MCPcopy Create free account

hub / github.com/cvlab-kaist/Talk3D / types & classes

Types & classes538 in github.com/cvlab-kaist/Talk3D

⨍ Functions 2,892◇ Types & classes 538↳ Endpoints 8
↓ 84 callersClassConv2d
Wav2Lip/models/conv.py:5
↓ 18 callersClassSynthesisBlock_noaffine
training/networks_diffusers.py:28
↓ 17 callersClassConv2d
eg3d/eg3d/torch_utils/ops/conv2d_gradfix.py:107
↓ 14 callersClassConvLayer
Conv Layer used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel num
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:530
↓ 14 callersClassConvLayer
Conv Layer used in StyleGAN2 Discriminator. Args: in_channels (int): Channel number of the input. out_channels (int): Channel num
GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:530
↓ 13 callersClassnonorm_Conv2d
Wav2Lip/models/conv.py:21
↓ 11 callersClassEqualConv2d
Equalized Linear as StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the ou
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:481
↓ 11 callersClassEqualConv2d
Equalized Linear as StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the ou
GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:481
↓ 10 callersClassConvBNReLU
eval/BiSeNet.py:99
↓ 10 callersClassConvBNReLU
eval/lmd/third_part/GPEN/face_parse/model.py:14
↓ 10 callersClassConvBNReLU
preprocess_utils/data_utils/face_parsing/model.py:14
↓ 10 callersClassConvBNReLU
vive3D/BiSeNet.py:99
↓ 10 callersClassFullyConnectedLayer
training/networks_stylegan2.py:98
↓ 9 callersClassConv2dLayer
training/networks_stylegan2.py:137
↓ 9 callersClassGFPGANer
Helper for restoration with GFPGAN. It will detect and crop faces, and then resize the faces to 512x512. GFPGAN is used to restored the resiz
GFPGAN/gfpgan/utils.py:16
↓ 9 callersClassResnetBlock
GFPGAN/gfpgan/archs/restoreformer_arch.py:152
↓ 8 callersClassBackbone
vive3D/model_irse.py:9
↓ 8 callersClassConv2dLayer
eg3d/eg3d/training/networks_stylegan2.py:135
↓ 8 callersClassConvBlock
eval/lmd/third_part/face_detection/models.py:13
↓ 8 callersClassConvBlock
Wav2Lip/face_detection/models.py:13
↓ 8 callersClassFullyConnectedLayer
eg3d/eg3d/training/networks_stylegan2.py:96
↓ 8 callersClassFusedLeakyReLU
eval/lmd/third_part/GPEN/face_model/op/fused_act.py:79
↓ 8 callersClassSynthesisBlock
training/networks_stylegan2.py:555
↓ 8 callersClassSynthesisBlock
eg3d/eg3d/training/networks_stylegan2.py:365
↓ 7 callersClassConvLayer
eval/lmd/third_part/GPEN/face_model/gpen_model.py:557
↓ 7 callersClassEqualLinear
eval/lmd/third_part/GPEN/face_model/gpen_model.py:139
↓ 7 callersClassFaceWarpException
eval/metrics/mtcnn/mtcnn_pytorch/src/align_trans.py:26
↓ 7 callersClassFaceWarpException
eval/lmd/third_part/GPEN/align_faces.py:96
↓ 7 callersClassSegmenter
eval/segmenter.py:31
↓ 6 callersClassAligner
vive3D/aligner.py:13
↓ 6 callersClassAttention
training/networks_diffusers.py:622
↓ 6 callersClassBackbone
eval/metrics/encoders/model_irse.py:9
↓ 6 callersClassConv2dTranspose
Wav2Lip/models/conv.py:33
↓ 6 callersClassConvLayer
eval/lmd/third_part/GPEN/face_parse/blocks.py:72
↓ 6 callersClassLandmarkDetector
vive3D/landmark_detector.py:3
↓ 6 callersClassMultiHeadAttnBlock
GFPGAN/gfpgan/archs/restoreformer_arch.py:197
↓ 6 callersClassScaledLeakyReLU
Scaled LeakyReLU. Args: negative_slope (float): Negative slope. Default: 0.2.
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:465
↓ 6 callersClassScaledLeakyReLU
Scaled LeakyReLU. Args: negative_slope (float): Negative slope. Default: 0.2.
GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:465
↓ 6 callersClassUnetSkipConnectionBlock
eval/lmd/third_part/ganimation_replicate/model/model_utils.py:278
↓ 5 callersClassConvBlock
eval/lmd/third_part/face3d/models/arcface_torch/backbones/mobilefacenet.py:16
↓ 5 callersClassEG3D_Generator
vive3D/eg3d_generator.py:12
↓ 5 callersClassFFHQDegradationDataset
FFHQ dataset for GFPGAN. It reads high resolution images, and then generate low-quality (LQ) images on-the-fly. Args: opt (dict): Co
GFPGAN/gfpgan/data/ffhq_degradation_dataset.py:17
↓ 5 callersClassMLP
preprocess_utils/data_utils/nerf/network.py:69
↓ 5 callersClassMappingNetwork
training/networks_stylegan2.py:195
↓ 5 callersClassMappingNetwork
eg3d/eg3d/training/networks_stylegan2.py:193
↓ 5 callersClassSyncNetInstance
eval/syncnet_python/SyncNetInstance.py:35
↓ 5 callersClassWav2Lip
Wav2Lip/models/wav2lip.py:8
↓ 4 callersClassCapturedException
eg3d/eg3d/viz/renderer.py:29
↓ 4 callersClassDepthWise
eval/lmd/third_part/face3d/models/arcface_torch/backbones/mobilefacenet.py:41
↓ 4 callersClassDiscriminatorBlock
training/networks_stylegan2.py:946
↓ 4 callersClassDiscriminatorBlock
eg3d/eg3d/training/networks_stylegan2.py:557
↓ 4 callersClassDiscriminatorEpilogue
training/networks_stylegan2.py:1064
↓ 4 callersClassDiscriminatorEpilogue
eg3d/eg3d/training/networks_stylegan2.py:675
↓ 4 callersClassEqualLinear
Equalized Linear as StyleGAN2. Args: in_channels (int): Size of each sample. out_channels (int): Size of each output sample.
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:24
↓ 4 callersClassEqualLinear
Equalized Linear as StyleGAN2. Args: in_channels (int): Size of each sample. out_channels (int): Size of each output sample.
GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:24
↓ 4 callersClassFeedForward
training/networks_diffusers.py:582
↓ 4 callersClassFullyConnectedLayer
training/networks_stylegan3.py:71
↓ 4 callersClassFullyConnectedLayer
eg3d/eg3d/training/networks_stylegan3.py:71
↓ 4 callersClassGFPGANv1Clean
The GFPGAN architecture: Unet + StyleGAN2 decoder with SFT. It is the clean version without custom compiled CUDA extensions used in StyleGAN2.
GFPGAN/gfpgan/archs/gfpganv1_clean_arch.py:153
↓ 4 callersClassResBlock
Residual block with bilinear upsampling/downsampling. Args: in_channels (int): Channel number of the input. out_channels (int): C
eval/lmd/third_part/GFPGAN/gfpgan/archs/gfpganv1_clean_arch.py:120
↓ 4 callersClassResBlock
Residual block with bilinear upsampling/downsampling. Args: in_channels (int): Channel number of the input. out_channels (int): C
GFPGAN/gfpgan/archs/gfpganv1_clean_arch.py:120
↓ 4 callersClassSynthesisLayer
training/networks_stylegan2.py:427
↓ 4 callersClassSynthesisLayer
eg3d/eg3d/training/networks_stylegan2.py:276
↓ 4 callersClassVideoTool
vive3D/video_tool.py:10
↓ 3 callersClassBiSeNetOutput
eval/BiSeNet.py:122
↓ 3 callersClassBiSeNetOutput
eval/lmd/third_part/GPEN/face_parse/model.py:37
↓ 3 callersClassBiSeNetOutput
preprocess_utils/data_utils/face_parsing/model.py:37
↓ 3 callersClassBiSeNetOutput
vive3D/BiSeNet.py:122
↓ 3 callersClassBlur
eval/lmd/third_part/GPEN/face_model/gpen_model.py:81
↓ 3 callersClassDataLoader
eval/lmd/third_part/ganimation_replicate/data/data_loader.py:18
↓ 3 callersClassDistributedLayerNorm
training/networks_diffusers.py:554
↓ 3 callersClassFeatureStats
eg3d/eg3d/metrics/metric_utils.py:73
↓ 3 callersClassGFPGANv1
The GFPGAN architecture: Unet + StyleGAN2 decoder with SFT. Ref: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior.
GFPGAN/gfpgan/archs/gfpganv1_arch.py:221
↓ 3 callersClassGenerator
eval/lmd/third_part/GPEN/face_model/gpen_model.py:380
↓ 3 callersClassInference_Dataset
talk3d_dataloader.py:138
↓ 3 callersClassKeypointExtractor
eval/lmd/third_part/face3d/extract_kp_videos.py:14
↓ 3 callersClassL2Norm
eval/syncnet_python/detectors/s3fd/nets.py:8
↓ 3 callersClassL2Norm
eval/lmd/third_part/face_detection/detection/sfd/net_s3fd.py:6
↓ 3 callersClassL2Norm
Wav2Lip/face_detection/detection/sfd/net_s3fd.py:6
↓ 3 callersClassResidual
eval/lmd/third_part/face3d/models/arcface_torch/backbones/mobilefacenet.py:63
↓ 3 callersClassResidualBlock
Residual block recommended in: http://torch.ch/blog/2016/02/04/resnets.html
eval/lmd/third_part/GPEN/face_parse/blocks.py:102
↓ 3 callersClassResnetBlock2D
training/networks_diffusers.py:351
↓ 3 callersClassS
eval/syncnet_python/SyncNetModel.py:16
↓ 3 callersClassSSH
eval/lmd/third_part/GPEN/face_detect/facemodels/net.py:40
↓ 3 callersClassStyleConv
Style conv. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the output. kerne
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:162
↓ 3 callersClassStyleConv
Style conv used in StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the out
eval/lmd/third_part/GFPGAN/gfpgan/archs/stylegan2_clean_arch.py:106
↓ 3 callersClassStyleConv
Style conv. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the output. kerne
GFPGAN/gfpgan/archs/stylegan2_bilinear_arch.py:162
↓ 3 callersClassStyleConv
Style conv used in StyleGAN2. Args: in_channels (int): Channel number of the input. out_channels (int): Channel number of the out
GFPGAN/gfpgan/archs/stylegan2_clean_arch.py:106
↓ 3 callersClassStyledConv
eval/lmd/third_part/GPEN/face_model/gpen_model.py:318
↓ 3 callersClassSynthesisBlockNoUp
training/superresolution.py:157
↓ 3 callersClassSynthesisBlockNoUp
eg3d/eg3d/training/superresolution.py:158
↓ 3 callersClassSynthesisBlock_mimic3d
training/networks_stylegan2.py:659
↓ 3 callersClasssimpleMLP
talk3d_helper.py:187
↓ 2 callersClassASR
preprocess_utils/data_utils/nerf/asr.py:35
↓ 2 callersClassArcFaceORT
eval/lmd/third_part/face3d/models/arcface_torch/onnx_helper.py:15
↓ 2 callersClassAttentionRefinementModule
eval/BiSeNet.py:152
↓ 2 callersClassAttentionRefinementModule
eval/lmd/third_part/GPEN/face_parse/model.py:67
↓ 2 callersClassAttentionRefinementModule
preprocess_utils/data_utils/face_parsing/model.py:67
↓ 2 callersClassAttentionRefinementModule
vive3D/BiSeNet.py:152
↓ 2 callersClassBasicBlock
eval/BiSeNet.py:17
next →1–100 of 538, ranked by callers