def __init__(self, in_channels, out_channels, final_sigmoid, basic_module, f_maps=64, layer_order='gcr',
num_groups=8, num_levels=4, is_segmentation=True, conv_kernel_size=3, pool_kernel_size=2,
conv_padding=1, **kwargs):
super(Abstract3DUNet, self).__init__()
if isinstance(f_maps, int):
f_maps = number_of_features_per_level(f_maps, num_levels=num_levels)
assert isinstance(f_maps, list) or isinstance(f_maps, tuple)
assert len(f_maps) > 1, "Required at least 2 levels in the U-Net"
# create encoder path
self.encoders = create_encoders(in_channels, f_maps, basic_module, conv_kernel_size, conv_padding, layer_order,
num_groups, pool_kernel_size)
# create decoder path
self.decoders = create_decoders(f_maps, basic_module, conv_kernel_size, conv_padding, layer_order, num_groups,
upsample=True)
# in the last layer a 1×1 convolution reduces the number of output
# channels to the number of labels
self.final_conv = nn.Conv3d(f_maps[0], out_channels, 1)
if is_segmentation:
# semantic segmentation problem
if final_sigmoid:
self.final_activation = nn.Sigmoid()
else:
self.final_activation = nn.Softmax(dim=1)
else:
# regression problem
self.final_activation = None
def __init__(self,
in_channels,
out_channels,
final_sigmoid,
basic_module,
f_maps=64,
layer_order='gcr',
num_groups=8,
num_levels=4,
is_segmentation=True,
testing=False,
**kwargs):
super(Abstract3DUNet, self).__init__()
self.testing = testing
if isinstance(f_maps, int):
f_maps = number_of_features_per_level(f_maps,
num_levels=num_levels)
# create encoder path consisting of Encoder modules. Depth of the encoder is equal to `len(f_maps)`
encoders = []
for i, out_feature_num in enumerate(f_maps):
if i == 0:
encoder = Encoder(in_channels,
out_feature_num,
apply_pooling=False,
basic_module=basic_module,
conv_layer_order=layer_order,
num_groups=num_groups)
else:
# TODO: adapt for anisotropy in the data, i.e. use proper pooling kernel to make the data isotropic after 1-2 pooling operations
# currently pools with a constant kernel: (2, 2, 2)
encoder = Encoder(f_maps[i - 1],
out_feature_num,
basic_module=basic_module,
conv_layer_order=layer_order,
num_groups=num_groups)
encoders.append(encoder)
self.encoders = nn.ModuleList(encoders)
# create decoder path consisting of the Decoder modules. The length of the decoder is equal to `len(f_maps) - 1`
decoders = []
reversed_f_maps = list(reversed(f_maps))
for i in range(len(reversed_f_maps) - 1):
if basic_module == DoubleConv:
in_feature_num = reversed_f_maps[i] + reversed_f_maps[i + 1]
else:
in_feature_num = reversed_f_maps[i]
out_feature_num = reversed_f_maps[i + 1]
# TODO: if non-standard pooling was used, make sure to use correct striding for transpose conv
# currently strides with a constant stride: (2, 2, 2)
decoder = Decoder(in_feature_num,
out_feature_num,
basic_module=basic_module,
conv_layer_order=layer_order,
num_groups=num_groups)
decoders.append(decoder)
self.decoders = nn.ModuleList(decoders)
# in the last layer a 1×1 convolution reduces the number of output
# channels to the number of labels
self.final_conv = nn.Conv3d(f_maps[0], out_channels, 1)
if is_segmentation:
# semantic segmentation problem
if final_sigmoid:
self.final_activation = nn.Sigmoid()
else:
self.final_activation = nn.Softmax(dim=1)
else:
# regression problem
self.final_activation = None