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

replace curvature with normals

Browse Source
This commit is contained in:
luni
2023-06-01 08:41:53 +00:00
parent a1470cfd6e
commit 534fbfcde1
4 changed files with 214 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/abl_norm.py
+192
View File
@@ -0,0 +1,192 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '0'
config['name'] = 'abl_torch_norm'
config['notes'] = ''
config['tags'] = ['iccv', 'abl_norm', 'torch']
config['script'] = 'scripts/cvae.py'
config['pretrained_model'] = ''
config['use_skinning'] = True # and deshaping
config['remove_global_orientation'] = True
config['use_normals'] = 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_normals'], 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_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'] = False
config['is_cape'] = False
config['device'] = 'cuda'
config['train_dir'] = '/data-local/127/train'
config['valid_dir'] = '/data-local/127/valid'
config['test_dir'] = '/data-net/dataset/test_ready'
config['train_frames'] = None
config['valid_frames'] = None
config['static_model'] = 'checkpoints/iccv/static_torch_orig_2'
config['body_model'] = 'checkpoints/iccv/body_torch_1'
config['normals_model'] = 'checkpoints/iccv/torch/norm_torch_1'
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_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']['is_label'] = True
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'
models/cvae_model.py
+9 -9
View File
@@ -27,16 +27,16 @@ class CVAE(nn.Module):
if config['body_model'] != '':
load_model(self.body_enc, config['body_model'] + '_enc')
if config['use_curvature']:
self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'], device=config['device'], is_label=True, nr_of_labels=7)
if config['curvature_model'] != '':
load_model(self.curv_enc, config['curvature_model'] + '_enc')
if config['use_normals']:
self.norm_enc : AEEncoder = AEEncoder(config['cond_ae_norm']['encoder_block_settings'], config['cond_ae_norm']['kernel_size'], config['cond_ae_norm']['activation'], device=config['device'])
if config['normals_model'] != '':
load_model(self.norm_enc, config['normals_model'] + '_enc')
if config['freeze_encoders']:
for param in self.static_enc.parameters(): param.requires_grad = False
for param in self.body_enc.parameters(): param.requires_grad = False
if config['use_curvature']:
for param in self.curv_enc.parameters(): param.requires_grad = False
if config['use_normals']:
for param in self.norm_enc.parameters(): param.requires_grad = False
self.encoder = VariationalEncoder(config['cvae']['encoder_block_settings'], config['cvae']['kernel_size'], config['cvae']['input_features'], device=config['device'])
self.decoder : Decoder = Decoder(config['cvae']['decoder_block_settings'], kernel_size=config['cvae']['kernel_size'], device=config['device'])
@@ -48,7 +48,7 @@ class CVAE(nn.Module):
else:
self.avg_garment = None
self.use_curvature = config['use_curvature']
self.use_normals = config['use_normals']
self.use_offsets_over_body = not config['use_skinning']
if self.use_offsets_over_body:
@@ -98,8 +98,8 @@ class CVAE(nn.Module):
def encode_conds(self, uv_template, uv_body_posed, uv_curv):
z_body = self.body_enc(uv_body_posed)
z_static = self.static_enc(uv_template)
if self.use_curvature:
z_curv = self.curv_enc(uv_curv)
if self.use_normals:
z_curv = self.norm_enc(uv_curv)
z_cond = torch.concat([z_static, z_body, z_curv], dim=1)
else:
z_cond = torch.concat([z_static, z_body], dim=1)
run.py
+1 -1
View File
@@ -1,6 +1,6 @@
import os
import sys
from configs.pyr_64_cape_m import config
from configs.abl_norm import config
import argparse
# parser = argparse.ArgumentParser(description='')
scripts/cvae.py
+12 -10
View File
@@ -13,7 +13,8 @@ args = vars(parser.parse_args())
config_module = importlib.import_module(args['config'])
config = config_module.config
if args['debug']:
pass
from configs.abl_norm import config
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
if args['debug']:
@@ -83,7 +84,7 @@ def train_step(batch):
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
model.train()
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']])
mesh_pred = uv2mesh(pred)
if config['use_skinning']:
@@ -139,7 +140,7 @@ def valid_step(batch):
model.eval()
with torch.inference_mode():
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']])
mesh_pred = uv2mesh(pred)
if config['use_skinning']:
@@ -188,15 +189,16 @@ def plot_everything(batch: dict, type: str):
model.eval()
with torch.inference_mode():
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']])
mesh_pred = uv2mesh(pred).detach().cpu().numpy()
orig_img = torch.permute(uv_orig, [0,2,3,1])
uv_static_img = torch.permute(batch['uv_static'], [0,2,3,1])
uv_body_posed_img = torch.permute(batch['uv_body_posed'], [0,2,3,1])
uv_normals_img = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.1) / 2.2
pred_img = torch.permute(pred, [0,2,3,1])
img = torch.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals_img, orig_img, pred_img), axis=2)
imgs = [wandb.Image((img[i].cpu().numpy() + 1) / 2.0) for i in range(4)]
F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
@@ -262,10 +264,10 @@ def sample(folder):
count = 0
for batch in dataset_train:
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
uv_normals = tf.one_hot(batch['uv_normals'], 7)
nr_of_samples=2
pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:]
pose, shape = tf.tile(pose[tf.newaxis,:], [nr_of_samples,1]), tf.tile(shape[tf.newaxis,:], [nr_of_samples,1])
@@ -281,7 +283,7 @@ def sample(folder):
mask = batch['mesh_mask'].numpy().astype(bool)[0]
_, faces = _maskFaces(np.ones((config['smpl_res'], 3)), F, mask)
pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True)
pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True)
mesh_pred_zero = uv2mesh(pred_zero)
mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy()
@@ -457,7 +459,7 @@ def train():
g_balancing_coeff += 1 / 10000
if step % 10000 == 0:
ckpt_saver(model, step, optimizer)
ckpt_saver(model, step, optimizer, None)
step += 1
@@ -491,6 +493,6 @@ if __name__ == '__main__':
if not args['debug']:
# model = torch.compile(model)
wandb.watch(model, log='all', log_freq=1000, log_graph=True)
wandb.watch(model, log='all', log_freq=10000, log_graph=True)
train()