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
↓ 3 callersFunctionupfirdn2d
r"""Pad, upsample, filter, and downsample a batch of 2D images. Performs the following sequence of operations for each channel: 1. Upsample
torch_utils/ops/upfirdn2d.py:120
↓ 3 callersFunctionupfirdn2d
(input, kernel, up=1, down=1, pad=(0, 0), device='cpu')
eval/lmd/third_part/GPEN/face_model/op/upfirdn2d.py:149
↓ 3 callersFunctionupfirdn2d
r"""Pad, upsample, filter, and downsample a batch of 2D images. Performs the following sequence of operations for each channel: 1. Upsample
eg3d/eg3d/torch_utils/ops/upfirdn2d.py:120
↓ 2 callersMethod__get_keys
(d, name)
eval/metrics/encoders/e4e.py:124
↓ 2 callersMethod__init__
(self, in_c, out_c, spatial)
eval/metrics/encoders/restyle_e4e_encoders.py:34
↓ 2 callersMethod__init__
(self, in_channel, out_channel)
eval/lmd/third_part/GPEN/face_detect/facemodels/net.py:41
↓ 2 callersMethod__init__
(self, in_channels, out_channels, mode='down')
eval/lmd/third_part/GFPGAN/gfpgan/archs/gfpganv1_clean_arch.py:129
↓ 2 callersMethod__init__
(self, c_dim, # Conditioning label (C) dimensionality. img_resolution
training/dual_discriminator.py:108
↓ 2 callersMethod__init__
(self, c_dim, # Conditioning label (C) dimensionality. img_resolution
eg3d/eg3d/training/dual_discriminator.py:108
↓ 2 callersMethod__init__
(self)
eg3d/eg3d/viz/renderer.py:126
↓ 2 callersMethod__init__
(self)
preprocess_utils/data_utils/face_tracking/render_land.py:116
↓ 2 callersMethod__init__
(self, cin, cout, kernel_size, stride, padding, residual=False, *args, **kwargs)
Wav2Lip/models/conv.py:6
↓ 2 callersMethod__init__
(self, channels, reduction)
vive3D/model_irse_helpers.py:57
↓ 2 callersMethod__init__
(self, in_channels, out_channels, mode='down')
GFPGAN/gfpgan/archs/gfpganv1_clean_arch.py:129
↓ 2 callersMethod__load_latent_avg
(self, ckpt, repeat=None)
eval/metrics/encoders/e4e.py:87
↓ 2 callersMethod_adjust_font_size
(self)
eg3d/eg3d/visualizer.py:112
↓ 2 callersFunction_amp_to_db
(x)
eval/lmd/utils/audio.py:103
↓ 2 callersFunction_amp_to_db
(x)
Wav2Lip/audio_process.py:103
↓ 2 callersFunction_amp_to_db
(x)
Wav2Lip/audio.py:105
↓ 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:
preprocess_utils/data_utils/nerf/utils.py:87
↓ 2 callersMethod_attach_glfw_callbacks
(self)
eg3d/eg3d/gui_utils/glfw_window.py:220
↓ 2 callersFunction_collect_tf_params
(tf_net)
legacy.py:75
↓ 2 callersFunction_collect_tf_params
(tf_net)
eg3d/eg3d/legacy.py:75
↓ 2 callersFunction_filtered_lrelu_cuda
Fast CUDA implementation of `filtered_lrelu()` using custom ops.
torch_utils/ops/filtered_lrelu.py:161
↓ 2 callersFunction_filtered_lrelu_cuda
Fast CUDA implementation of `filtered_lrelu()` using custom ops.
eg3d/eg3d/torch_utils/ops/filtered_lrelu.py:161
↓ 2 callersFunction_get_array_priv
( string: str, *, size: int = 32, max_width: Optional[int]=None, max_height: Optional[int]=Non
eg3d/eg3d/gui_utils/text_utils.py:47
↓ 2 callersFunction_get_filter_size
(f)
torch_utils/ops/filtered_lrelu.py:37
↓ 2 callersFunction_get_filter_size
(f)
eg3d/eg3d/torch_utils/ops/filtered_lrelu.py:37
↓ 2 callersMethod_get_pinned_buf
(self, ref)
eg3d/eg3d/viz/renderer.py:210
↓ 2 callersFunction_get_weight_shape
(w)
torch_utils/ops/conv2d_resample.py:23
↓ 2 callersFunction_get_weight_shape
(w)
eg3d/eg3d/torch_utils/ops/conv2d_resample.py:23
↓ 2 callersMethod_get_zipfile
(self)
training/dataset.py:195
↓ 2 callersMethod_get_zipfile
(self)
eg3d/eg3d/training/dataset.py:195
↓ 2 callersMethod_ignore_timing
(self)
eg3d/eg3d/viz/renderer.py:224
↓ 2 callersFunction_index_from_letter
(letter: str)
preprocess_utils/data_utils/nerf/utils.py:120
↓ 2 callersFunction_normalize
(S)
eval/lmd/utils/audio.py:110
↓ 2 callersFunction_normalize
(S)
Wav2Lip/audio_process.py:110
↓ 2 callersFunction_normalize
(S)
Wav2Lip/audio.py:112
↓ 2 callersMethod_open_file
(self, fname)
training/dataset.py:201
↓ 2 callersMethod_open_file
(self, fname)
eg3d/eg3d/training/dataset.py:201
↓ 2 callersFunction_parse_padding
(padding)
torch_utils/ops/filtered_lrelu.py:44
↓ 2 callersFunction_parse_padding
(padding)
eg3d/eg3d/torch_utils/ops/filtered_lrelu.py:44
↓ 2 callersFunction_populate_module_params
(module, *patterns)
legacy.py:88
↓ 2 callersFunction_populate_module_params
(module, *patterns)
eg3d/eg3d/legacy.py:88
↓ 2 callersFunction_preprocess
Preprocessing step before feeding the network. Arguments: img: a float numpy array of shape [h, w, c]. Returns: a float nump
eval/metrics/mtcnn/mtcnn_pytorch/src/box_utils.py:226
↓ 2 callersFunction_should_use_custom_op
(input)
torch_utils/ops/conv2d_gradfix.py:49
↓ 2 callersFunction_should_use_custom_op
(input)
eg3d/eg3d/torch_utils/ops/conv2d_gradfix.py:49
↓ 2 callersFunction_stft
(y)
eval/lmd/utils/audio.py:57
↓ 2 callersFunction_stft
(y)
Wav2Lip/audio_process.py:57
↓ 2 callersFunction_stft
(y)
Wav2Lip/audio.py:57
↓ 2 callersMethod_tensor_size
(self,t)
eval/lmd/third_part/ganimation_replicate/model/model_utils.py:542
↓ 2 callersFunction_umeyama
Estimate N-D similarity transformation with or without scaling. Parameters ---------- src : (M, N) array Source coordinates. d
eval/lmd/third_part/GPEN/align_faces.py:25
↓ 2 callersFunction_upfirdn2d_cuda
Fast CUDA implementation of `upfirdn2d()` using custom ops.
torch_utils/ops/upfirdn2d.py:219
↓ 2 callersFunction_upfirdn2d_cuda
Fast CUDA implementation of `upfirdn2d()` using custom ops.
eg3d/eg3d/torch_utils/ops/upfirdn2d.py:219
↓ 2 callersMethodappend_torch
(self, x, num_gpus=1, rank=0)
eg3d/eg3d/metrics/metric_utils.py:113
↓ 2 callersFunctionapply_img_affine
(img, affine_inv, method=Image.BICUBIC)
eval/lmd/third_part/face3d/data/base_dataset.py:98
↓ 2 callersMethodbegin_frame
(self)
eg3d/eg3d/gui_utils/glfw_window.py:163
↓ 2 callersFunctionbgr2rgb
(img)
eval/lmd/third_part/GPEN/face_morpher/facemorpher/plotter.py:11
↓ 2 callersMethodbind
(self)
eg3d/eg3d/gui_utils/gl_utils.py:292
↓ 2 callersFunctionblockPrint
()
eval/calc_IDSIM.py:23
↓ 2 callersFunctionbutton
(label, width=0, enabled=True)
eg3d/eg3d/gui_utils/imgui_utils.py:92
↓ 2 callersFunctioncal_col_loss
(pred_img, gt_img, img_mask)
preprocess_utils/data_utils/face_tracking/util.py:103
↓ 2 callersFunctioncal_lap_loss
(tensor_list, weight_list)
preprocess_utils/data_utils/face_tracking/util.py:57
↓ 2 callersFunctioncalc_output_padding
(input_shape, output_shape)
torch_utils/ops/conv2d_gradfix.py:95
↓ 2 callersFunctioncalc_output_padding
(input_shape, output_shape)
eg3d/eg3d/torch_utils/ops/conv2d_gradfix.py:95
↓ 2 callersFunctioncalculate_idsim
(ori_video_path, video_path, video_id)
eval/calc_IDSIM.py:59
↓ 2 callersFunctioncalculate_val_far
(threshold, dist, actual_issame)
eval/lmd/third_part/face3d/models/arcface_torch/eval/verification.py:165
↓ 2 callersMethodcheck
(self, track='cfat', test_img = None)
eval/lmd/third_part/face3d/models/arcface_torch/onnx_helper.py:22
↓ 2 callersMethodcheckerboard
(self, size, blocksize=16)
vive3D/aligner.py:171
↓ 2 callersMethodcheckpoint
(self, func, num_seg, x)
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet2060.py:145
↓ 2 callersFunctionchoose_bytes_unit
(num_bytes)
eg3d/dataset_preprocessing/ffhq/download_ffhq.py:135
↓ 2 callersMethodclear_queue
(self)
preprocess_utils/data_utils/nerf/asr.py:364
↓ 2 callersMethodclear_result
(self)
eg3d/eg3d/visualizer.py:101
↓ 2 callersMethodclose
(self)
training/dataset.py:69
↓ 2 callersMethodclose
(self)
eg3d/eg3d/training/dataset.py:69
↓ 2 callersFunctioncompute_distances
(row_features, col_features, num_gpus, rank, col_batch_size)
eg3d/eg3d/metrics/precision_recall.py:21
↓ 2 callersMethodcompute_rotation
Return: rot -- torch.tensor, size (B, 3, 3) pts @ trans_mat Parameters: angles -- tor
eval/lmd/third_part/face3d/models/bfm.py:174
↓ 2 callersFunctioncompute_transform
(lm, predictor, detector=None, scale=1.0, fa=None)
eval/lmd/utils/alignment_stit.py:116
↓ 2 callersMethodconfigure_optimizer
(self, opts, tune=False)
trainer.py:696
↓ 2 callersFunctionconstruct_affine_bandlimit_filter
(mat, a=3, amax=16, aflt=64, up=4, cutoff_in=1, cutoff_out=1)
eg3d/eg3d/metrics/equivariance.py:104
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
eval/BiSeNet.py:11
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet.py:7
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
eval/lmd/third_part/face3d/models/arcface_torch/backbones/iresnet2060.py:10
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
eval/lmd/third_part/GPEN/face_parse/resnet.py:14
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
preprocess_utils/data_utils/face_parsing/resnet.py:14
↓ 2 callersFunctionconv3x3
3x3 convolution with padding
vive3D/BiSeNet.py:11
↓ 2 callersFunctionconvert_mrc
(input_filename, output_filename, isosurface_level=1)
eg3d/eg3d/shape_utils.py:103
↓ 2 callersFunctionconvert_tf_generator
(tf_G)
legacy.py:109
↓ 2 callersFunctionconvert_tf_generator
(tf_G)
eg3d/eg3d/legacy.py:109
↓ 2 callersFunctioncosine_loss
(a, v, y)
Wav2Lip/color_syncnet_train.py:134
↓ 2 callersFunctioncreate_dataloader
(opt)
eval/lmd/third_part/ganimation_replicate/data/data_loader.py:12
↓ 2 callersFunctioncreate_model
(opt)
eval/lmd/third_part/ganimation_replicate/model/__init__.py:7
↓ 2 callersFunctioncreate_model
Create a model given the option. This function warps the class CustomDatasetDataLoader. This is the main interface between this package and '
eval/lmd/third_part/face3d/models/__init__.py:54
↓ 2 callersFunctioncrop
(img, bbox)
eval/lmd/third_part/face3d/util/preprocess.py:86
↓ 2 callersMethodcrop
(self, image)
vive3D/video_tool.py:35
↓ 2 callersMethodcrop_audio_window
(self, spec, start_frame)
talk3d_dataloader.py:385
↓ 2 callersMethodcrop_audio_window
(self, spec, start_frame)
Wav2Lip/wav2lip_train.py:75
↓ 2 callersMethodcrop_audio_window
(self, spec, start_frame)
Wav2Lip/hq_wav2lip_train.py:77
↓ 2 callersFunctioncrop_image
(filepath, output_size, quad, enable_padding=False)
eval/lmd/utils/alignment_stit.py:68
↓ 2 callersFunctiondecode
Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo
eval/lmd/third_part/GPEN/face_detect/utils/box_utils.py:209
← previousnext →301–400 of 2,892, ranked by callers