Delete animation/SadTalker directory

animation/SadTalker/src/config/auido2exp.yaml

@@ -1,58 +0,0 @@
-DATASET:
-  TRAIN_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/file_list/train.txt
-  EVAL_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/file_list/val.txt
-  TRAIN_BATCH_SIZE: 32
-  EVAL_BATCH_SIZE: 32
-  EXP: True
-  EXP_DIM: 64
-  FRAME_LEN: 32
-  COEFF_LEN: 73
-  NUM_CLASSES: 46
-  AUDIO_ROOT_PATH: /apdcephfs_cq2/share_1290939/wenxuazhang/voxceleb1/wav
-  COEFF_ROOT_PATH: /apdcephfs_cq2/share_1290939/wenxuazhang/voxceleb1/wav2lip_3dmm
-  LMDB_PATH: /apdcephfs_cq2/share_1290939/shadowcun/datasets/VoxCeleb/v1/imdb
-  DEBUG: True
-  NUM_REPEATS: 2
-  T: 40
-  
-
-MODEL:
-  FRAMEWORK: V2
-  AUDIOENCODER:
-    LEAKY_RELU: True
-    NORM: 'IN'
-  DISCRIMINATOR:
-    LEAKY_RELU: False
-    INPUT_CHANNELS: 6
-  CVAE:
-    AUDIO_EMB_IN_SIZE: 512
-    AUDIO_EMB_OUT_SIZE: 128
-    SEQ_LEN: 32
-    LATENT_SIZE: 256
-    ENCODER_LAYER_SIZES: [192, 1024]
-    DECODER_LAYER_SIZES: [1024, 192]
-    
-
-TRAIN:
-  MAX_EPOCH: 300
-  GENERATOR:
-    LR: 2.0e-5
-  DISCRIMINATOR:
-    LR: 1.0e-5
-  LOSS:
-    W_FEAT: 0
-    W_COEFF_EXP: 2
-    W_LM: 1.0e-2
-    W_LM_MOUTH: 0
-    W_REG: 0
-    W_SYNC: 0
-    W_COLOR: 0
-    W_EXPRESSION: 0
-    W_LIPREADING: 0.01
-    W_LIPREADING_VV: 0
-    W_EYE_BLINK: 4
-
-TAG:
-  NAME:  small_dataset
-
-

animation/SadTalker/src/config/auido2pose.yaml

@@ -1,49 +0,0 @@
-DATASET:
-  TRAIN_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/audio2pose_unet_noAudio/dataset/train_33.txt
-  EVAL_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/audio2pose_unet_noAudio/dataset/val.txt
-  TRAIN_BATCH_SIZE: 64
-  EVAL_BATCH_SIZE: 1
-  EXP: True
-  EXP_DIM: 64
-  FRAME_LEN: 32
-  COEFF_LEN: 73
-  NUM_CLASSES: 46
-  AUDIO_ROOT_PATH: /apdcephfs_cq2/share_1290939/wenxuazhang/voxceleb1/wav
-  COEFF_ROOT_PATH: /apdcephfs_cq2/share_1290939/shadowcun/datasets/VoxCeleb/v1/imdb
-  DEBUG: True
-  
-
-MODEL:
-  AUDIOENCODER:
-    LEAKY_RELU: True
-    NORM: 'IN'
-  DISCRIMINATOR:
-    LEAKY_RELU: False
-    INPUT_CHANNELS: 6
-  CVAE:
-    AUDIO_EMB_IN_SIZE: 512
-    AUDIO_EMB_OUT_SIZE: 6
-    SEQ_LEN: 32
-    LATENT_SIZE: 64
-    ENCODER_LAYER_SIZES: [192, 128]
-    DECODER_LAYER_SIZES: [128, 192]
-    
-
-TRAIN:
-  MAX_EPOCH: 150
-  GENERATOR:
-    LR: 1.0e-4
-  DISCRIMINATOR:
-    LR: 1.0e-4
-  LOSS:
-    LAMBDA_REG: 1
-    LAMBDA_LANDMARKS: 0
-    LAMBDA_VERTICES: 0
-    LAMBDA_GAN_MOTION: 0.7
-    LAMBDA_GAN_COEFF: 0
-    LAMBDA_KL: 1
-
-TAG:
-  NAME: cvae_UNET_useAudio_usewav2lipAudioEncoder
-
-

animation/SadTalker/src/config/facerender.yaml

@@ -1,45 +0,0 @@
-model_params:
-  common_params:
-    num_kp: 15 
-    image_channel: 3                    
-    feature_channel: 32
-    estimate_jacobian: False   # True
-  kp_detector_params:
-     temperature: 0.1
-     block_expansion: 32            
-     max_features: 1024
-     scale_factor: 0.25         # 0.25
-     num_blocks: 5
-     reshape_channel: 16384  # 16384 = 1024 * 16
-     reshape_depth: 16
-  he_estimator_params:
-     block_expansion: 64            
-     max_features: 2048
-     num_bins: 66
-  generator_params:
-    block_expansion: 64
-    max_features: 512
-    num_down_blocks: 2
-    reshape_channel: 32
-    reshape_depth: 16         # 512 = 32 * 16
-    num_resblocks: 6
-    estimate_occlusion_map: True
-    dense_motion_params:
-      block_expansion: 32
-      max_features: 1024
-      num_blocks: 5
-      reshape_depth: 16
-      compress: 4
-  discriminator_params:
-    scales: [1]
-    block_expansion: 32                 
-    max_features: 512
-    num_blocks: 4
-    sn: True
-  mapping_params:
-      coeff_nc: 70
-      descriptor_nc: 1024
-      layer: 3
-      num_kp: 15
-      num_bins: 66
-

animation/SadTalker/src/config/facerender_still.yaml

@@ -1,45 +0,0 @@
-model_params:
-  common_params:
-    num_kp: 15 
-    image_channel: 3                    
-    feature_channel: 32
-    estimate_jacobian: False   # True
-  kp_detector_params:
-     temperature: 0.1
-     block_expansion: 32            
-     max_features: 1024
-     scale_factor: 0.25         # 0.25
-     num_blocks: 5
-     reshape_channel: 16384  # 16384 = 1024 * 16
-     reshape_depth: 16
-  he_estimator_params:
-     block_expansion: 64            
-     max_features: 2048
-     num_bins: 66
-  generator_params:
-    block_expansion: 64
-    max_features: 512
-    num_down_blocks: 2
-    reshape_channel: 32
-    reshape_depth: 16         # 512 = 32 * 16
-    num_resblocks: 6
-    estimate_occlusion_map: True
-    dense_motion_params:
-      block_expansion: 32
-      max_features: 1024
-      num_blocks: 5
-      reshape_depth: 16
-      compress: 4
-  discriminator_params:
-    scales: [1]
-    block_expansion: 32                 
-    max_features: 512
-    num_blocks: 4
-    sn: True
-  mapping_params:
-      coeff_nc: 73
-      descriptor_nc: 1024
-      layer: 3
-      num_kp: 15
-      num_bins: 66
-