Functions — github.com/antgroup/echomimic_v2

CodeHub MCPcopy Create free account

hub / github.com/antgroup/echomimic_v2 / functions

Functions395 in github.com/antgroup/echomimic_v2

⨍ Functions 395◇ Types & classes 84

( self, hidden_states, temb=None, encoder_hidden_states=None, audio_co

src/models/unet_3d_blocks.py:269

( self, hidden_states, temb=None, encoder_hidden_states=None, audio_co

src/models/unet_3d_blocks.py:400

(self, hidden_states, temb=None, encoder_hidden_states=None)

src/models/unet_3d_blocks.py:545

( self, hidden_states, res_hidden_states_tuple, temb=None, encoder_hid

src/models/unet_3d_blocks.py:687

( self, hidden_states, res_hidden_states_tuple, temb=None, upsample_si

src/models/unet_3d_blocks.py:824

(self, conditioning)

src/models/pose_guider.py:47

r""" Args: sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor timestep (`torch.FloatTen

src/models/unet_3d_emo.py:397

src/models/resnet.py:10

src/models/resnet.py:21

(self, hidden_states, output_size=None)

src/models/resnet.py:53

(self, hidden_states)

src/models/resnet.py:112

(self, input_tensor, temb)

src/models/resnet.py:217

( self, input_tensor, temb, encoder_hidden_states, attention_mask=None

src/models/motion_module.py:77

(self, hidden_states, encoder_hidden_states=None, attention_mask=None)

src/models/motion_module.py:146

( self, hidden_states, encoder_hidden_states=None, attention_mask=None,

src/models/motion_module.py:237

src/models/motion_module.py:276

( self, hidden_states, encoder_hidden_states=None, attention_mask=None,

src/models/motion_module.py:352

( self, hidden_states, encoder_hidden_states=None, attention_mask=None,

src/models/motion_module.py:463

(self, x: Tensor)

src/models/whisper/whisper/model.py:30

( self, x: Tensor, xa: Optional[Tensor] = None, mask: Optional[Tensor] = None,

src/models/whisper/whisper/model.py:66

( self, x: Tensor, xa: Optional[Tensor] = None, mask: Optional[Tensor] = None,

src/models/whisper/whisper/model.py:117

x : torch.Tensor, shape = (batch_size, n_mels, n_ctx) the mel spectrogram of the audio include_embeddings: bool

src/models/whisper/whisper/model.py:143

x : torch.LongTensor, shape = (batch_size, <= n_ctx) the text tokens xa : torch.Tensor, shape = (batch_size, n_mels, n_au

src/models/whisper/whisper/model.py:189

(self, mel: torch.Tensor, tokens: torch.Tensor)

src/models/whisper/whisper/model.py:245

Methodframes_to_face_regions

(self, frames, toPIL=True)

src/utils/util_emo.py:35

Methodfrom_pretrained_2d

( cls, pretrained_model_path: PathLike, motion_module_path: PathLike, subfolde

src/models/unet_3d_emo.py:583

Functiongenerate

(image_input, audio_input, pose_input, width, height,

Functiongenerate

(image_input, audio_input, pose_input, width, height, length, steps, sample_rate, cfg, fps, context_frames, co

Functionget_down_block

( down_block_type, num_layers, in_channels, out_channels, temb_channels, add_downsampl

src/models/unet_3d_blocks.py:15

Functionget_fps

src/utils/util.py:140

Functionget_image_pose

process image pose Args: ref_image (np.ndarray): reference image pixel value Returns: np.ndarray: pose visual image in RGB-m

src/models/dwpose/preprocess.py:61

Methodget_sliced_feature_sparse

Get sliced features based on a given index :param feature_array: :param start_idx: the start index of the feature :p

src/models/whisper/audio2feature.py:48

Functionget_timestep_list_wrt_margin_and_nsteps

(timestep, margin, total_steps)

src/pipelines/step_func.py:10

Functionget_total_steps

( scheduler, timesteps: List[int], num_steps: Optional[int] = None, num_frames: int = ...,

src/pipelines/context.py:52

Functionget_up_block

( up_block_type, num_layers, in_channels, out_channels, prev_output_channel, temb_chan

src/models/unet_3d_blocks.py:94

Functionget_video_pose

( video_path: str, sample_stride: int=1, max_frame=None)

src/models/dwpose/preprocess.py:75

Functionget_video_pose_with_refimg

preprocess ref image pose and video pose Args: video_path (str): video pose path ref_image (np.ndarray): reference image

src/models/dwpose/preprocess.py:9

Methodhacked_basic_transformer_inner_forward

( self, hidden_states: torch.FloatTensor, attention_mask: Optional[torch.F

src/models/mutual_self_attention.py:93

Functionimport_filename

src/utils/util.py:27

Methodinstall_hooks

(layer: nn.Module)

src/models/whisper/whisper/model.py:280

Methodis_multilingual

src/models/whisper/whisper/model.py:253

Methodlanguage_token

Returns the token id corresponding to the value of the `language` field

src/models/whisper/whisper/tokenizer.py:196

src/pipelines/utils.py:15

(self, tokens: Tensor, audio_features: Tensor, include_embeddings=False)

src/models/whisper/whisper/decoding.py:139

(self, tokens: torch.Tensor, audio_features: torch.Tensor)

src/models/whisper/whisper/model.py:242

Functionmotion_sync

(sequence_driver_det, reference_det, per_landmark_align=True)

src/utils/motion_utils.py:135

Methodno_speech

src/models/whisper/whisper/tokenizer.py:181

Methodno_timestamps

src/models/whisper/whisper/tokenizer.py:186

Methodnon_speech_tokens

Returns the list of tokens to suppress in order to avoid any speaker tags or non-speech annotations, to prevent sampling texts that a

src/models/whisper/whisper/tokenizer.py:237

Functionold_motion_sync_old

(sequence_driver_det, reference_det)

src/utils/motion_utils.py:88

Functionoptional_float

src/models/whisper/whisper/utils.py:22

Functionoptional_int

src/models/whisper/whisper/utils.py:18

Functionpils_from_video

src/utils/img_utils.py:22

Methodpred_prev

(self, noisy_images, noisy_residual, timestep, timestep_prev )

src/pipelines/myschedulers.py:13

Methodpred_prev

(self, noisy_images, noisy_residual, timestep, timestep_prev )

src/pipelines/myschedulers.py:143

Methodpred_prev_train

(self, noisy_images, noisy_residual, timestep, timestep_prev )

src/pipelines/myschedulers.py:72

Methodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echomimicv2.py:177

Methodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echomimicv2_acc.py:176

Methodprepare_latents_bp

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echomimicv2.py:141

Methodprepare_latents_bp

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echomimicv2_acc.py:140

src/utils/util_emo.py:21

(self, tokens: List[List[Tensor]], sum_logprobs: List[List[float]])

src/models/whisper/whisper/decoding.py:182

Functionread_frames

src/utils/util.py:123

Methodrearrange_kv_cache

(self, source_indices)

src/models/whisper/whisper/decoding.py:158

Functionremove_symbols

Replace any other markers, symbols, punctuations with a space, keeping diacritics

src/models/whisper/whisper/normalizers/basic.py:46

src/models/whisper/whisper/decoding.py:292

Functionsave_pose_params_item

EMTD_dataset/preprocess.py:208

Methodsave_to_cache

(module, _, output)

src/models/whisper/whisper/model.py:273

Functionsave_video2imgs

(videos: torch.Tensor, path: str, rescale=False, n_rows=6, fps=8)

src/utils/util.py:106

Functionsave_videos_from_pils

(pils, path, fps=24)

src/utils/img_utils.py:35

Functionscheduler_pred_multisteps

( npred_model, noisy_images, scheduler, timestep_list, audio_cond_fea, face_musk_fea,

src/pipelines/step_func.py:61

(logprobs, lengths)

src/models/whisper/whisper/decoding.py:183

Functionseed_everything

src/utils/util.py:16

Methodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

src/models/unet_3d.py:359

Methodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

src/models/unet_3d_emo.py:359

Methodset_chunk_feed_forward

(self, chunk_size: Optional[int], dim: int = 0)

src/models/attention.py:145

Methodset_default_attn_processor

Disables custom attention processors and sets the default attention implementation.

src/models/unet_2d_condition.py:742

Functionset_tensor_interpolation_method

src/pipelines/utils.py:10

Methodset_use_memory_efficient_attention_xformers

( self, use_memory_efficient_attention_xformers: bool, attention_op: Optional[Callable

src/models/motion_module.py:310

Methodset_use_memory_efficient_attention_xformers

( self, use_memory_efficient_attention_xformers: bool, attention_op: Optional[Callable

src/models/motion_module.py:421

( v0: torch.Tensor, v1: torch.Tensor, t: float, DOT_THRESHOLD: float = 0.9995 )

src/pipelines/utils.py:19

src/models/whisper/whisper/tokenizer.py:166

src/models/whisper/whisper/tokenizer.py:171

src/models/whisper/whisper/tokenizer.py:176

Methodsot_sequence_including_notimestamps

src/models/whisper/whisper/tokenizer.py:232

Functionsplit_video

EMTD_dataset/slice_video.py:10

Functionstr2bool

src/models/whisper/whisper/utils.py:10

src/models/wav_clip.py:48

Methodtimestamp_begin

src/models/whisper/whisper/tokenizer.py:191

Methodto_fraction

src/models/whisper/whisper/normalizers/english.py:165

Functionuniform

( step: int = ..., num_steps: Optional[int] = None, num_frames: int = ..., context_size: Optio

src/pipelines/context.py:15

(self, tokens: Tensor, logits: Tensor, sum_logprobs: Tensor)

src/models/whisper/whisper/decoding.py:258

(self, tokens: Tensor, logits: Tensor, sum_logprobs: Tensor)

src/models/whisper/whisper/decoding.py:295

Functionvideo_to_frame

(video_path: str, interval=1, max_frame=None, imh=None, imw=None, is_return_sum=False, is_rgb=False)

src/utils/util_emo.py:57

Functionxyxy2x0y0wh

src/utils/util_emo.py:53

← previous301–395 of 395, ranked by callers