MCPcopy Create free account

hub / github.com/Rudrabha/Wav2Lip / functions

Functions169 in github.com/Rudrabha/Wav2Lip

⨍ Functions 169◇ Types & classes 23
↓ 5 callersMethodget_detections_for_batch
(self, images)
face_detection/api.py:64
↓ 4 callersMethod__init__
(self, num_modules=1)
face_detection/models.py:147
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1)
face_detection/models.py:229
↓ 4 callersFunctiontransform
Generate and affine transformation matrix. Given a set of points, a center, a scale and a targer resolution, the function generates and affin
face_detection/utils.py:56
↓ 3 callersFunctionconv3x3
3x3 convolution with padding
face_detection/models.py:7
↓ 3 callersMethodget_frame_id
(self, frame)
wav2lip_train.py:44
↓ 3 callersMethodget_frame_id
(self, frame)
hq_wav2lip_train.py:46
↓ 3 callersFunctionget_image_list
(data_root, split)
hparams.py:4
↓ 3 callersFunctionload_checkpoint
(path, model, optimizer, reset_optimizer=False, overwrite_global_states=True)
hq_wav2lip_train.py:375
↓ 2 callersMethod__init__
(self, cin, cout, kernel_size, stride, padding, residual=False, *args, **kwargs)
models/conv.py:6
↓ 2 callersFunction_amp_to_db
(x)
audio.py:103
↓ 2 callersFunction_normalize
(S)
audio.py:110
↓ 2 callersFunction_stft
(y)
audio.py:57
↓ 2 callersFunctioncosine_loss
(a, v, y)
color_syncnet_train.py:134
↓ 2 callersMethodcrop_audio_window
(self, spec, start_frame)
wav2lip_train.py:75
↓ 2 callersMethodcrop_audio_window
(self, spec, start_frame)
hq_wav2lip_train.py:77
↓ 2 callersFunctiondetect
(net, img, device)
face_detection/detection/sfd/detect.py:19
↓ 2 callersMethodevaluate
(self, opt, videofile)
evaluation/scores_LSE/SyncNetInstance_calc_scores.py:42
↓ 2 callersFunctionface_detect
(images)
inference.py:68
↓ 2 callersMethodget_frame_id
(self, frame)
color_syncnet_train.py:41
↓ 2 callersFunctionget_hop_size
()
audio.py:30
↓ 2 callersMethodget_lower_half
(self, face_sequences)
models/wav2lip.py:155
↓ 2 callersFunctionget_sync_loss
(mel, g)
wav2lip_train.py:192
↓ 2 callersFunctionget_sync_loss
(mel, g)
hq_wav2lip_train.py:194
↓ 2 callersMethodget_window
(self, start_frame)
wav2lip_train.py:47
↓ 2 callersMethodget_window
(self, start_frame)
hq_wav2lip_train.py:49
↓ 2 callersMethodloadParameters
(self, path)
evaluation/scores_LSE/SyncNetInstance_calc_scores.py:203
↓ 2 callersFunctionload_checkpoint
(path, model, optimizer, reset_optimizer=False, overwrite_global_states=True)
wav2lip_train.py:316
↓ 2 callersFunctionnms
(dets, thresh)
face_detection/detection/sfd/bbox.py:44
↓ 2 callersMethodperceptual_forward
(self, false_face_sequences)
models/wav2lip.py:163
↓ 2 callersFunctionpreemphasis
(wav, k, preemphasize=True)
audio.py:20
↓ 2 callersMethodprepare_window
(self, window)
wav2lip_train.py:101
↓ 2 callersMethodprepare_window
(self, window)
hq_wav2lip_train.py:103
↓ 2 callersMethodread_window
(self, window_fnames)
wav2lip_train.py:59
↓ 2 callersMethodread_window
(self, window_fnames)
hq_wav2lip_train.py:61
↓ 2 callersFunctionsave_checkpoint
(model, optimizer, step, checkpoint_dir, epoch, prefix='')
hq_wav2lip_train.py:354
↓ 2 callersMethodset_hparam
(self, key, value)
hparams.py:27
↓ 2 callersMethodto_2d
(self, face_sequences)
models/wav2lip.py:158
↓ 1 callersMethod__init__
(self)
face_detection/detection/sfd/net_s3fd.py:23
↓ 1 callersMethod__init__
(self)
models/wav2lip.py:9
↓ 1 callersFunction_build_mel_basis
()
audio.py:98
↓ 1 callersMethod_forward
(self, level, inp)
face_detection/models.py:119
↓ 1 callersFunction_gaussian
( size=3, sigma=0.25, amplitude=1, normalize=False, width=None, height=None, sigma_horz=None,
face_detection/utils.py:11
↓ 1 callersMethod_generate_network
(self, level)
face_detection/models.py:107
↓ 1 callersFunction_linear_to_mel
(spectogram)
audio.py:92
↓ 1 callersFunction_load
(checkpoint_path)
wav2lip_train.py:308
↓ 1 callersFunction_load
(checkpoint_path)
color_syncnet_train.py:221
↓ 1 callersFunction_load
(checkpoint_path)
hq_wav2lip_train.py:366
↓ 1 callersFunction_load
(checkpoint_path)
inference.py:160
↓ 1 callersFunction_load
(checkpoint_path)
evaluation/gen_videos_from_filelist.py:129
↓ 1 callersFunction_load
(checkpoint_path)
evaluation/real_videos_inference.py:176
↓ 1 callersFunction_lws_processor
()
audio.py:53
↓ 1 callersFunctionbatch_decode
Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo
face_detection/detection/sfd/bbox.py:111
↓ 1 callersFunctionbatch_detect
(net, imgs, device)
face_detection/detection/sfd/detect.py:58
↓ 1 callersFunctioncalc_pdist
(feat1, feat2, vshift=10)
evaluation/scores_LSE/SyncNetInstance_calc_scores.py:19
↓ 1 callersFunctioncosine_loss
(a, v, y)
wav2lip_train.py:180
↓ 1 callersFunctioncosine_loss
(a, v, y)
hq_wav2lip_train.py:182
↓ 1 callersMethodcrop_audio_window
(self, spec, start_frame)
color_syncnet_train.py:56
↓ 1 callersFunctiondatagen
(frames, mels)
inference.py:108
↓ 1 callersFunctiondatagen
(frames, face_det_results, mels)
evaluation/gen_videos_from_filelist.py:79
↓ 1 callersFunctiondatagen
(frames, face_det_results, mels)
evaluation/real_videos_inference.py:108
↓ 1 callersFunctiondecode
Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo
face_detection/detection/sfd/bbox.py:91
↓ 1 callersMethoddetect_from_batch
(self, images)
face_detection/detection/sfd/sfd_detector.py:41
↓ 1 callersMethoddetect_from_image
Detects faces in a given image. This function detects the faces present in a provided BGR(usually) image. The input can be either the
face_detection/detection/core.py:32
↓ 1 callersFunctioneval_model
(test_data_loader, global_step, device, model, checkpoint_dir)
wav2lip_train.py:262
↓ 1 callersFunctioneval_model
(test_data_loader, global_step, device, model, checkpoint_dir)
color_syncnet_train.py:181
↓ 1 callersFunctioneval_model
(test_data_loader, global_step, device, model, disc)
hq_wav2lip_train.py:300
↓ 1 callersFunctionface_detect
(images)
evaluation/gen_videos_from_filelist.py:44
↓ 1 callersFunctionface_detect
(images)
evaluation/real_videos_inference.py:73
↓ 1 callersMethodget_segmented_mels
(self, spec, start_frame)
wav2lip_train.py:86
↓ 1 callersMethodget_segmented_mels
(self, spec, start_frame)
hq_wav2lip_train.py:88
↓ 1 callersFunctionget_smoothened_boxes
(boxes, T)
inference.py:59
↓ 1 callersFunctionget_smoothened_boxes
(boxes, T)
evaluation/gen_videos_from_filelist.py:35
↓ 1 callersFunctionget_smoothened_boxes
(boxes, T)
evaluation/real_videos_inference.py:42
↓ 1 callersMethodget_window
(self, start_frame)
color_syncnet_train.py:44
↓ 1 callersFunctionincrease_frames
(frames, l)
evaluation/real_videos_inference.py:149
↓ 1 callersFunctionload_checkpoint
(path, model, optimizer, reset_optimizer=False)
color_syncnet_train.py:229
↓ 1 callersFunctionload_model
(path)
inference.py:168
↓ 1 callersFunctionload_model
(path)
evaluation/gen_videos_from_filelist.py:137
↓ 1 callersFunctionload_model
(path)
evaluation/real_videos_inference.py:184
↓ 1 callersFunctionmain
(args)
preprocess.py:91
↓ 1 callersFunctionmain
()
inference.py:181
↓ 1 callersFunctionmain
()
evaluation/gen_videos_from_filelist.py:152
↓ 1 callersFunctionmain
()
evaluation/real_videos_inference.py:199
↓ 1 callersFunctionnum_frames
Compute number of time frames of spectrogram
audio.py:65
↓ 1 callersFunctionprocess_audio_file
(vfile, args)
preprocess.py:69
↓ 1 callersFunctionprocess_video_file
(vfile, args, gpu_id)
preprocess.py:38
↓ 1 callersFunctionrescale_frames
(images)
evaluation/real_videos_inference.py:51
↓ 1 callersFunctionsave_checkpoint
(model, optimizer, step, checkpoint_dir, epoch)
wav2lip_train.py:294
↓ 1 callersFunctionsave_checkpoint
(model, optimizer, step, checkpoint_dir, epoch)
color_syncnet_train.py:208
↓ 1 callersFunctionsave_sample_images
(x, g, gt, global_step, checkpoint_dir)
wav2lip_train.py:166
↓ 1 callersFunctionsave_sample_images
(x, g, gt, global_step, checkpoint_dir)
hq_wav2lip_train.py:168
↓ 1 callersFunctionshuffle_lr
Shuffle the points left-right according to the axis of symmetry of the object. Arguments: parts {torch.tensor} -- a 3D or 4D object c
face_detection/utils.py:212
↓ 1 callersMethodtensor_or_path_to_ndarray
Convert path (represented as a string) or torch.tensor to a numpy.ndarray Arguments: tensor_or_path {numpy.ndarray, torch.tensor
face_detection/detection/core.py:116
↓ 1 callersFunctiontrain
(device, model, train_data_loader, test_data_loader, optimizer, checkpoint_dir=None, checkpoint_inte
wav2lip_train.py:200
↓ 1 callersFunctiontrain
(device, model, train_data_loader, test_data_loader, optimizer, checkpoint_dir=None, checkpoint_inte
color_syncnet_train.py:140
↓ 1 callersFunctiontrain
(device, model, disc, train_data_loader, test_data_loader, optimizer, disc_optimizer, checkpoint_dir
hq_wav2lip_train.py:202
FunctionIOU
(ax1, ay1, ax2, ay2, bx1, by1, bx2, by2)
face_detection/detection/sfd/bbox.py:17
Method__getattr__
(self, key)
hparams.py:22
Method__getitem__
(self, idx)
wav2lip_train.py:111
next →1–100 of 169, ranked by callers