MCPcopy Create free account

hub / github.com/cvlab-kaist/Talk3D / functions

Functions2,892 in github.com/cvlab-kaist/Talk3D

⨍ Functions 2,892◇ Types & classes 538↳ Endpoints 8
↓ 6 callersMethodsample_mixed
(self, coordinates, directions, ws, truncation_psi=1, truncation_cutoff=None, update_emas=False, **synthesis_k
training/triplane.py:207
↓ 6 callersMethodset_camera_parameters
(self, focal_length=3.5, cam_pivot=[0, 0, 0.2], use_ddp = False)
vive3D/eg3d_generator.py:83
↓ 6 callersMethodstd
r"""Returns the standard deviation of the scalars that were accumulated for the given statistic between the last two calls to `update(
torch_utils/training_stats.py:200
↓ 6 callersMethodtensor2im
(self, input_image, imtype=np.uint8)
eval/lmd/third_part/ganimation_replicate/visualizer.py:80
↓ 6 callersFunctiontransform
Generate and affine transformation matrix. Given a set of points, a center, a scale and a targer resolution, the function generates and affin
eval/lmd/third_part/face_detection/utils.py:56
↓ 6 callersMethodupdate
r"""Copies current values of the internal counters to the user-visible state and resets them for the next round. If `keep_previous=Tr
eg3d/eg3d/torch_utils/training_stats.py:149
↓ 5 callersMethod__init__
(self, embedding_size)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/mobilefacenet.py:76
↓ 5 callersMethod__init__
(self, z_dim, # Input latent (Z) dimensionality. c_dim,
training/networks_stylegan3.py:493
↓ 5 callersMethod__init__
(self, in_channels, # Number of input channels, 0 = first block. ou
training/superresolution.py:158
↓ 5 callersMethod__init__
(self, z_dim, # Input latent (Z) dimensionality. c_dim,
eg3d/eg3d/training/networks_stylegan3.py:493
↓ 5 callersMethod__init__
(self, in_channels, # Number of input channels, 0 = first block. ou
eg3d/eg3d/training/superresolution.py:159
↓ 5 callersFunction_get_filter_size
(f)
torch_utils/ops/upfirdn2d.py:57
↓ 5 callersFunction_get_filter_size
(f)
eg3d/eg3d/torch_utils/ops/upfirdn2d.py:57
↓ 5 callersFunction_iresnet
(arch, block, layers, pretrained, progress, **kwargs)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet.py:157
↓ 5 callersFunction_sinc
(x)
eg3d/eg3d/viz/renderer.py:50
↓ 5 callersFunctionalign_img
Return: transparams --numpy.array (raw_W, raw_H, scale, tx, ty) img_new --PIL.Image (target_size, target_size
eval/lmd/third_part/face3d/util/preprocess.py:169
↓ 5 callersMethodbackward
Calculate losses, gradients, and update network weights; called in every training iteration
eval/lmd/third_part/face3d/models/template_model.py:88
↓ 5 callersFunctionboundary_points
Produce additional boundary points :param points: *m* x 2 array of x,y points :param width_percent: [-1, 1] percentage of width to taper inwards.
eval/lmd/third_part/GPEN/face_morpher/facemorpher/locator.py:19
↓ 5 callersFunctioncompute_mse_loss
(data1, data2)
eval/action_unit_error.py:11
↓ 5 callersFunctionconv_bn
(inp, oup, stride = 1, leaky = 0)
eval/lmd/third_part/GPEN/face_detect/facemodels/net.py:9
↓ 5 callersMethodencode
(self, x)
GFPGAN/gfpgan/archs/restoreformer_arch.py:641
↓ 5 callersMethodflush
Flush written text to both stdout and a file, if open.
dnnlib/util.py:95
↓ 5 callersMethodget_average_w
(self)
vive3D/eg3d_generator.py:118
↓ 5 callersMethodget_body_BiSeNet
(self, input_tensor, dilate=0)
eval/segmenter.py:93
↓ 5 callersMethodget_foreground_BiSeNet
(self, input_tensor, background_classes=[0, 18, 16, 14], dilate_num=-1, erosion_num=-1, neck_treatment=False)
vive3D/segmenter.py:71
↓ 5 callersFunctionget_model
(name, **kwargs)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/__init__.py:5
↓ 5 callersMethodinference_step
(self, inferencetype='train', cameratype='GT')
trainer.py:359
↓ 5 callersFunctioniterate_images
()
eg3d/eg3d/dataset_tool.py:86
↓ 5 callersMethodloadParameters
(self, path)
eval/syncnet_python/SyncNetInstance.py:201
↓ 5 callersMethodload_checkpoint
(self, checkpoint=None, model_only=False)
preprocess_utils/data_utils/nerf/utils.py:1364
↓ 5 callersFunctionmaybe_min
(a: int, b: Optional[int])
eg3d/eg3d/dataset_tool.py:52
↓ 5 callersMethodrender
(self, **args)
eg3d/eg3d/viz/renderer.py:138
↓ 5 callersFunctionscale2d_inv
(sx, sy, **kwargs)
training/augment.py:110
↓ 5 callersFunctionscale2d_inv
(sx, sy, **kwargs)
eg3d/eg3d/training/augment.py:110
↓ 5 callersMethodskip_frame
(self)
eg3d/eg3d/gui_utils/glfw_window.py:132
↓ 5 callersFunctiontformfwd
Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array tr
eval/metrics/mtcnn/mtcnn_pytorch/src/matlab_cp2tform.py:19
↓ 5 callersMethodupdate
Set updated weight and weight_mom to memory bank.
eval/lmd/third_part/face3d/models/arcface_torch/partial_fc.py:133
↓ 4 callersMethod__getitem__
(self, index)
GFPGAN/gfpgan/data/ffhq_degradation_dataset.py:145
↓ 4 callersMethod__init__
(self, channels, reduction)
eval/metrics/encoders/helpers.py:58
↓ 4 callersMethod__init__
(self, num_modules=1)
eval/lmd/third_part/face_detection/models.py:147
↓ 4 callersMethod__init__
( self, block: Type[Union[BasicBlock, Bottleneck]], layers: List[int], num_cla
eval/lmd/third_part/face3d/models/networks.py:266
↓ 4 callersMethod__init__
(self, inplanes, planes, stride=1, downsample=None, use_se=True)
eval/lmd/third_part/GFPGAN/gfpgan/archs/arcface_arch.py:68
↓ 4 callersMethod__init__
( self, out_size, num_style_feat=512, channel_multiplier=1,
eval/lmd/third_part/GFPGAN/gfpgan/archs/gfpganv1_arch.py:243
↓ 4 callersMethod__init__
(self, in_channels, num_style_feat, upsample=True)
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_clean_arch.py:150
↓ 4 callersMethod__init__
(self, num_modules=1)
Wav2Lip/face_detection/models.py:147
↓ 4 callersMethod__init__
(self, inplanes, planes, stride=1, downsample=None, use_se=True)
GFPGAN/gfpgan/archs/arcface_arch.py:68
↓ 4 callersMethod__init__
( self, out_size, num_style_feat=512, channel_multiplier=1,
GFPGAN/gfpgan/archs/gfpganv1_arch.py:243
↓ 4 callersMethod__init__
(self, in_channels, num_style_feat, upsample=True)
GFPGAN/gfpgan/archs/stylegan2_clean_arch.py:150
↓ 4 callersFunction_check_sha1
Check whether the sha1 hash of the file content matches the expected hash. Parameters ---------- filename : str Path to the
preprocess_utils/data_utils/deepspeech_features/deepspeech_store.py:148
↓ 4 callersFunction_conv2d_gradfix
(transpose, weight_shape, stride, padding, output_padding, dilation, groups)
torch_utils/ops/conv2d_gradfix.py:68
↓ 4 callersFunction_conv2d_gradfix
(transpose, weight_shape, stride, padding, output_padding, dilation, groups)
eg3d/eg3d/torch_utils/ops/conv2d_gradfix.py:68
↓ 4 callersMethod_get_raw_labels
(self)
training/dataset.py:55
↓ 4 callersMethod_get_raw_labels
(self)
eg3d/eg3d/training/dataset.py:55
↓ 4 callersMethod_gram_mat
Calculate Gram matrix. Args: x (torch.Tensor): Tensor with shape of (n, c, h, w). Returns: torch.Tensor: Gra
eval/lmd/third_part/GFPGAN/gfpgan/models/gfpgan_model.py:267
↓ 4 callersMethod_gram_mat
Calculate Gram matrix. Args: x (torch.Tensor): Tensor with shape of (n, c, h, w). Returns: torch.Tensor: Gra
GFPGAN/gfpgan/models/gfpgan_model.py:266
↓ 4 callersFunction_lanczos_window
(x, a)
eg3d/eg3d/viz/renderer.py:55
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1)
eval/lmd/third_part/face_detection/models.py:229
↓ 4 callersMethod_make_layer
(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int, stride: int =
eval/lmd/third_part/face3d/models/networks.py:331
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilate=False)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet.py:114
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilate=False)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet2060.py:119
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride=1)
eval/lmd/third_part/GFPGAN/gfpgan/archs/arcface_arch.py:214
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1)
Wav2Lip/face_detection/models.py:229
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride=1)
GFPGAN/gfpgan/archs/arcface_arch.py:214
↓ 4 callersFunction_tuple_of_ints
(xs, ndim)
torch_utils/ops/conv2d_gradfix.py:57
↓ 4 callersFunction_tuple_of_ints
(xs, ndim)
eg3d/eg3d/torch_utils/ops/conv2d_gradfix.py:57
↓ 4 callersMethodclear
(self)
eval/lmd/third_part/GPEN/face_detect/utils/timer.py:35
↓ 4 callersFunctionconv3x3
A simple wrapper for 3x3 convolution with padding. Args: inplanes (int): Channel number of inputs. outplanes (int): Channel numbe
eval/lmd/third_part/GFPGAN/gfpgan/archs/arcface_arch.py:5
↓ 4 callersFunctionconv3x3
A simple wrapper for 3x3 convolution with padding. Args: inplanes (int): Channel number of inputs. outplanes (int): Channel numbe
GFPGAN/gfpgan/archs/arcface_arch.py:5
↓ 4 callersFunctionconvert_poses
(poses)
preprocess_utils/data_utils/nerf/utils.py:231
↓ 4 callersFunctionconvert_to_square
Convert bounding boxes to a square form. Arguments: bboxes: a float numpy array of shape [n, 5]. Returns: a float numpy arra
eval/metrics/mtcnn/mtcnn_pytorch/src/box_utils.py:71
↓ 4 callersFunctioncreate_cam2world_matrix
Takes in the direction the camera is pointing and the camera origin and returns a cam2world matrix. Works on batches of forward_vectors, orig
eg3d/eg3d/camera_utils.py:118
↓ 4 callersFunctioncreate_layer_basic
(in_chan, out_chan, bnum, stride=1)
eval/BiSeNet.py:48
↓ 4 callersFunctioncreate_layer_basic
(in_chan, out_chan, bnum, stride=1)
eval/lmd/third_part/GPEN/face_parse/resnet.py:51
↓ 4 callersFunctioncreate_layer_basic
(in_chan, out_chan, bnum, stride=1)
preprocess_utils/data_utils/face_parsing/resnet.py:51
↓ 4 callersFunctioncreate_layer_basic
(in_chan, out_chan, bnum, stride=1)
vive3D/BiSeNet.py:48
↓ 4 callersMethodend_frame
(self)
eg3d/eg3d/gui_utils/glfw_window.py:200
↓ 4 callersMethodenhance
(self, img, has_aligned=False, only_center_face=False, paste_back=True, weight=0.5)
GFPGAN/gfpgan/utils.py:107
↓ 4 callersMethodevaluate
(self, opt, videofile)
eval/syncnet_python/SyncNetInstance.py:42
↓ 4 callersMethodextract_feats
(self, x)
vive3D/inset_pipeline.py:80
↓ 4 callersMethodextract_keypoint
(self, images, name=None, info=False)
eval/lmd/third_part/face3d/extract_kp_videos.py:18
↓ 4 callersMethodfeed_data
(self, data)
GFPGAN/gfpgan/models/gfpgan_model.py:201
↓ 4 callersMethodflush
Flush written text to both stdout and a file, if open.
eg3d/eg3d/dnnlib/util.py:95
↓ 4 callersFunctionforward_rott
(geometry, euler_angle, trans)
preprocess_utils/data_utils/face_tracking/util.py:86
↓ 4 callersFunctionfused_leaky_relu
(input, bias, negative_slope=0.2, scale=2 ** 0.5, device='cpu')
eval/lmd/third_part/GPEN/face_model/op/fused_act.py:92
↓ 4 callersMethodget_all
(self)
eg3d/eg3d/metrics/metric_utils.py:125
↓ 4 callersFunctionget_audio_features
(features, att_mode, index)
preprocess_utils/data_utils/nerf/utils.py:42
↓ 4 callersFunctionget_embedder
(multires,input_dim=3,i=0,include_input=False)
training/PE.py:101
↓ 4 callersFunctionget_image_boxes
Cut out boxes from the image. Arguments: bounding_boxes: a float numpy array of shape [n, 5]. img: an instance of PIL.Image.
eval/metrics/mtcnn/mtcnn_pytorch/src/box_utils.py:127
↓ 4 callersFunctionget_norm_layer
Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNorm
eval/lmd/third_part/ganimation_replicate/model/model_utils.py:14
↓ 4 callersFunctionget_rays
get rays Args: poses: [B, 4, 4], cam2world intrinsics: [4] H, W, N: int Returns: rays_o, rays_d: [B, N, 3]
preprocess_utils/data_utils/nerf/utils.py:249
↓ 4 callersFunctionget_texture_format
(dtype, channels)
eg3d/eg3d/gui_utils/gl_utils.py:78
↓ 4 callersMethodget_w_std
(self)
vive3D/eg3d_generator.py:121
↓ 4 callersFunctionhas_same_layout
torch_utils/ops/bias_act.cpp:20
↓ 4 callersFunctionhas_same_layout
eg3d/eg3d/torch_utils/ops/bias_act.cpp:20
↓ 4 callersFunctioninit_net
(net, init_type='normal', init_gain=0.02, gpu_ids=[])
eval/lmd/third_part/ganimation_replicate/model/model_utils.py:73
↓ 4 callersFunctionlanczos_window
(x, a)
eg3d/eg3d/metrics/equivariance.py:29
↓ 4 callersFunctionlinear_to_srgb
(x)
preprocess_utils/data_utils/nerf/utils.py:78
↓ 4 callersFunctionload_lm3d
(bfm_folder)
eval/lmd/third_part/face3d/util/load_mats.py:105
↓ 4 callersMethodlogical_and_reduce
(self, *tensors)
vive3D/segmenter.py:41
↓ 4 callersFunctionmodulated_conv2d
( x, # Input tensor of shape [batch_size, in_channels, in_height, in_width].
training/networks_stylegan2.py:36
← previousnext →101–200 of 2,892, ranked by callers