def __init__(self):
super(BasicStem, self).__init__(
ReplicationPad3d((3, 3, 3, 3, 1, 1)),
nn.Conv3d(3, 64, kernel_size=(3, 7, 7), stride=(1, 2, 2),
padding=(0, 0, 0), bias=False),
nn.BatchNorm3d(64),
nn.ReLU(inplace=True))
def __init__(self):
super(BasicStem2D, self).__init__(
ReplicationPad3d((3, 3, 3, 3, 0, 0)),
nn.Conv3d(3, 64, kernel_size=(1, 7, 7), stride=(1, 2, 2),
padding=(0, 0, 0), bias=False),
nn.BatchNorm3d(64), # HACK maybe don't use 3d batch norm? to make life harder
nn.ReLU(inplace=True))
def __init__(self, denselayer2d, inflate_convs=False):
super(_DenseLayer3d, self).__init__()
self.inflate_convs = inflate_convs
for name, child in denselayer2d.named_children():
if isinstance(child, torch.nn.BatchNorm2d):
self.add_module(name, inflate.inflate_batch_norm(child))
elif isinstance(child, torch.nn.ReLU):
self.add_module(name, child)
elif isinstance(child, torch.nn.Conv2d):
kernel_size = child.kernel_size[0]
if inflate_convs and kernel_size > 1:
# Pad input in the time dimension
assert kernel_size % 2 == 1, 'kernel size should be\
odd be got {}'.format(kernel_size)
pad_size = int(kernel_size / 2)
pad_time = ReplicationPad3d(
(0, 0, 0, 0, pad_size, pad_size))
self.add_module('padding.1', pad_time)
# Add time dimension of same dim as the space one
self.add_module(name,
inflate.inflate_conv(child, kernel_size))
else:
self.add_module(name, inflate.inflate_conv(child, 1))
else:
raise ValueError('{} is not among handled layer types'.format(
type(child)))
self.drop_rate = denselayer2d.drop_rate
def __init__(self,
in_planes,
out_planes,
midplanes,
stride=1,
padding=1):
super(Conv2Plus1D, self).__init__(
ReplicationPad3d((padding, padding, padding, padding, 0, 0)),
nn.Conv3d(in_planes, midplanes, kernel_size=(1, 3, 3),
stride=(1, stride, stride), padding=(0, padding, padding),
bias=False),
nn.BatchNorm3d(midplanes),
nn.ReLU(inplace=True),
ReplicationPad3d((0, 0, 0, 0, padding, padding)),
nn.Conv3d(midplanes, out_planes, kernel_size=(3, 1, 1),
stride=(stride, 1, 1), padding=(padding, 0, 0),
bias=False))
def __init__(self,
in_planes,
out_planes,
midplanes=None,
stride=1,
padding=1):
super(Conv3DSimplePad, self).__init__()
self.pieces = nn.Sequential(
ReplicationPad3d(
(padding, padding, padding, padding, padding, padding)),
Conv3DSimple(in_planes, out_planes, midplanes, stride, (0, 0, 0)))
def __init__(self,
in_planes,
out_planes,
midplanes=None,
stride=1,
padding=1):
super(Conv3DNoTemporalPad, self).__init__()
self.pieces = nn.Sequential(
ReplicationPad3d((padding, padding, padding, padding, 0, 0)),
nn.Conv3d(in_channels=in_planes,
out_channels=out_planes,
kernel_size=(1, 3, 3),
stride=(1, stride, stride),
padding=(0, 0, 0),
bias=False))
def __init__(self, transition2d, inflate_conv=False):
"""
Inflates transition layer from transition2d
"""
super(_Transition3d, self).__init__()
for name, layer in transition2d.named_children():
if isinstance(layer, torch.nn.BatchNorm2d):
self.add_module(name, inflate.inflate_batch_norm(layer))
elif isinstance(layer, torch.nn.ReLU):
self.add_module(name, layer)
elif isinstance(layer, torch.nn.Conv2d):
if inflate_conv:
pad_time = ReplicationPad3d((0, 0, 0, 0, 1, 1))
self.add_module('padding.1', pad_time)
self.add_module(name, inflate.inflate_conv(layer, 3))
else:
self.add_module(name, inflate.inflate_conv(layer, 1))
elif isinstance(layer, torch.nn.AvgPool2d):
self.add_module(name, inflate.inflate_pool(layer, 2))
else:
raise ValueError('{} is not among handled layer types'.format(
type(layer)))