_percentage
(self, number)
core/mike.py:79
↓ 2 callersFunctionget_hubert_from_16k_speech
(speech, device="cuda:0")
talkers/synctalk/data_utils/hubert.py:18
↓ 2 callersFunctionget_hubert_from_16k_speech
(speech, device="cuda:0")
talkers/er_nerf/data_utils/hubert.py:18
↓ 2 callersMethodget_next_feat
(self)
links/synctalk/synctalk_link.py:491
↓ 2 callersMethodget_next_feat
(self)
links/er_nerf/er_nerf_link.py:337
↓ 2 callersMethodinitialize
(self)
talkers/synctalk/data_utils/UNFaceFlow/options_test_flow.py:95
↓ 2 callersMethodinitialize
(self, opt)
talkers/synctalk/data_utils/UNFaceFlow/data_test_flow/__init__.py:19
↓ 2 callersMethodlisten
(self)
talkers/synctalk/nerf_triplane/asr.py:117
↓ 2 callersMethodlisten
(self)
talkers/er_nerf/data_utils/wav2vec.py:117
↓ 2 callersMethodlisten
(self)
talkers/er_nerf/nerf_triplane/asr.py:117
↓ 2 callersFunctionm
(e,t)
web/mpegts-1.7.3.min.js:1
↓ 2 callersFunctionmake_conv_2d
(n_in, n_out, n_blocks, kernel=3, normalization=torch.nn.BatchNorm2d, activation=torch.nn.ReLU)
talkers/synctalk/data_utils/UNFaceFlow/core/nnutils.py:18
↓ 2 callersMethodmark_untrained_grid
(self, poses, intrinsic, S=64)
talkers/synctalk/nerf_triplane/renderer.py:354
↓ 2 callersMethodmark_untrained_grid
(self, poses, intrinsic, S=64)
talkers/er_nerf/nerf_triplane/renderer.py:356
↓ 2 callersMethodmeasure
(self)
talkers/synctalk/nerf_triplane/utils.py:473
↓ 2 callersMethodmeasure
(self)
talkers/synctalk/nerf_triplane/utils.py:509
↓ 2 callersMethodmeasure
(self)
talkers/er_nerf/nerf_triplane/utils.py:430
↓ 2 callersMethodmeasure
(self)
talkers/er_nerf/nerf_triplane/utils.py:466
↓ 2 callersFunctionmesh_grid
(B, H, W)
talkers/synctalk/data_utils/UNFaceFlow/core/warp_utils.py:6
↓ 2 callersMethodnew_asrclient
(self)
core/mike.py:49
↓ 2 callersFunctionp
(e)
web/mpegts-1.7.3.min.js:1
↓ 2 callersFunctionpreemphasis
(wav, k, preemphasize=True)
talkers/er_nerf/data_utils/wav2mel.py:12
↓ 2 callersMethodprepare_buffer
(self, outputs)
talkers/synctalk/nerf_triplane/gui.py:161
↓ 2 callersMethodprepare_buffer
(self, outputs)
talkers/er_nerf/nerf_triplane/gui.py:164
↓ 2 callersFunctionpreprocess_render
(geometry, euler, trans, cam, tris, vert_tris, ori_img)
talkers/synctalk/data_utils/face_tracking/render_land.py:45
↓ 2 callersFunctionpreprocess_render
(geometry, euler, trans, cam, tris, vert_tris, ori_img)
talkers/er_nerf/data_utils/face_tracking/render_land.py:45
↓ 2 callersMethodprocess_data
(self, color, mask)
talkers/synctalk/data_utils/UNFaceFlow/data_test_flow/dd_dataset_bak.py:53
↓ 2 callersMethodprocess_data
(self, color, mask)
talkers/synctalk/data_utils/UNFaceFlow/data_test_flow/dd_dataset.py:53
↓ 2 callersMethodpush_audio
(self, byte_stream)
links/er_nerf/er_nerf_link.py:549
↓ 2 callersFunctionquestion
(cont)
ai_module/nlp/nlp_ollama_api.py:7
↓ 2 callersMethodrender_data_submit_track
渲染单帧并提交轨道
links/synctalk/synctalk_link.py:849
↓ 2 callersMethodrender_data_submit_track
渲染单帧并提交轨道
links/er_nerf/er_nerf_link.py:667
↓ 2 callersMethodreport
(self)
talkers/synctalk/nerf_triplane/utils.py:612
↓ 2 callersMethodreport
(self)
talkers/er_nerf/nerf_triplane/utils.py:569
↓ 2 callersMethodreset_parameters
(self)
talkers/synctalk/gridencoder/grid.py:132
↓ 2 callersMethodreset_parameters
(self)
talkers/er_nerf/gridencoder/grid.py:132
↓ 2 callersFunctionrot_trans_pts
(geometry, rot, trans)
talkers/er_nerf/data_utils/face_tracking/util.py:52
↓ 2 callersMethodrun
(self)
talkers/synctalk/nerf_triplane/asr.py:356
↓ 2 callersMethodrun
(self)
talkers/er_nerf/data_utils/wav2vec.py:357
↓ 2 callersMethodrun
(*args)
ai_module/ASR/funasr_client.py:78
↓ 2 callersMethodrun_step
(self)
talkers/er_nerf/data_utils/wav2vec.py:185
↓ 2 callersMethodsay
(self, text, voicename="zh-CN-YunxiaNeural", tts_type="edgetts")
links/er_nerf/er_nerf_link.py:708
↓ 2 callersFunctionset_opt
(opt)
talkers/er_nerf/config.py:4
↓ 2 callersFunctionsrgb_to_linear
(x)
talkers/synctalk/nerf_triplane/utils.py:89
↓ 2 callersFunctionsrgb_to_linear
(x)
talkers/er_nerf/nerf_triplane/utils.py:83
↓ 2 callersMethodstop
(self)
talkers/synctalk/nerf_triplane/asr.py:129
↓ 2 callersMethodstop
(self)
talkers/er_nerf/nerf_triplane/asr.py:129
↓ 2 callersMethodstop
(self)
core/mike.py:45
← previousnext →101–200 of 977, ranked by callers