Functions — github.com/cvlab-kaist/ControlFace

↓ 1 callersMethodload_mask

(self, maskpath, h, w)

decalib/datasets/train_datasets.py:192

↓ 1 callersMethodload_mask

(self, maskpath, h, w)

decalib/datasets/ethnicity.py:114

↓ 1 callersMethodload_mask

(self, maskpath, h, w)

decalib/datasets/vggface.py:109

↓ 1 callersMethodload_mask

(self, maskpath, h, w)

decalib/datasets/vggface.py:218

↓ 1 callersFunctionload_model

(args)

sample.py:106

↓ 1 callersFunctionload_state_dict

Set parameters converted from Caffe models authors of VGGFace2 provide. See https://www.robots.ox.ac.uk/~vgg/data/vgg_face2/. Arguments:

decalib/models/frnet.py:156

↓ 1 callersMethodload_weights

Function to load luatorch pretrained Args: path: path for the luatorch pretrained

decalib/utils/lossfunc.py:491

↓ 1 callersFunctionmain

()

sample.py:186

↓ 1 callersMethodpatch_extraction

(self, featmaps)

decalib/utils/lossfunc.py:388

↓ 1 callersMethodpatch_extraction

(self, featmaps)

decalib/utils/lossfunc.py:569

↓ 1 callersFunctionplot_kpts

Draw 68 key points Args: image: the input image kpt: (68, 3).

decalib/utils/util.py:579

↓ 1 callersFunctionpoints2bbox

(points, points_scale=None)

decalib/utils/tensor_cropper.py:13

↓ 1 callersFunctionprepare_control

()

tools/download_weights.py:83

↓ 1 callersMethodprepare_data

(self)

decalib/trainer.py:361

↓ 1 callersMethodprepare_data

(self)

decalib/utils/trainer.py:247

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/pipelines/pipeline_point.py:146

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, dtype

src/pipelines/pipeline_point.py:167

↓ 1 callersMethodprepare_point_embeddings

( self, handle_points, target_points, )

src/pipelines/pipeline_point.py:220

↓ 1 callersFunctionread_frames

(video_path)

src/utils/util.py:141

↓ 1 callersMethodregister_reference_hooks

( self, mode, do_ref_guidance, attention_auto_machine_weight

src/models/mutual_self_attention_point.py:120

↓ 1 callersFunctionresnet50

Constructs a ResNet-50 model.

decalib/models/frnet.py:149

↓ 1 callersFunctionrotation_matrix_to_quaternion

Convert 3x4 rotation matrix to 4d quaternion vector This algorithm is based on algorithm described in https://github.com/KieranWynn/pyquatern

decalib/utils/rotation_converter.py:88

↓ 1 callersFunctionsave_videos_from_pil_

(pil_images, path, fps=8)

src/utils/util.py:85

↓ 1 callersMethodseletec_3d68

(self, vertices)

decalib/models/FLAME.py:169

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to comp

src/models/unet_2d_condition.py:761

↓ 1 callersMethodset_attn_processor

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

src/models/unet_2d_condition.py:700

↓ 1 callersFunctionset_rasterizer

(type = 'pytorch3d')

decalib/utils/renderer.py:22

↓ 1 callersFunctionset_up_point_attn_processor

(denoising_unet,point_embedding)

src/models/mutual_self_attention_point.py:31

↓ 1 callersFunctionstandard_rasterize

decalib/utils/rasterizer/standard_rasterize_cuda.cpp:13

↓ 1 callersMethodsum_normalize

(self, featmaps)

decalib/utils/lossfunc.py:384

↓ 1 callersMethodsum_normalize

(self, featmaps)

decalib/utils/lossfunc.py:565

↓ 1 callersMethodtraining_step

(self, batch, batch_nb, training_type='coarse')

decalib/trainer.py:110

↓ 1 callersMethodtraining_step

(self, batch, batch_nb)

decalib/utils/trainer.py:101

↓ 1 callersFunctiontransform_mat

Creates a batch of transformation matrices Args: - R: Bx3x3 array of a batch of rotation matrices - t: Bx3x1 array of

decalib/models/lbs.py:308

↓ 1 callersFunctionupdate_cfg

(cfg, cfg_file)

decalib/utils/config.py:122

↓ 1 callersMethodvalidation_step

(self)

decalib/trainer.py:296

↓ 1 callersMethodvalidation_step

(self)

decalib/utils/trainer.py:194

↓ 1 callersFunctionvertices2joints

Calculates the 3D joint locations from the vertices Parameters ---------- J_regressor : torch.tensor JxV The regressor array tha

decalib/models/lbs.py:230

↓ 1 callersFunctionvideo2sequence

(video_path, sample_step=10)

decalib/datasets/datasets.py:30

FunctionPYBIND11_MODULE

decalib/utils/rasterizer/standard_rasterize_cuda.cpp:43

Method__call__

( self, ref_image, pose_image, width, height, num_inference_st

src/pipelines/pipeline_point.py:231

Method__call__

( self, attn, hidden_states: torch.FloatTensor, encoder_hidden_states: Optiona

src/models/attn_proc.py:48

Method__getitem__

(self, index)

src/training_utils.py:75

Method__getitem__

(self, index)

src/training_utils.py:205

Method__getitem__

(self, index)

src/training_utils.py:303

Method__getitem__

(self, index)

src/training_utils.py:378

Method__getitem__

(self, index)

src/training_utils.py:466

Method__getitem__

(self, index)

src/training_utils.py:552

Method__getitem__

(self, index)

src/training_utils.py:690

Method__getitem__

(self, idx)

decalib/datasets/vox.py:74

Method__getitem__

(self, index)

decalib/datasets/aflw2000.py:37

Method__getitem__

(self, index)

decalib/datasets/datasets.py:122

Method__getitem__

(self, idx)

decalib/datasets/train_datasets.py:113

Method__getitem__

(self, idx)

decalib/datasets/train_datasets.py:223

Method__getitem__

(self, idx)

decalib/datasets/train_datasets.py:316

Method__getitem__

(self, index)

decalib/datasets/train_datasets.py:444

Method__getitem__

(self, index)

decalib/datasets/train_datasets.py:528

Method__getitem__

(self, index)

decalib/datasets/now.py:31

Method__getitem__

(self, idx)

decalib/datasets/ethnicity.py:37

Method__getitem__

(self, idx)

decalib/datasets/vggface.py:39

Method__getitem__

(self, idx)

decalib/datasets/vggface.py:149

Method__init__

( self, path, path_arc=None, )

src/training_utils.py:154

Method__init__

( self, path, )

src/training_utils.py:254

Method__init__

( self, path,num, arc=None )

src/training_utils.py:344

Method__init__

( self, path, arc=None )

src/training_utils.py:424

Method__init__

( self, path, arc=None )

src/training_utils.py:519

Method__init__

( self, path, arc_path, path_code=None, stage=1, )

src/training_utils.py:627

Method__init__

( self, vae, image_encoder, reference_unet, denoising_unet, po

src/pipelines/pipeline_point.py:63

Method__init__

(self)

src/models/pointemb.py:60

Method__init__

( self, input_dim=2, vae_downsample_scale=8, unet_downsample_scale=8,

src/models/pointemb.py:69

Method__init__

( self, num_attention_heads: int = 16, attention_head_dim: int = 88, in_channe

src/models/transformer_2d.py:63

Method__init__

( self, sample_size: Optional[int] = None, in_channels: int = 4, out_channels:

src/models/unet_2d_condition.py:160

Method__init__

(self, embed_dim, hidden_size, use_norm=False)

src/models/attn_proc.py:33

Method__init__

( self, dim: int, num_attention_heads: int, attention_head_dim: int, d

src/models/attention.py:298

Method__init__

(self, unet, mode="write", do_ref_guidance=False,

src/models/mutual_self_attention_point.py:85

Method__init__

(self, in_channels: int, out_channels: int, act_fn: str)

src/models/unet_2d_blocks.py:202

Method__init__

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

src/models/unet_2d_blocks.py:254

Method__init__

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

src/models/unet_2d_blocks.py:357

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_2d_blocks.py:501

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_2d_blocks.py:662

Method__init__

( self, in_channels: int, out_channels: int, prev_output_channel: int,

src/models/unet_2d_blocks.py:760

Method__init__

( self, conditioning_embedding_channels: int, conditioning_channels: int = 3,

src/models/pose_guider.py:13

Method__init__

( self, channels, use_conv=False, out_channels=None, padding=1, name="conv" )

src/models/resnet.py:94

Method__init__

( self, *, in_channels, out_channels=None, conv_shortcut=False,

src/models/resnet.py:124

Method__init__

( self, in_channels, num_attention_heads=8, num_transformer_block=2, a

src/models/motion_module.py:45

Method__init__

( self, in_channels, num_attention_heads, attention_head_dim, num_laye

src/models/motion_module.py:95

Method__init__

( self, dim, num_attention_heads, attention_head_dim, attention_block_

src/models/motion_module.py:186

Method__init__

( self, attention_mode=None, cross_frame_attention_mode=None, temporal_positio

src/models/motion_module.py:281

Method__init__

(self, config=None, device='cuda')

decalib/deca.py:39

Method__init__

(self, model, config=None, device='cuda:0')

decalib/trainer.py:44

Method__init__

use fixed raster_settings for rendering faces

decalib/utils/renderer.py:52

Method__init__

use fixed raster_settings for rendering faces

decalib/utils/renderer.py:114

Method__init__

(self)

decalib/utils/lossfunc.py:340

Method__init__

(self, featlayer=VGG19FeatLayer)

decalib/utils/lossfunc.py:374

Method__init__

(self)

decalib/utils/lossfunc.py:553

Method__init__

(self, pretrained_model, pretrained_data='vggface2')

decalib/utils/lossfunc.py:641

Method__init__

(self, crop_size, scale=[1,1], trans_scale = 0.)

decalib/utils/tensor_cropper.py:86

Method__init__

(self, **kwargs)

decalib/utils/util.py:558

Method__init__

(self, model, config=None, device='cuda:0')

decalib/utils/trainer.py:44

Method__init__

(self, K, image_size, scale, trans_scale = 0, dataname='vox2', n_train=100000, isTemporal=False, isEval=False,

decalib/datasets/vox.py:13

Functions408 in github.com/cvlab-kaist/ControlFace