def __init__(self, opt, test=False):
super().__init__(opt)
self.init_fix()
self.print_loss_info()
self.git_repo_path = "https://github.com/ThibaultGROUEIX/CycleConsistentDeformation/commit/"
self.init_save_dict(opt)
self.ddn_config = config.load_config(self.opt.ddn_config, os.path.join(os.environ['DDN_HOME'], 'configs/default.yaml'))
if test:
self.ddn_config['training']['cycle_length'] = 1
def __init__(self, cfg_path, pointcloud_n, dataset=None, model_file=None):
self.cfg = config.load_config(cfg_path, 'configs/default.yaml')
self.pointcloud_n = pointcloud_n
self.dataset = dataset
self.model = config.get_model(self.cfg, dataset)
# Output directory of psgn model
out_dir = self.cfg['training']['out_dir']
# If model_file not specified, use the one from psgn model
if model_file is None:
model_file = self.cfg['test']['model_file']
# Load model
self.checkpoint_io = CheckpointIO(model=model, checkpoint_dir=out_dir)
self.checkpoint_io.load(model_file)
from im2mesh.checkpoints import CheckpointIO
# Arguments
parser = argparse.ArgumentParser(
description='Train a 3D reconstruction model.')
parser.add_argument('config', type=str, help='Path to config file.')
parser.add_argument('--no-cuda', action='store_true', help='Do not use cuda.')
parser.add_argument(
'--exit-after',
type=int,
default=-1,
help='Checkpoint and exit after specified number of seconds'
'with exit code 2.')
args = parser.parse_args()
cfg = config.load_config(args.config, 'configs/default.yaml')
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda:1" if is_cuda else "cpu")
# Set t0
t0 = time.time()
# Shorthands
out_dir = cfg['training']['out_dir']
batch_size = cfg['training']['batch_size']
backup_every = cfg['training']['backup_every']
exit_after = args.exit_after
model_selection_metric = cfg['training']['model_selection_metric']
if cfg['training']['model_selection_mode'] == 'maximize':
model_selection_sign = 1
import csv
import warnings
# Arguments
parser = argparse.ArgumentParser(
description='Train a 3D reconstruction model.')
parser.add_argument('--no-cuda', action='store_true', help='Do not use cuda.')
parser.add_argument(
'--exit-after',
type=int,
default=-1,
help='Checkpoint and exit after specified number of seconds'
'with exit code 2.')
args = parser.parse_args()
cfg = config.load_config('configs/semseg/onet.yaml', 'configs/default.yaml')
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda" if is_cuda else "cpu")
# Set t0
t0 = time.time()
# Shorthands hardcoded
root = "/visinf/projects_students/VCLabOccNet/test"
out_dir = "out/semseg/onet"
batch_size = 64
backup_every = 500
exit_after = args.exit_after
epoch_limit = 100
model_selection_metric = 'iou_complete'
'--da',
action='store_true',
help=
'Generate using the target dataset, for unsupervised domain adaptation.')
parser.add_argument(
'--generation_dir',
type=str,
default="",
help=
'path of generation dir. If omitted, will use the one in the config yaml')
args = parser.parse_args()
config_yaml_path = glob.glob(os.path.join(args.out_dir, "*.yaml"))
if len(config_yaml_path) != 1:
raise ValueError("no yaml, or more than one yaml")
cfg = config.load_config(config_yaml_path[0], 'configs/default.yaml')
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda:{}".format(args.gpu) if is_cuda else "cpu")
# Shorthands
out_dir = cfg['training']['out_dir']
if args.generation_dir == "":
generation_dir = os.path.join(out_dir, cfg['generation']['generation_dir'])
else:
generation_dir = os.path.join(out_dir, args.generation_dir)
if not args.eval_input:
out_file = os.path.join(generation_dir, 'eval_meshes_full.pkl')
out_file_class = os.path.join(generation_dir, 'eval_meshes.csv')
else:
from collections import defaultdict
import pandas as pd
import tensorflow as tf
from im2mesh import config
from im2mesh.checkpoints import CheckpointIO
from im2mesh.utils.io import export_pointcloud
from im2mesh.utils.visualize import visualize_data
from im2mesh.utils.voxels import VoxelGrid
parser = argparse.ArgumentParser(
description="Extract meshes from occupancy process.")
parser.add_argument("config", type=str, help="Path to config file.")
parser.add_argument("--no-cuda", action="store_true", help="Do not use cuda.")
args = parser.parse_args()
cfg = config.load_config(args.config, "configs/default.yaml")
out_dir = cfg["training"]["out_dir"]
generation_dir = os.path.join(out_dir, cfg["generation"]["generation_dir"])
out_time_file = os.path.join(generation_dir, "time_generation_full.pkl")
out_time_file_class = os.path.join(generation_dir, "time_generation.pkl")
batch_size = cfg["generation"]["batch_size"]
input_type = cfg["data"]["input_type"]
vis_n_outputs = cfg["generation"]["vis_n_outputs"]
if vis_n_outputs is None:
vis_n_outputs = -1
# Model
# Dataset
dataset = config.get_dataset('test',
help="Do not use cuda.",
default=True)
parser.add_argument(
"--exit-after",
type=int,
default=-1,
help=
"Checkpoint and exit after specified number of seconds with exit code 2."
)
args = parser.parse_args()
return args
if __name__ == "__main__":
args = get_args()
cfg = config.load_config(args.config, "configs/shapenet_singleview.yaml")
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda" if is_cuda else "cpu")
# Set t0
t0 = time.time()
# Shorthands
out_dir = cfg['training']['out_dir']
batch_size = cfg['training']['batch_size']
backup_every = cfg['training']['backup_every']
exit_after = args.exit_after
model_selection_metric = cfg['training']['model_selection_metric']
if cfg['training']['model_selection_mode'] == 'maximize':
model_selection_sign = 1
from im2mesh import config, data
from im2mesh.checkpoints import CheckpointIO
# Arguments
parser = argparse.ArgumentParser(
description='Train a 3D reconstruction model.'
)
parser.add_argument('config', type=str, help='Path to config file.')
parser.add_argument('--no-cuda', action='store_true', help='Do not use cuda.')
parser.add_argument('--exit-after', type=int, default=-1,
help='Checkpoint and exit after specified number of seconds'
'with exit code 2.')
args = parser.parse_args()
cfg = config.load_config(args.config, '/home/hpclab/kyg/occupancy_networks/configs/default.yaml')
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda" if is_cuda else "cpu")
# Set t0
t0 = time.time()
# Shorthands
out_dir = cfg['training']['out_dir']
batch_size = cfg['training']['batch_size']
backup_every = cfg['training']['backup_every']
exit_after = args.exit_after
model_selection_metric = cfg['training']['model_selection_metric']
if cfg['training']['model_selection_mode'] == 'maximize':
model_selection_sign = 1
def SMPLD_register(args):
cfg = config.load_config(args.config, 'configs/default.yaml')
out_dir = cfg['training']['out_dir']
generation_dir = os.path.join(out_dir, cfg['generation']['generation_dir'])
is_cuda = (torch.cuda.is_available() and not args.no_cuda)
device = torch.device("cuda" if is_cuda else "cpu")
if args.subject_idx >= 0 and args.sequence_idx >= 0:
logger, _ = create_logger(generation_dir, phase='reg_subject{}_sequence{}'.format(args.subject_idx, args.sequence_idx), create_tf_logs=False)
else:
logger, _ = create_logger(generation_dir, phase='reg_all', create_tf_logs=False)
# Get dataset
if args.subject_idx >= 0 and args.sequence_idx >= 0:
dataset = config.get_dataset('test', cfg, sequence_idx=args.sequence_idx, subject_idx=args.subject_idx)
else:
dataset = config.get_dataset('test', cfg)
batch_size = cfg['generation']['batch_size']
# Loader
test_loader = torch.utils.data.DataLoader(
dataset, batch_size=batch_size, num_workers=1, shuffle=False)
model_counter = defaultdict(int)
# Set optimization hyper parameters
iterations, pose_iterations, steps_per_iter, pose_steps_per_iter = 3, 2, 30, 30
inner_dists = []
outer_dists = []
for it, data in enumerate(tqdm(test_loader)):
idxs = data['idx'].cpu().numpy()
loc = data['points.loc'].cpu().numpy()
batch_size = idxs.shape[0]
# Directories to load corresponding informations
mesh_dir = os.path.join(generation_dir, 'meshes') # directory for posed and (optionally) unposed implicit outer/inner meshes
label_dir = os.path.join(generation_dir, 'labels') # directory for part labels
register_dir = os.path.join(generation_dir, 'registrations') # directory for part labels
if args.use_raw_scan:
scan_dir = dataset.dataset_folder # this is the folder that contains CAPE raw scans
else:
scan_dir = None
all_posed_minimal_meshes = []
all_posed_cloth_meshes = []
all_posed_vertices = []
all_unposed_vertices = []
scan_part_labels = []
for idx in idxs:
model_dict = dataset.get_model_dict(idx)
subset = model_dict['subset']
subject = model_dict['subject']
sequence = model_dict['sequence']
gender = model_dict['gender']
filebase = os.path.basename(model_dict['data_path'])[:-4]
folder_name = os.path.join(subset, subject, sequence)
# TODO: we assume batch size stays the same if one resumes the job
# can be more flexible to support different batch sizes before and
# after resume
register_file = os.path.join(register_dir, folder_name, filebase + 'minimal.registered.ply')
if os.path.exists(register_file):
# batch already computed, break
break
# points_dict = np.load(model_dict['data_path'])
# gender = str(points_dict['gender'])
mesh_dir_ = os.path.join(mesh_dir, folder_name)
label_dir_ = os.path.join(label_dir, folder_name)
if scan_dir is not None:
scan_dir_ = os.path.join(scan_dir, subject, sequence)
# Load part labels and vertex translations
label_file_name = filebase + '.minimal.npz'
label_dict = dict(np.load(os.path.join(label_dir_, label_file_name)))
labels = torch.tensor(label_dict['part_labels'].astype(np.int64)).to(device) # part labels for each vertex (14 or 24)
scan_part_labels.append(labels)
# Load minimal implicit surfaces
mesh_file_name = filebase + '.minimal.posed.ply'
# posed_mesh = Mesh(filename=os.path.join(mesh_dir_, mesh_file_name))
posed_mesh = trimesh.load(os.path.join(mesh_dir_, mesh_file_name), process=False)
posed_vertices = np.array(posed_mesh.vertices)
all_posed_vertices.append(posed_vertices)
posed_mesh = tm.from_tensors(torch.tensor(posed_mesh.vertices.astype('float32'), requires_grad=False, device=device),
torch.tensor(posed_mesh.faces.astype('int64'), requires_grad=False, device=device))
all_posed_minimal_meshes.append(posed_mesh)
mesh_file_name = filebase + '.minimal.unposed.ply'
if os.path.exists(os.path.join(mesh_dir_, mesh_file_name)) and args.init_pose:
# unposed_mesh = Mesh(filename=os.path.join(mesh_dir_, mesh_file_name))
unposed_mesh = trimesh.load(os.path.join(mesh_dir_, mesh_file_name), process=False)
unposed_vertices = np.array(unposed_mesh.vertices)
all_unposed_vertices.append(unposed_vertices)
if args.use_raw_scan:
# Load raw scans
mesh_file_name = filebase + '.ply'
# posed_mesh = Mesh(filename=os.path.join(scan_dir_, mesh_file_name))
posed_mesh = trimesh.load(os.path.join(scan_dir_, mesh_file_name), process=False)
posed_mesh = tm.from_tensors(torch.tensor(posed_mesh.vertices.astype('float32') / 1000, requires_grad=False, device=device),
torch.tensor(posed_mesh.faces.astype('int64'), requires_grad=False, device=device))
all_posed_cloth_meshes.append(posed_mesh)
else:
# Load clothed implicit surfaces
mesh_file_name = filebase + '.cloth.posed.ply'
# posed_mesh = Mesh(filename=os.path.join(mesh_dir_, mesh_file_name))
posed_mesh = trimesh.load(os.path.join(mesh_dir_, mesh_file_name), process=False)
posed_mesh = tm.from_tensors(torch.tensor(posed_mesh.vertices.astype('float32'), requires_grad=False, device=device),
torch.tensor(posed_mesh.faces.astype('int64'), requires_grad=False, device=device))
all_posed_cloth_meshes.append(posed_mesh)
if args.num_joints == 24:
bm = BodyModel(bm_path='body_models/smpl/male/model.pkl', num_betas=10, batch_size=batch_size).to(device)
parents = bm.kintree_table[0].detach().cpu().numpy()
labels = bm.weights.argmax(1)
# Convert 24 parts to 14 parts
smpl2ipnet = torch.from_numpy(SMPL2IPNET_IDX).to(device)
labels = smpl2ipnet[labels].clone().unsqueeze(0)
del bm
elif args.num_joints == 14:
with open('body_models/misc/smpl_parts_dense.pkl', 'rb') as f:
part_labels = pkl.load(f)
labels = np.zeros((6890,), dtype=np.int64)
for n, k in enumerate(part_labels):
labels[part_labels[k]] = n
labels = torch.tensor(labels).to(device).unsqueeze(0)
else:
raise ValueError('Got {} joints but umber of joints can only be either 14 or 24'.format(args.num_joints))
th_faces = torch.tensor(smpl_faces.astype('float32'), dtype=torch.long).to(device)
# We assume loaded meshes are properly scaled and offsetted to the orignal SMPL space,
if len(all_posed_minimal_meshes) > 0 and len(all_unposed_vertices) == 0:
# IPNet optimization without vertex traslation
# raise NotImplementedError('Optimization for IPNet is not implemented yet.')
if args.num_joints == 24:
for idx in range(len(scan_part_labels)):
scan_part_labels[idx] = smpl2ipnet[scan_part_labels[idx]].clone()
prior = get_prior(gender=gender, precomputed=True)
pose_init = torch.zeros((batch_size, 72))
pose_init[:, 3:] = prior.mean
betas, pose, trans = torch.zeros((batch_size, 10)), pose_init, torch.zeros((batch_size, 3))
# Init SMPL, pose with mean smpl pose, as in ch.registration
smpl = th_batch_SMPL(batch_size, betas, pose, trans, faces=th_faces, gender=gender).to(device)
smpl_part_labels = torch.cat([labels] * batch_size, axis=0)
# Optimize pose first
optimize_pose_only(all_posed_minimal_meshes, smpl, pose_iterations, pose_steps_per_iter, scan_part_labels,
smpl_part_labels, None, args)
# Optimize pose and shape
optimize_pose_shape(all_posed_minimal_meshes, smpl, iterations, steps_per_iter, scan_part_labels, smpl_part_labels,
None, args)
inner_vertices, _, _, _ = smpl()
# Optimize vertices for SMPLD
init_smpl_meshes = [tm.from_tensors(vertices=v.clone().detach(),
faces=smpl.faces) for v in inner_vertices]
optimize_offsets(all_posed_cloth_meshes, smpl, init_smpl_meshes, 5, 10, args)
outer_vertices, _, _, _ = smpl()
elif len(all_posed_minimal_meshes) > 0:
# NASA+PTFs optimization with vertex traslations
# Compute poses from implicit surfaces and correspondences
# TODO: we could also compute bone-lengths if we train PTFs to predict A-pose with a global translation
# that equals to the centroid of the pointcloud
poses = compute_poses(all_posed_vertices, all_unposed_vertices, scan_part_labels, parents, args)
# Convert 24 parts to 14 parts
for idx in range(len(scan_part_labels)):
scan_part_labels[idx] = smpl2ipnet[scan_part_labels[idx]].clone()
pose_init = torch.from_numpy(poses).float()
betas, pose, trans = torch.zeros((batch_size, 10)), pose_init, torch.zeros((batch_size, 3))
# Init SMPL, pose with mean smpl pose, as in ch.registration
smpl = th_batch_SMPL(batch_size, betas, pose, trans, faces=th_faces, gender=gender).to(device)
smpl_part_labels = torch.cat([labels] * batch_size, axis=0)
# Optimize pose first
optimize_pose_only(all_posed_minimal_meshes, smpl, pose_iterations, pose_steps_per_iter, scan_part_labels,
smpl_part_labels, None, args)
# Optimize pose and shape
optimize_pose_shape(all_posed_minimal_meshes, smpl, iterations, steps_per_iter, scan_part_labels, smpl_part_labels,
None, args)
inner_vertices, _, _, _ = smpl()
# Optimize vertices for SMPLD
init_smpl_meshes = [tm.from_tensors(vertices=v.clone().detach(),
faces=smpl.faces) for v in inner_vertices]
optimize_offsets(all_posed_cloth_meshes, smpl, init_smpl_meshes, 5, 10, args)
outer_vertices, _, _, _ = smpl()
else:
inner_vertices = outer_vertices = None
if args.use_raw_scan:
for i, idx in enumerate(idxs):
model_dict = dataset.get_model_dict(idx)
subset = model_dict['subset']
subject = model_dict['subject']
sequence = model_dict['sequence']
filebase = os.path.basename(model_dict['data_path'])[:-4]
folder_name = os.path.join(subset, subject, sequence)
register_dir_ = os.path.join(register_dir, folder_name)
if not os.path.exists(register_dir_):
os.makedirs(register_dir_)
if not os.path.exists(os.path.join(register_dir_, filebase + 'minimal.registered.ply')):
registered_mesh = trimesh.Trimesh(inner_vertices[i].detach().cpu().numpy().astype(np.float64), smpl_faces, process=False)
registered_mesh.export(os.path.join(register_dir_, filebase + 'minimal.registered.ply'))
if not os.path.exists(os.path.join(register_dir_, filebase + 'cloth.registered.ply')):
registered_mesh = trimesh.Trimesh(outer_vertices[i].detach().cpu().numpy().astype(np.float64), smpl_faces, process=False)
registered_mesh.export(os.path.join(register_dir_, filebase + 'cloth.registered.ply'))
else:
# Evaluate registered mesh
gt_smpl_mesh = data['points.minimal_smpl_vertices'].to(device)
gt_smpld_mesh = data['points.smpl_vertices'].to(device)
if inner_vertices is None:
# if vertices are None, we assume they already exist due to previous runs
inner_vertices = []
outer_vertices = []
for i, idx in enumerate(idxs):
model_dict = dataset.get_model_dict(idx)
subset = model_dict['subset']
subject = model_dict['subject']
sequence = model_dict['sequence']
filebase = os.path.basename(model_dict['data_path'])[:-4]
folder_name = os.path.join(subset, subject, sequence)
register_dir_ = os.path.join(register_dir, folder_name)
# registered_mesh = Mesh(filename=os.path.join(register_dir_, filebase + 'minimal.registered.ply'))
registered_mesh = trimesh.load(os.path.join(register_dir_, filebase + 'minimal.registered.ply'), process=False)
registered_v = torch.tensor(registered_mesh.vertices.astype(np.float32), requires_grad=False, device=device)
inner_vertices.append(registered_v)
# registered_mesh = Mesh(filename=os.path.join(register_dir_, filebase + 'cloth.registered.ply'))
registered_mesh = trimesh.load(os.path.join(register_dir_, filebase + 'cloth.registered.ply'), process=False)
registered_v = torch.tensor(registered_mesh.vertices.astype(np.float32), requires_grad=False, device=device)
outer_vertices.append(registered_v)
inner_vertices = torch.stack(inner_vertices, dim=0)
outer_vertices = torch.stack(outer_vertices, dim=0)
inner_dist = torch.norm(gt_smpl_mesh - inner_vertices, dim=2).mean(-1)
outer_dist = torch.norm(gt_smpld_mesh - outer_vertices, dim=2).mean(-1)
for i, idx in enumerate(idxs):
model_dict = dataset.get_model_dict(idx)
subset = model_dict['subset']
subject = model_dict['subject']
sequence = model_dict['sequence']
filebase = os.path.basename(model_dict['data_path'])[:-4]
folder_name = os.path.join(subset, subject, sequence)
register_dir_ = os.path.join(register_dir, folder_name)
if not os.path.exists(register_dir_):
os.makedirs(register_dir_)
logger.info('Inner distance for input {}: {} cm'.format(filebase, inner_dist[i].item()))
logger.info('Outer distance for input {}: {} cm'.format(filebase, outer_dist[i].item()))
if not os.path.exists(os.path.join(register_dir_, filebase + 'minimal.registered.ply')):
registered_mesh = trimesh.Trimesh(inner_vertices[i].detach().cpu().numpy().astype(np.float64), smpl_faces, process=False)
registered_mesh.export(os.path.join(register_dir_, filebase + 'minimal.registered.ply'))
if not os.path.exists(os.path.join(register_dir_, filebase + 'cloth.registered.ply')):
registered_mesh = trimesh.Trimesh(outer_vertices[i].detach().cpu().numpy().astype(np.float64), smpl_faces, process=False)
registered_mesh.export(os.path.join(register_dir_, filebase + 'cloth.registered.ply'))
inner_dists.extend(inner_dist.detach().cpu().numpy())
outer_dists.extend(outer_dist.detach().cpu().numpy())
logger.info('Mean inner distance: {} cm'.format(np.mean(inner_dists)))
logger.info('Mean outer distance: {} cm'.format(np.mean(outer_dists)))