186 lines
3.5 KiB
YAML
186 lines
3.5 KiB
YAML
dataset_params:
|
|
root_dir: ./data/voxceleb1-png/
|
|
split_len:
|
|
frame_shape: [256, 256, 3]
|
|
id_sampling: True
|
|
pairs_list:
|
|
augmentation_params:
|
|
flip_param:
|
|
horizontal_flip: True
|
|
time_flip: True
|
|
jitter_param:
|
|
brightness: 0.1
|
|
contrast: 0.1
|
|
saturation: 0.1
|
|
hue: 0.1
|
|
|
|
dense_motion:
|
|
block_expansion: 64
|
|
max_features: 1024
|
|
num_blocks: 5
|
|
scale_factor: 0.25
|
|
num_kp: 10
|
|
num_channels: 3
|
|
estimate_occlusion_map: True
|
|
fomm_kp_detector:
|
|
block_expansion: 32
|
|
num_kp: 10
|
|
num_channels: 3
|
|
max_features: 1024
|
|
num_blocks: 5
|
|
temperature: 0.1
|
|
scale_factor: 0.25
|
|
estimate_jacobian: True
|
|
estimate_occlusion: False
|
|
tpsm_kp_detector:
|
|
num_tps: 10
|
|
tpsm_dense_motion:
|
|
block_expansion: 64
|
|
max_features: 1024
|
|
num_blocks: 5
|
|
scale_factor: 0.25
|
|
num_tps: 10
|
|
num_channels: 3
|
|
|
|
raft_flow:
|
|
prior_only: False
|
|
num_kp: 10
|
|
dim: 256
|
|
size: 256
|
|
generator:
|
|
num_channels: 3
|
|
block_expansion: 64
|
|
max_features: 512
|
|
num_up_blocks: 5
|
|
driving_encoder:
|
|
in_features: 10
|
|
block_expansion: 32
|
|
max_features: 512
|
|
num_blocks: 5
|
|
source_encoder:
|
|
in_features: 13
|
|
block_expansion: 32
|
|
max_features: 512
|
|
num_blocks: 5
|
|
|
|
train_params:
|
|
## [mtia, tpsm, fomm]
|
|
prior_model: mtia
|
|
num_epochs: 100
|
|
num_repeats: 150
|
|
epoch_milestones: [60, 90]
|
|
# ### enable this for tpsm
|
|
# epoch_milestones: [70, 90]
|
|
# ### enable this for tpsm
|
|
|
|
lr: 2.0e-4
|
|
batch_size: 80
|
|
scales: [1, 0.5, 0.25, 0.125]
|
|
clip_grad: True
|
|
clip: 10
|
|
bg_start: 1000
|
|
checkpoint_freq: 100
|
|
### for tpsm
|
|
dropout_epoch: 35
|
|
dropout_maxp: 0.3
|
|
dropout_startp: 0.1
|
|
dropout_inc_epoch: 10
|
|
### for tpsm
|
|
|
|
transform_params:
|
|
sigma_affine: 0.05
|
|
sigma_tps: 0.005
|
|
points_tps: 5
|
|
loss_weights:
|
|
perceptual: [10, 10, 10, 10, 10]
|
|
equivariance: 10
|
|
equivariance_jacobian: 10
|
|
# ### enable this for tpsm
|
|
# equivariance_jacobian: 0
|
|
# ### enable this for tpsm
|
|
|
|
reconstruction_params:
|
|
num_videos: 1000
|
|
format: '.mp4'
|
|
|
|
animate_params:
|
|
num_pairs: 50
|
|
format: '.mp4'
|
|
normalization_params:
|
|
adapt_movement_scale: False
|
|
use_relative_movement: True
|
|
use_relative_jacobian: True
|
|
|
|
visualizer_params:
|
|
draw_border: True
|
|
colormap: 'gist_rainbow'
|
|
|
|
mtia_kp_detector:
|
|
MODEL:
|
|
ESTIMATE_JACOBIAN: True
|
|
DATA_PREPROCESS: False
|
|
FIX_IMG2MOTION_ATTENTION: False
|
|
TRANSFORMER_DEPTH: 12
|
|
TRANSFORMER_HEADS: 8
|
|
DIM: 192 # 4*4*3
|
|
INIT_WEIGHTS: False
|
|
NAME: pose_tokenpose_b
|
|
NUM_JOINTS: 10
|
|
PRETRAINED: ''
|
|
PATCH_SIZE: [4, 4]
|
|
IMAGE_SIZE: [256, 256]
|
|
HEATMAP_SIZE: [64, 64]
|
|
|
|
## default
|
|
TAG_PER_JOINT: True
|
|
HIDDEN_HEATMAP_DIM: -1
|
|
MULTI_TRANSFORMER_DEPTH: [12, 12]
|
|
MULTI_TRANSFORMER_HEADS: [16, 16]
|
|
MULTI_DIM: [48, 48]
|
|
NUM_BRANCHES: 1
|
|
BASE_CHANNEL: 32
|
|
TRANSFORMER_MLP_RATIO: 3
|
|
POS_EMBEDDING_TYPE: 'sine-full'
|
|
TEMPERATURE: 0.1
|
|
TARGET_TYPE: gaussian
|
|
INIT: True
|
|
|
|
SIGMA: 2
|
|
EXTRA:
|
|
PRETRAINED_LAYERS:
|
|
- 'conv1'
|
|
- 'bn1'
|
|
- 'conv2'
|
|
- 'bn2'
|
|
- 'layer1'
|
|
- 'transition1'
|
|
- 'stage2'
|
|
- 'transition2'
|
|
- 'stage3'
|
|
FINAL_CONV_KERNEL: 1
|
|
STAGE2:
|
|
NUM_MODULES: 1
|
|
NUM_BRANCHES: 2
|
|
BLOCK: BASIC
|
|
NUM_BLOCKS:
|
|
- 4
|
|
- 4
|
|
NUM_CHANNELS:
|
|
- 32
|
|
- 64
|
|
FUSE_METHOD: SUM
|
|
STAGE3:
|
|
NUM_MODULES: 4
|
|
NUM_BRANCHES: 3
|
|
BLOCK: BASIC
|
|
NUM_BLOCKS:
|
|
- 4
|
|
- 4
|
|
- 4
|
|
NUM_CHANNELS:
|
|
- 32
|
|
- 64
|
|
- 128
|
|
FUSE_METHOD: SUM
|
|
## default
|
|
|