steffen/Labeling-Primitives-With-Point2Net
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Labels can now be placed along next to the points within the datasetfile

Browse Source
This commit is contained in:
Si11ium 2019-08-06 08:36:59 +02:00
parent 54a5b48ddc
commit 97e36df1ba
2 changed files with 41 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
dataset/shapenet.py
View File

@ -23,16 +23,15 @@ class CustomShapeNet(InMemoryDataset):
categories = {key: val for val, key in enumerate(['Box', 'Cone', 'Cylinder', 'Sphere'])} categories = {key: val for val, key in enumerate(['Box', 'Cone', 'Cylinder', 'Sphere'])}
modes = {key: val for val, key in enumerate(['train', 'test', 'predict'])} modes = {key: val for val, key in enumerate(['train', 'test', 'predict'])}
def __init__(self, root, collate_per_segment=True, mode='train', transform=None, pre_filter=None, pre_transform=None, def __init__(self, root_dir, collate_per_segment=True, mode='train', transform=None, pre_filter=None,
headers=True, has_variations=False, refresh=False): pre_transform=None, headers=True, has_variations=False, refresh=False, labels_within=False):
assert mode in self.modes.keys(), f'"mode" must be one of {self.modes.keys()}' assert mode in self.modes.keys(), f'"mode" must be one of {self.modes.keys()}'
assert not (collate_per_segment and has_variations), 'Either use each element or pointclouds - with variations' assert not (collate_per_segment and has_variations), 'Either use each element or pointclouds - with variations'
self.has_headers = headers
self.has_variations = has_variations #Set the Dataset Parameters
self.collate_per_element = collate_per_segment self.has_headers, self.has_variations, self.labels_within = headers, has_variations, labels_within
self.mode = mode self.collate_per_element, self.mode, self.refresh = collate_per_segment, mode, refresh
self.refresh = refresh super(CustomShapeNet, self).__init__(root_dir, transform, pre_transform, pre_filter)
super(CustomShapeNet, self).__init__(root, transform, pre_transform, pre_filter)
self.data, self.slices = self._load_dataset() self.data, self.slices = self._load_dataset()
print("Initialized") print("Initialized")
@ -116,19 +115,6 @@ class CustomShapeNet(InMemoryDataset):
if pattern.match(os.path.split(element)[-1]): if pattern.match(os.path.split(element)[-1]):
continue continue
else: else:
# The following two lines were intendations
# check if it is "just" a pc.dat or pc.xyz
# if all([x not in os.path.split(element)[-1] for x in ['pc.dat', 'pc.xyz']]):
# Assign training data to the data container
# Following the original logic;
# y should be the label;
# pos should be the six dimensional vector describing: !its pos not points!!
# x,y,z,x_rot,y_rot,z_rot
# Get the y - Label
y_raw = next(i for i, v in enumerate(self.categories.keys()) if v.lower() in element.lower())
# y_raw = os.path.splitext(element)[0].split('_')[-2]
with open(element,'r') as f: with open(element,'r') as f:
if self.has_headers: if self.has_headers:
headers = f.__next__() headers = f.__next__()
@ -142,7 +128,15 @@ class CustomShapeNet(InMemoryDataset):
points = torch.tensor(src, dtype=None).squeeze() points = torch.tensor(src, dtype=None).squeeze()
if not len(points.shape) > 1: if not len(points.shape) > 1:
continue continue
y_all = ([y_raw] if self.mode != 'predict' else [-1]) * points.shape[0] # Place Fake Labels to hold the given structure
if self.labels_within:
y_all = points[:, -1]
points = points[:, :-1]
else:
# Get the y - Label
y_raw = next(i for i, v in enumerate(self.categories.keys()) if v.lower() in element.lower())
y_all = ([y_raw] if self.mode != 'predict' else [-1]) * points.shape[0]
y = torch.as_tensor(y_all, dtype=torch.int) y = torch.as_tensor(y_all, dtype=torch.int)
if self.collate_per_element: if self.collate_per_element:
data = Data(y=y, pos=points[:, :3]) # , points=points, norm=points[:, 3:]) data = Data(y=y, pos=points[:, :3]) # , points=points, norm=points[:, 3:])
@ -178,12 +172,11 @@ class ShapeNetPartSegDataset(Dataset):
Resample raw point cloud to fixed number of points. Resample raw point cloud to fixed number of points.
Map raw label from range [1, N] to [0, N-1]. Map raw label from range [1, N] to [0, N-1].
""" """
def __init__(self, root_dir, collate_per_segment=True, mode='train', transform=None, refresh=False, def __init__(self, root_dir, npoints=1024, **kwargs):
has_variations=False, npoints=1024, headers=True):
super(ShapeNetPartSegDataset, self).__init__() super(ShapeNetPartSegDataset, self).__init__()
kwargs.update(dict(root_dir=root_dir))
self.npoints = npoints self.npoints = npoints
self.dataset = CustomShapeNet(root=root_dir, collate_per_segment=collate_per_segment, refresh=refresh, self.dataset = CustomShapeNet(**kwargs)
mode=mode, transform=transform, headers=headers, has_variations=has_variations)
def __getitem__(self, index): def __getitem__(self, index):
data = self.dataset[index] data = self.dataset[index]

39
main.py
View File

@ -33,6 +33,7 @@ parser.add_argument('--npoints', type=int, default=1024, help='resample points n
parser.add_argument('--model', type=str, default='', help='model path') parser.add_argument('--model', type=str, default='', help='model path')
parser.add_argument('--nepoch', type=int, default=250, help='number of epochs to train for') parser.add_argument('--nepoch', type=int, default=250, help='number of epochs to train for')
parser.add_argument('--outf', type=str, default='checkpoint', help='output folder') parser.add_argument('--outf', type=str, default='checkpoint', help='output folder')
parser.add_argument('--labels_within', type=strtobool, default=False, help='defines the label location')
parser.add_argument('--batch_size', type=int, default=8, help='input batch size') parser.add_argument('--batch_size', type=int, default=8, help='input batch size')
parser.add_argument('--test_per_batches', type=int, default=1000, help='run a test batch per training batches number') parser.add_argument('--test_per_batches', type=int, default=1000, help='run a test batch per training batches number')
parser.add_argument('--num_workers', type=int, default=4, help='number of data loading workers') parser.add_argument('--num_workers', type=int, default=4, help='number of data loading workers')
@ -56,30 +57,34 @@ torch.manual_seed(opt.manual_seed)
torch.cuda.manual_seed(opt.manual_seed) torch.cuda.manual_seed(opt.manual_seed)
if __name__ == '__main__': if __name__ == '__main__':
# Dataset and transform # Dataset and transform
print('Construct dataset ..') print('Construct dataset ..')
if True:
rot_max_angle = 15
trans_max_distance = 0.01
RotTransform = GT.Compose([GT.RandomRotate(rot_max_angle, 0), rot_max_angle = 15
GT.RandomRotate(rot_max_angle, 1), trans_max_distance = 0.01
GT.RandomRotate(rot_max_angle, 2)]
)
TransTransform = GT.RandomTranslate(trans_max_distance)
train_transform = GT.Compose([GT.NormalizeScale(), RotTransform, TransTransform]) RotTransform = GT.Compose([GT.RandomRotate(rot_max_angle, 0),
test_transform = GT.Compose([GT.NormalizeScale(), ]) GT.RandomRotate(rot_max_angle, 1),
GT.RandomRotate(rot_max_angle, 2)]
)
dataset = ShapeNetPartSegDataset(root_dir=opt.dataset, collate_per_segment=opt.collate_per_segment, TransTransform = GT.RandomTranslate(trans_max_distance)
mode='train', transform=train_transform, npoints=opt.npoints, train_transform = GT.Compose([GT.NormalizeScale(), RotTransform, TransTransform])
has_variations=opt.has_variations, headers=opt.headers) test_transform = GT.Compose([GT.NormalizeScale(), ])
params = dict(root_dir=opt.dataset,
collate_per_segment=opt.collate_per_segment,
transform=train_transform,
npoints=opt.npoints,
labels_within=opt.labels_within,
has_variations=opt.has_variations,
headers=opt.headers
)
dataset = ShapeNetPartSegDataset(mode='train', **params)
dataLoader = DataLoader(dataset, batch_size=opt.batch_size, shuffle=True, num_workers=opt.num_workers) dataLoader = DataLoader(dataset, batch_size=opt.batch_size, shuffle=True, num_workers=opt.num_workers)
test_dataset = ShapeNetPartSegDataset(root_dir=opt.dataset, collate_per_segment=opt.collate_per_segment, test_dataset = ShapeNetPartSegDataset(mode='test', **params)
mode='test', transform=test_transform, npoints=opt.npoints,
has_variations=opt.has_variations, headers=opt.headers)
test_dataLoader = DataLoader(test_dataset, batch_size=opt.batch_size, shuffle=True, num_workers=opt.num_workers) test_dataLoader = DataLoader(test_dataset, batch_size=opt.batch_size, shuffle=True, num_workers=opt.num_workers)
num_classes = dataset.num_classes() num_classes = dataset.num_classes()