luni/cvpr_2023
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

config updates

Browse Source
This commit is contained in:
luni
2023-07-03 22:55:52 +02:00
parent 891a8241b8
commit da706c4197
8 changed files with 1100 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/iccvw/abl_all.py
+3 -1
View File
@@ -34,14 +34,16 @@ config['device'] = 'cuda'
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-net/dataset/test_ready'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
configs/iccvw/abl_all_3.py
+3 -1
View File
@@ -33,14 +33,16 @@ config['device'] = 'cuda'
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-net/dataset/test_ready'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
configs/iccvw/abl_all_skirt.py
+196
View File
@@ -0,0 +1,196 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '2'
config['name'] = 'abl_iccvw_all_skirt'
config['notes'] = 'fixed collision loss, train from zero'
config['tags'] = ['iccv', 'abl_all', 'torch']
config['script'] = 'scripts/cvae.py'
config['pretrained_model'] = ''
config['use_skinning'] = True # and deshaping
config['use_normals'] = True
config['use_extra_losses'] = True # edge, collision, 3d mesh
config['use_norm_loss'] = True
ablation_count = [config['use_skinning'], config['use_normals'], config['use_extra_losses']].count(False)
assert ablation_count == 1 or ablation_count == 0
config['avg_garment_path'] = 'custom_data/avg/train_skirt_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['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'] = True
config['dataset_in_memory'] = False
config['is_cape'] = False
config['device'] = 'cuda'
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['static_model'] = 'checkpoints/iccvw/static_iccvw_1_skirt'
config['body_model'] = 'checkpoints/iccvw/body_iccvw_1_skirt'
config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1_skirt'
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['balancing_activation_limit'] = 0.01
config['signature']: set = { 'id',
'frame_nr',
'pose_shape',
'uv_body_posed',
'mesh_body_posed',
'mesh_posed',
'uv_normals',
'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+3 if config['use_normals'] 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_norm ############################
config['cond_ae_norm'] = dict()
config['cond_ae_norm']['device'] = config['device']
config['cond_ae_norm']['latent_dim'] = config['latent_dim']
config['cond_ae_norm']['kernel_size'] = 7
config['cond_ae_norm']['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_norm']['bottleneck_size'], 9),
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 9),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
config['cond_ae_norm']['encoder_block_settings'] = block_setting
config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
config['cond_ae_norm']['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'
configs/iccvw/pyr_32.py
+3 -1
View File
@@ -30,14 +30,16 @@ config['pyramid']['final_upscale_enhancer'] = ''
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-net/dataset/test_ready'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['dataset_in_memory'] = False
config['resolution'] = None
configs/iccvw/pyr_64.py
+3 -1
View File
@@ -30,14 +30,16 @@ config['pyramid']['final_upscale_enhancer'] = ''
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-net/dataset/test_ready'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['dataset_in_memory'] = False
config['resolution'] = None
configs/iccvw/pyr_64_cape_f.py
+295
View File
@@ -0,0 +1,295 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '2'
config['name'] = 'pyr_iccvw_64_cape_f'
config['notes'] = ''
config['tags'] = ['pyr', 'iccv', 'torch']
config['script'] = 'scripts/cvae_pyramid.py'
config['batch_size'] = 4
config['is_skirt'] = False
config['is_cape'] = True
config['device'] = 'cuda'
config['use_skinning'] = True # and deshaping
config['use_extra_losses'] = True # edge, collision, 3d mesh
config['use_norm_loss'] = True
config['use_normals'] = True
config['pretrained_model'] = ''
config['pretrained_model_iteration'] = ''
config['pyramid'] = dict()
config['pyramid']['resolutions'] = [64]
config['pyramid']['pretrained_pyramid'] = ''
config['pyramid']['pretrained_pyramid_iteration'] = ''
config['pyramid']['final_upscale_enhancer'] = ''
config['train_dir'] = '/data-local/127_2/cape_processed/train/female'
config['valid_dir'] = '/data-local/127_2/cape_processed/test/female'
config['test_dir'] = '/data-local/127_2/cape_processed/test/female'
config['train_frames'] = None
config['valid_frames'] = None
config['dataset_in_memory'] = False
config['resolution'] = None
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['lr'] = 0.0001
config['starting_balancing_coeff'] = 0.001
config['balancing_activation_limit'] = 0.012
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
config['avg_garment_path'] = ''
config['bottleneck_scale'] = 2
config['signature']: set = { 'id',
'frame_nr',
'pose_shape',
'uv_body_posed',
'mesh_body_posed',
'mesh_posed',
'mesh_unposed',
'uv_unposed',
'uv_normals',
'uv_static',
'mesh_mask',
'uv_mask',
}
config['pyramid']['is_label'] = False
# config['pyramid']['add_noise'] = False
# config['pyramid']['noise_amount'] = 0.0
config['pyramid']['loss_weights'] = [1,1,1,1,1]
for res in config['pyramid']['resolutions']:
if res != 512:
res_modifier = '_' + str(res)
config['signature'].add('uv_body_posed' + res_modifier)
config['signature'].add('uv_unposed' + res_modifier)
config['signature'].add('uv_normals' + res_modifier)
config['signature'].add('uv_static' + res_modifier)
config['signature'].add('uv_mask' + res_modifier)
config['static_model'] = 'checkpoints/iccvw/static_iccvw_cape_f'
config['body_model'] = 'checkpoints/iccvw/body_iccvw_cape_f'
config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_cape_f'
config['freeze_encoders'] = True
config['pyramid']['levels'] = []
for res in config['pyramid']['resolutions']:
if res == 512:
level = dict()
level['resolution'] = 512
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 7
level['upscale_enhancer'] = ''
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 3),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 256:
level = dict()
level['resolution'] = 256
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 128, 9),
CNBlockConfig(128, 65, 3),
CNBlockConfig(64, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 128:
level = dict()
level['resolution'] = 128
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 9),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
CNBlockConfig(128, 128, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 64:
level = dict()
level['resolution'] = 64
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 32:
level = dict()
level['resolution'] = 32
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(level['bottleneck_size'], None, 16),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
else:
raise NotImplementedError
####################### cond_ae_norm ############################
config['cond_ae_norm'] = dict()
config['cond_ae_norm']['device'] = config['device']
config['cond_ae_norm']['is_label'] = False
# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
config['cond_ae_norm']['kernel_size'] = 7
config['cond_ae_norm']['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_norm']['bottleneck_size'], 9),
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 9),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
config['cond_ae_norm']['encoder_block_settings'] = block_setting
config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
config['cond_ae_norm']['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'
configs/iccvw/pyr_64_cape_m.py
+295
View File
@@ -0,0 +1,295 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '0'
config['name'] = 'pyr_iccvw_64_cape_m'
config['notes'] = ''
config['tags'] = ['pyr', 'iccv', 'torch']
config['script'] = 'scripts/cvae_pyramid.py'
config['batch_size'] = 4
config['is_skirt'] = False
config['is_cape'] = True
config['device'] = 'cuda'
config['use_skinning'] = True # and deshaping
config['use_extra_losses'] = True # edge, collision, 3d mesh
config['use_norm_loss'] = True
config['use_normals'] = True
config['pretrained_model'] = ''
config['pretrained_model_iteration'] = ''
config['pyramid'] = dict()
config['pyramid']['resolutions'] = [64]
config['pyramid']['pretrained_pyramid'] = ''
config['pyramid']['pretrained_pyramid_iteration'] = ''
config['pyramid']['final_upscale_enhancer'] = ''
config['train_dir'] = '/data-local/127_2/cape_processed/train/male'
config['valid_dir'] = '/data-local/127_2/cape_processed/test/male'
config['test_dir'] = '/data-local/127_2/cape_processed/test/male'
config['train_frames'] = None
config['valid_frames'] = None
config['dataset_in_memory'] = False
config['resolution'] = None
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['lr'] = 0.0001
config['starting_balancing_coeff'] = 0.001
config['balancing_activation_limit'] = 0.012
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
config['avg_garment_path'] = ''
config['bottleneck_scale'] = 2
config['signature']: set = { 'id',
'frame_nr',
'pose_shape',
'uv_body_posed',
'mesh_body_posed',
'mesh_posed',
'mesh_unposed',
'uv_unposed',
'uv_normals',
'uv_static',
'mesh_mask',
'uv_mask',
}
config['pyramid']['is_label'] = False
# config['pyramid']['add_noise'] = False
# config['pyramid']['noise_amount'] = 0.0
config['pyramid']['loss_weights'] = [1,1,1,1,1]
for res in config['pyramid']['resolutions']:
if res != 512:
res_modifier = '_' + str(res)
config['signature'].add('uv_body_posed' + res_modifier)
config['signature'].add('uv_unposed' + res_modifier)
config['signature'].add('uv_normals' + res_modifier)
config['signature'].add('uv_static' + res_modifier)
config['signature'].add('uv_mask' + res_modifier)
config['static_model'] = 'checkpoints/iccvw/static_iccvw_cape_m'
config['body_model'] = 'checkpoints/iccvw/body_torch_cape_m'
config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_cape_m'
config['freeze_encoders'] = True
config['pyramid']['levels'] = []
for res in config['pyramid']['resolutions']:
if res == 512:
level = dict()
level['resolution'] = 512
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 7
level['upscale_enhancer'] = ''
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 3),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 256:
level = dict()
level['resolution'] = 256
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 128, 9),
CNBlockConfig(128, 65, 3),
CNBlockConfig(64, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 128:
level = dict()
level['resolution'] = 128
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 9),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
CNBlockConfig(128, 128, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 64:
level = dict()
level['resolution'] = 64
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 32:
level = dict()
level['resolution'] = 32
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(level['bottleneck_size'], None, 16),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
else:
raise NotImplementedError
####################### cond_ae_norm ############################
config['cond_ae_norm'] = dict()
config['cond_ae_norm']['device'] = config['device']
config['cond_ae_norm']['is_label'] = False
# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
config['cond_ae_norm']['kernel_size'] = 7
config['cond_ae_norm']['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_norm']['bottleneck_size'], 9),
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 9),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
config['cond_ae_norm']['encoder_block_settings'] = block_setting
config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
config['cond_ae_norm']['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'
configs/iccvw/pyr_64_skirt.py
+302
View File
@@ -0,0 +1,302 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '1'
config['name'] = 'pyr_iccvw_64_skirt'
config['notes'] = ''
config['tags'] = ['pyr', 'iccv', 'torch']
config['script'] = 'scripts/cvae_pyramid.py'
config['batch_size'] = 4
config['is_skirt'] = True
config['is_cape'] = False
config['device'] = 'cuda'
config['use_skinning'] = True # and deshaping
config['use_extra_losses'] = True # edge, collision, 3d mesh
config['use_norm_loss'] = True
config['use_normals'] = True
config['pretrained_model'] = ''
config['pretrained_model_iteration'] = ''
config['pyramid'] = dict()
config['pyramid']['resolutions'] = [64]
config['pyramid']['pretrained_pyramid'] = ''
config['pyramid']['pretrained_pyramid_iteration'] = ''
config['pyramid']['final_upscale_enhancer'] = ''
config['train_dir'] = '/data-local/127/cloth3d_processed'
config['valid_dir'] = '/data-local/127/cloth3d_processed'
config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
if config['is_skirt']:
config['train_frames'] = 'frames_train_skirt.txt'
config['valid_frames'] = 'frames_valid_skirt.txt'
config['test_frames'] = 'frames_test_skirt.txt'
else:
config['train_frames'] = 'frames_train.txt'
config['valid_frames'] = 'frames_valid.txt'
config['test_frames'] = 'frames_test.txt'
config['dataset_in_memory'] = False
config['resolution'] = None
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['lr'] = 0.0001
config['starting_balancing_coeff'] = 0.001
config['balancing_activation_limit'] = 0.012
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
config['avg_garment_path'] = ''
config['bottleneck_scale'] = 2
config['signature']: set = { 'id',
'frame_nr',
'pose_shape',
'uv_body_posed',
'mesh_body_posed',
'mesh_posed',
'mesh_unposed',
'uv_unposed',
'uv_normals',
'uv_static',
'mesh_mask',
'uv_mask',
}
config['pyramid']['is_label'] = False
# config['pyramid']['add_noise'] = False
# config['pyramid']['noise_amount'] = 0.0
config['pyramid']['loss_weights'] = [1,1,1,1,1]
for res in config['pyramid']['resolutions']:
if res != 512:
res_modifier = '_' + str(res)
config['signature'].add('uv_body_posed' + res_modifier)
config['signature'].add('uv_unposed' + res_modifier)
config['signature'].add('uv_normals' + res_modifier)
config['signature'].add('uv_static' + res_modifier)
config['signature'].add('uv_mask' + res_modifier)
config['static_model'] = 'checkpoints/iccvw/static_iccvw_1_skirt'
config['body_model'] = 'checkpoints/iccvw/body_iccvw_1_skirt'
config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1_skirt'
config['freeze_encoders'] = True
config['pyramid']['levels'] = []
for res in config['pyramid']['resolutions']:
if res == 512:
level = dict()
level['resolution'] = 512
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 7
level['upscale_enhancer'] = ''
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 3),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 256:
level = dict()
level['resolution'] = 256
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256_skirt'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 128, 9),
CNBlockConfig(128, 65, 3),
CNBlockConfig(64, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 128:
level = dict()
level['resolution'] = 128
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128_skirt'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 9),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
CNBlockConfig(128, 128, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 64:
level = dict()
level['resolution'] = 64
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64_skirt'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(64, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 32:
level = dict()
level['resolution'] = 32
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32_skirt'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
block_setting = [
CNBlockConfig(level['bottleneck_size'], None, 16),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
else:
raise NotImplementedError
####################### cond_ae_norm ############################
config['cond_ae_norm'] = dict()
config['cond_ae_norm']['device'] = config['device']
config['cond_ae_norm']['is_label'] = False
# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
config['cond_ae_norm']['kernel_size'] = 7
config['cond_ae_norm']['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_norm']['bottleneck_size'], 9),
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 9),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
config['cond_ae_norm']['encoder_block_settings'] = block_setting
config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
config['cond_ae_norm']['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'