193 lines
6.8 KiB
Python
193 lines
6.8 KiB
Python
from utils.convnext_utils import CNBlockConfig
|
|
|
|
config = dict()
|
|
|
|
config['gpu'] = '4'
|
|
config['name'] = 'cape_03223_SS'
|
|
config['notes'] = ''
|
|
config['tags'] = ['iccv', 'cape_03223_SS', 'torch']
|
|
config['script'] = 'scripts/cvae.py'
|
|
|
|
config['pretrained_model'] = ''
|
|
|
|
config['use_skinning'] = True # and deshaping
|
|
config['remove_global_orientation'] = True
|
|
config['use_curvature'] = True
|
|
config['use_extra_losses'] = True # edge, collision, 3d mesh
|
|
config['use_offsets'] = True
|
|
|
|
config['use_norm_loss'] = True
|
|
|
|
ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
|
|
assert ablation_count == 1 or ablation_count == 0
|
|
|
|
config['avg_garment_path'] = 'custom_data/avg/train_cape_f_03223_SL_2_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv train_no_shape_one_hot_avg_uv
|
|
if config['use_skinning']:
|
|
assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
|
|
|
|
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
|
|
|
|
config['batch_size'] = 4
|
|
config['resolution'] = 512
|
|
config['is_skirt'] = False
|
|
config['dataset_in_memory'] = True
|
|
config['is_cape'] = True
|
|
config['device'] = 'cuda'
|
|
|
|
config['train_dir'] = '/data-local/127/cape_processed/train/female'
|
|
config['valid_dir'] = '/data-local/127/cape_processed/train/female'
|
|
config['test_dir'] = '/data-local/127/cape_processed/train/female'
|
|
config['train_frames'] = 'frames_03223_SS_train_2.txt'
|
|
config['valid_frames'] = 'frames_03223_SS_test_2.txt'
|
|
config['test_frames'] = 'frames_03223_SS_test_2.txt'
|
|
|
|
config['static_model'] = 'checkpoints/iccv/torch/static_torch_cape_f'
|
|
config['body_model'] = 'checkpoints/iccv/torch/body_torch_cape_f'
|
|
config['curvature_model'] = 'checkpoints/iccv/torch/curv_torch_cape_f'
|
|
|
|
config['smpl_res'] = 14475
|
|
if config['is_cape']:
|
|
config['smpl_res'] = 3638
|
|
|
|
config['latent_dim'] = 128
|
|
|
|
###############
|
|
config['lr'] = 0.0001# 0.0001
|
|
###############
|
|
config['starting_balancing_coeff'] = 0.0001
|
|
|
|
config['signature']: set = { 'id',
|
|
'frame_nr',
|
|
'pose_shape',
|
|
'uv_body_posed',
|
|
'mesh_body_posed',
|
|
'mesh_posed',
|
|
'uv_curvature',
|
|
'uv_static',
|
|
'mesh_mask',
|
|
'uv_mask',
|
|
}
|
|
|
|
if config['use_skinning']:
|
|
config['signature'].add('uv_unposed')
|
|
config['signature'].add('mesh_unposed')
|
|
else:
|
|
config['signature'].add('uv_posed')
|
|
|
|
config['upscale_enhancer'] = ''
|
|
config['freeze_encoders'] = True
|
|
config['use_one_hot'] = False
|
|
config['bottleneck_scale'] = 2
|
|
|
|
config['cvae'] = dict()
|
|
config['cvae']['device'] = config['device']
|
|
config['cvae']['is_label'] = False
|
|
config['cvae']['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
|
|
config['cvae']['kernel_size'] = 7
|
|
config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
|
|
config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
|
|
|
|
block_setting = [
|
|
CNBlockConfig(32, 64, 3),
|
|
CNBlockConfig(64, 128, 3),
|
|
CNBlockConfig(128, 256, 3),
|
|
CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
|
|
CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
|
|
]
|
|
|
|
block_setting_reverse = [
|
|
CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
|
|
CNBlockConfig(256, 128, 9),
|
|
CNBlockConfig(128, 64, 9),
|
|
CNBlockConfig(64, 32, 3),
|
|
CNBlockConfig(32, 3, 3),
|
|
]
|
|
|
|
config['cvae']['encoder_block_settings'] = block_setting
|
|
config['cvae']['decoder_block_settings'] = block_setting_reverse
|
|
|
|
|
|
|
|
####################### cond_ae_curv ############################
|
|
config['cond_ae_curv'] = dict()
|
|
config['cond_ae_curv']['device'] = config['device']
|
|
config['cond_ae_curv']['is_label'] = True
|
|
config['cond_ae_curv']['latent_dim'] = config['latent_dim']
|
|
config['cond_ae_curv']['kernel_size'] = 7
|
|
config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
|
|
|
|
block_setting = [
|
|
CNBlockConfig(16, 32, 3),
|
|
CNBlockConfig(32, 64, 3),
|
|
CNBlockConfig(64, 128, 9),
|
|
CNBlockConfig(128, config['cond_ae_curv']['bottleneck_size'], 9),
|
|
CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], None, 3),
|
|
]
|
|
|
|
block_setting_reverse = [
|
|
CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], 128, 3),
|
|
CNBlockConfig(128, 64, 9),
|
|
CNBlockConfig(64, 32, 9),
|
|
CNBlockConfig(32, 16, 3),
|
|
CNBlockConfig(16, 3, 3),
|
|
]
|
|
|
|
config['cond_ae_curv']['encoder_block_settings'] = block_setting
|
|
config['cond_ae_curv']['decoder_block_settings'] = block_setting_reverse
|
|
config['cond_ae_curv']['activation'] = 'tanh'
|
|
|
|
####################### cond_ae_body ############################
|
|
config['cond_ae_body'] = dict()
|
|
config['cond_ae_body']['device'] = config['device']
|
|
config['cond_ae_body']['is_label'] = False
|
|
config['cond_ae_body']['latent_dim'] = config['latent_dim']
|
|
config['cond_ae_body']['kernel_size'] = 7
|
|
config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
|
|
|
|
block_setting = [
|
|
CNBlockConfig(16, 32, 3),
|
|
CNBlockConfig(32, 64, 3),
|
|
CNBlockConfig(64, 128, 9),
|
|
CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
|
|
CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
|
|
]
|
|
|
|
block_setting_reverse = [
|
|
CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
|
|
CNBlockConfig(128, 64, 9),
|
|
CNBlockConfig(64, 32, 9),
|
|
CNBlockConfig(32, 16, 3),
|
|
CNBlockConfig(16, 3, 3),
|
|
]
|
|
|
|
config['cond_ae_body']['encoder_block_settings'] = block_setting
|
|
config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
|
|
config['cond_ae_body']['activation'] = 'tanh'
|
|
|
|
####################### cond_ae_static ############################
|
|
config['cond_ae_static'] = dict()
|
|
config['cond_ae_static']['device'] = config['device']
|
|
config['cond_ae_static']['is_label'] = False
|
|
config['cond_ae_static']['latent_dim'] = config['latent_dim']
|
|
config['cond_ae_static']['kernel_size'] = 7
|
|
config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
|
|
|
|
block_setting = [
|
|
CNBlockConfig(8, 16, 3),
|
|
CNBlockConfig(16, 32, 3),
|
|
CNBlockConfig(32, 64, 3),
|
|
CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
|
|
CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
|
|
]
|
|
|
|
block_setting_reverse = [
|
|
CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
|
|
CNBlockConfig(64, 32, 9),
|
|
CNBlockConfig(32, 16, 3),
|
|
CNBlockConfig(16, 8, 3),
|
|
CNBlockConfig(8, 3, 3),
|
|
]
|
|
|
|
config['cond_ae_static']['encoder_block_settings'] = block_setting
|
|
config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
|
|
config['cond_ae_static']['activation'] = 'tanh' |