def get_inputs_field(mode, cfg):
''' Returns the inputs fields.
Args:
mode (str): the mode which is used
cfg (dict): config dictionary
'''
input_type = cfg['data']['input_type']
if input_type is None:
inputs_field = None
elif input_type == 'img_seq':
if mode == 'train' and cfg['data']['img_augment']:
resize_op = transforms.RandomResizedCrop(cfg['data']['img_size'],
(0.75, 1.), (1., 1.))
else:
resize_op = transforms.Resize((cfg['data']['img_size']))
transform = transforms.Compose([
resize_op,
transforms.ToTensor(),
])
if mode == 'train':
random_view = True
else:
random_view = False
inputs_field = data.ImageSubseqField(cfg['data']['img_seq_folder'],
transform,
random_view=random_view)
elif input_type == 'pcl_seq':
connected_samples = cfg['data']['input_pointcloud_corresponding']
transform = transforms.Compose([
data.SubsamplePointcloudSeq(cfg['data']['input_pointcloud_n'],
connected_samples=connected_samples),
data.PointcloudNoise(cfg['data']['input_pointcloud_noise'])
])
inputs_field = data.PointCloudSubseqField(
cfg['data']['pointcloud_seq_folder'],
transform,
seq_len=cfg['data']['length_sequence'])
elif input_type == 'end_pointclouds':
transform = data.SubsamplePointcloudSeq(
cfg['data']['input_pointcloud_n'],
connected_samples=cfg['data']['input_pointcloud_corresponding'])
inputs_field = data.PointCloudSubseqField(
cfg['data']['pointcloud_seq_folder'],
only_end_points=True,
seq_len=cfg['data']['length_sequence'],
transform=transform)
elif input_type == 'idx':
inputs_field = data.IndexField()
else:
raise ValueError('Invalid input type (%s)' % input_type)
return inputs_field
def get_inputs_field(mode, cfg):
''' Returns the inputs fields.
Args:
mode (str): the mode which is used
cfg (dict): config dictionary
'''
input_type = cfg['data']['input_type']
with_transforms = cfg['data']['with_transforms']
if input_type is None:
inputs_field = None
elif input_type == 'img':
if mode == 'train' and cfg['data']['img_augment']:
resize_op = transforms.RandomResizedCrop(
cfg['data']['img_size'], (0.75, 1.), (1., 1.))
else:
resize_op = transforms.Resize((cfg['data']['img_size']))
transform = transforms.Compose([
resize_op, transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
inputs_field = data.ImagesField(
cfg['data']['img_folder'], transform,
with_camera=with_camera, random_view=random_view
)
elif input_type == 'pointcloud':
transform = transforms.Compose([
data.SubsamplePointcloud(cfg['data']['pointcloud_n']),
data.PointcloudNoise(cfg['data']['pointcloud_noise'])
])
with_transforms = cfg['data']['with_transforms']
inputs_field = data.PointCloudField(
cfg['data']['pointcloud_file'], transform,
with_transforms=with_transforms
)
elif input_type == 'voxels':
inputs_field = data.VoxelsField(
cfg['data']['voxels_file']
)
elif input_type == 'idx':
inputs_field = data.IndexField()
else:
raise ValueError(
'Invalid input type (%s)' % input_type)
return inputs_field
def get_inputs_field(mode, cfg):
''' Returns the inputs fields.
Args:
mode (str): the mode which is used
cfg (dict): config dictionary
'''
input_type = cfg['data']['input_type']
with_transforms = cfg['data']['with_transforms']
if input_type is None:
inputs_field = None
elif input_type == 'img':
if mode == 'train' and cfg['data']['img_augment']:
resize_op = transforms.RandomResizedCrop(cfg['data']['img_size'],
(0.75, 1.), (1., 1.))
else:
resize_op = transforms.Resize((cfg['data']['img_size']))
transform = transforms.Compose([
resize_op,
transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
if 'img_extension' in cfg['data']:
inputs_field = data.ImagesField(
cfg['data']['img_folder'],
transform,
extension=cfg['data']['img_extension'],
with_camera=with_camera,
random_view=random_view)
else:
inputs_field = data.ImagesField(cfg['data']['img_folder'],
transform,
with_camera=with_camera,
random_view=random_view)
elif input_type == 'img_with_depth':
# data augment not supported
transform = transforms.Compose([
transforms.Resize((cfg['data']['img_size'])),
transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
data_params = {
'with_camera': with_camera,
'random_view': random_view,
}
if 'absolute_depth' in cfg['data']:
data_params['absolute_depth'] = cfg['data']['absolute_depth']
if 'with_minmax' in cfg['data']:
data_params['with_minmax'] = cfg['data']['with_minmax']
if 'img_extension' in cfg['data']:
data_params['extension'] = cfg['data']['img_extension']
inputs_field = data.ImagesWithDepthField('img', 'depth', 'mask',
transform, **data_params)
elif input_type == 'depth_pred':
# data augment not supported
transform = transforms.Compose([
transforms.Resize((cfg['data']['img_size'])),
transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
data_params = {
'with_camera': with_camera,
'random_view': random_view,
}
if 'absolute_depth' in cfg['data']:
data_params['absolute_depth'] = cfg['data']['absolute_depth']
if 'with_minmax' in cfg['data']:
data_params['with_minmax'] = cfg['data']['with_minmax']
if 'pred_with_img' in cfg['model']:
data_params['with_img'] = cfg['model']['pred_with_img']
if 'img_extension' in cfg['data']:
data_params['extension'] = cfg['data']['img_extension']
inputs_field = data.DepthPredictedField('img', 'depth', 'mask',
cfg['data']['depth_pred_root'],
'depth_pred', transform,
**data_params)
elif input_type == 'depth_pointcloud':
t_lst = []
if 'depth_pointcloud_n' in cfg['data'] and cfg['data'][
'depth_pointcloud_n'] is not None:
t_lst.append(
data.SubsampleDepthPointcloud(
cfg['data']['depth_pointcloud_n']))
if 'depth_pointcloud_noise' in cfg['data'] and cfg['data'][
'depth_pointcloud_noise'] is not None:
t_lst.append(
data.PointcloudNoise(cfg['data']['depth_pointcloud_noise']))
transform = transforms.Compose(t_lst)
if mode == 'train':
random_view = True
else:
random_view = False
data_params = {
'random_view': random_view,
'with_camera': True,
'img_folder_name': 'img'
}
if 'view_penalty' in cfg['training'] and cfg['training'][
'view_penalty']:
data_params['with_mask'] = True
data_params['mask_folder_name'] = 'mask'
data_params['mask_flow_folder_name'] = 'mask_flow'
data_params['extension'] = 'png'
img_transform = transforms.Compose([
transforms.Resize((cfg['data']['img_size'])),
transforms.ToTensor(),
])
data_params['img_transform'] = img_transform
data_params['with_depth_pred'] = True
data_params['depth_pred_folder_name'] = 'depth_pred'
inputs_field = data.DepthPointCloudField(
cfg['data']['depth_pointcloud_root'],
cfg['data']['depth_pointcloud_folder'], transform, **data_params)
elif input_type == 'multi_img':
if mode == 'train' and cfg['data']['img_augment']:
resize_op = transforms.RandomResizedCrop(cfg['data']['img_size'],
(0.75, 1.), (1., 1.))
else:
resize_op = transforms.Resize((cfg['data']['img_size']))
transform = transforms.Compose([
resize_op,
transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
inputs_field = data.ImagesField(cfg['data']['img_folder'],
transform,
with_camera=with_camera,
random_view=random_view)
elif input_type == 'pointcloud':
transform = transforms.Compose([
data.SubsamplePointcloud(cfg['data']['pointcloud_n']),
data.PointcloudNoise(cfg['data']['pointcloud_noise'])
])
with_transforms = cfg['data']['with_transforms']
inputs_field = data.PointCloudField(cfg['data']['pointcloud_file'],
transform,
with_transforms=with_transforms)
elif input_type == 'voxels':
inputs_field = data.VoxelsField(cfg['data']['voxels_file'])
elif input_type == 'idx':
inputs_field = data.IndexField()
else:
raise ValueError('Invalid input type (%s)' % input_type)
return inputs_field
def get_inputs_field(mode, cfg, use_target_domain = False):
''' Returns the inputs fields.
Args:
mode (str): the mode which is used
cfg (dict): config dictionary
use_target_domain (bool): whether to use the target_domain dataset
'''
input_type = cfg['data']['input_type']
with_transforms = cfg['data']['with_transforms']
if input_type is None:
inputs_field = None
elif input_type == 'img':
if mode == 'train' and cfg['data']['img_augment']:
resize_op = transforms.RandomResizedCrop(
cfg['data']['img_size'], (0.75, 1.), (1., 1.))
else:
resize_op = transforms.Resize((cfg['data']['img_size']))
transform = transforms.Compose([
resize_op, transforms.ToTensor(),
])
with_camera = cfg['data']['img_with_camera']
if mode == 'train':
random_view = True
else:
random_view = False
if use_target_domain:
img_folder_name = cfg['data']['uda_img_folder']
filename_pattern= cfg['data']['uda_bg_configure']
else:
img_folder_name = cfg['data']['img_folder']
filename_pattern = cfg['data']['img_filename_pattern']
inputs_field = data.ImagesField(
img_folder_name, transform,
with_camera=with_camera, random_view=random_view, filename_pattern=filename_pattern, extensions=['jpg', 'jpeg', 'png']
)
elif input_type == 'pointcloud':
transform = transforms.Compose([
data.SubsamplePointcloud(cfg['data']['pointcloud_n']),
data.PointcloudNoise(cfg['data']['pointcloud_noise'])
])
with_transforms = cfg['data']['with_transforms']
inputs_field = data.PointCloudField(
cfg['data']['pointcloud_file'], transform,
with_transforms=with_transforms
)
elif input_type == 'voxels':
inputs_field = data.VoxelsField(
cfg['data']['voxels_file']
)
elif input_type == 'idx':
inputs_field = data.IndexField()
else:
raise ValueError(
'Invalid input type (%s)' % input_type)
return inputs_field
def preprocess(points):
output = data.SubsamplePointcloud(
cfg["data"]["pointcloud_n"])(points)
output = data.PointcloudNoise(
cfg["data"]["pointcloud_noise"])(output)
return output