def __init__(self,nInputChannels=3, n_classes=7, os=16,input_channels=256,hidden_layers=128,out_channels=256):
super(deeplab_xception_transfer_basemodel_synBN_savememory, self).__init__(nInputChannels=nInputChannels, n_classes=n_classes,
os=os, )
### source graph
# self.source_featuremap_2_graph = gcn.Featuremaps_to_Graph(input_channels=input_channels, hidden_layers=hidden_layers,
# nodes=n_classes)
# self.source_graph_conv1 = gcn.GraphConvolution(hidden_layers, hidden_layers)
# self.source_graph_conv2 = gcn.GraphConvolution(hidden_layers, hidden_layers)
# self.source_graph_conv3 = gcn.GraphConvolution(hidden_layers, hidden_layers)
#
# self.source_graph_2_fea = gcn.Graph_to_Featuremaps(input_channels=input_channels, output_channels=out_channels,
# hidden_layers=hidden_layers, nodes=n_classes
# )
# self.source_skip_conv = nn.Sequential(*[nn.Conv2d(input_channels, input_channels, kernel_size=1),
# nn.ReLU(True)])
### target graph
self.target_featuremap_2_graph = gcn.Featuremaps_to_Graph(input_channels=input_channels, hidden_layers=hidden_layers,
nodes=n_classes)
self.target_graph_conv1 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.target_graph_conv2 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.target_graph_conv3 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.target_graph_2_fea = gcn.Graph_to_Featuremaps_savemem(input_channels=input_channels, output_channels=out_channels,
hidden_layers=hidden_layers, nodes=n_classes
)
self.target_skip_conv = nn.Sequential(*[nn.Conv2d(input_channels, input_channels, kernel_size=1),
nn.BatchNorm2d(input_channels),
nn.ReLU(True)])
def __init__(
self,
nInputChannels=3,
n_classes=7,
os=16,
input_channels=256,
hidden_layers=128,
out_channels=256,
transfer_graph=None,
source_classes=20,
):
super(deeplab_xception_transfer_projection_savemem, self).__init__(
nInputChannels=nInputChannels,
n_classes=n_classes,
os=os,
input_channels=input_channels,
hidden_layers=hidden_layers,
out_channels=out_channels,
)
self.source_featuremap_2_graph = gcn.Featuremaps_to_Graph(
input_channels=input_channels,
hidden_layers=hidden_layers,
nodes=source_classes,
)
self.source_graph_conv1 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.source_graph_conv2 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.source_graph_conv3 = gcn.GraphConvolution(hidden_layers, hidden_layers)
self.transpose_graph = gcn.Graph_trans(
in_features=hidden_layers,
out_features=hidden_layers,
adj=transfer_graph,
begin_nodes=source_classes,
end_nodes=n_classes,
)
self.fc_graph = gcn.GraphConvolution(hidden_layers * 3, hidden_layers)
def __init__(self, n_classes, hidden_layers, gcn_mode=2, device='cpu'):
super(DeepLabv3_plus_gcn_skipconnection_3d_subnet2, self).__init__()
self.device = device
self.gcn_mode = gcn_mode
self.feature_projection_conv2 = nn.Conv3d(32, 64, 1, bias=False)
self.feature_projection_bn2 = nn.BatchNorm3d(64)
self.relu = nn.ReLU()
if self.gcn_mode == 0:
self.featuremap_2_graph = gcn.Featuremaps_to_Graph(
input_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
self.graph_conv1 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv2 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv3 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_2_fea = gcn.Graph_to_Featuremaps_savemem(
input_channels=128,
output_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
elif self.gcn_mode == 1:
self.global_reasoning_unit = GloRe_Unit_3D(num_in=128,
num_s=128,
num_n=64)
elif self.gcn_mode == 2:
self.featuremap_2_graph = gcn.My_Featuremaps_to_Graph(
input_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
self.graph_conv1 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv2 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv3 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_2_fea = gcn.My_Graph_to_Featuremaps(
hidden_layers=hidden_layers, output_channels=128)
self.skip_conv = nn.Sequential(
*[nn.Conv3d(128, 128, kernel_size=1),
nn.ReLU(True)])
def __init__(self,
nInputChannels=3,
n_classes=21,
os=16,
pretrained=False,
_print=True,
final_sigmoid=False,
hidden_layers=128,
gcn_mode=0,
device=None):
if _print:
print("Constructing DeepLabv3+ model...")
print("Number of classes: {}".format(n_classes))
print("Output stride: {}".format(os))
print("Number of Input Channels: {}".format(nInputChannels))
super(DeepLabv3_plus_gcn_skipconnection_2d, self).__init__()
self.in_channels = nInputChannels
self.gcn_mode = gcn_mode
self.device = device
# Atrous Conv
self.xception_features = Xception(nInputChannels, os, pretrained)
# ASPP
if os == 16:
rates = [1, 6, 12, 18]
elif os == 8:
rates = [1, 12, 24, 36]
raise NotImplementedError
else:
raise NotImplementedError
self.aspp1 = ASPP_module_rate0(1024, 128, rate=rates[0])
self.aspp2 = ASPP_module(1024, 128, rate=rates[1])
self.aspp3 = ASPP_module(1024, 128, rate=rates[2])
self.aspp4 = ASPP_module(1024, 128, rate=rates[3])
self.relu = nn.ReLU()
self.global_avg_pool = nn.Sequential(
nn.AdaptiveAvgPool2d((1, 1)),
nn.Conv2d(1024, 128, 1, stride=1, bias=False), nn.BatchNorm2d(128),
nn.ReLU())
self.concat_projection_conv1 = nn.Conv2d(640, 128, 1, bias=False)
self.concat_projection_bn1 = nn.BatchNorm2d(128)
# adopt [1x1, 48] for channel reduction.
self.feature_projection_conv1 = nn.Conv2d(128, 24, 1, bias=False)
self.feature_projection_bn1 = nn.BatchNorm2d(24)
self.feature_projection_conv2 = nn.Conv2d(32, 64, 1, bias=False)
self.feature_projection_bn2 = nn.BatchNorm2d(64)
self.decoder1 = nn.Sequential(Decoder_module(152, 128),
Decoder_module(128, 128))
self.decoder2 = nn.Sequential(Decoder_module(192, 256),
Decoder_module(256, 256))
if self.gcn_mode == 0:
self.featuremap_2_graph = gcn.Featuremaps_to_Graph(
input_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
self.graph_conv1 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv2 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv3 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_2_fea = gcn.Graph_to_Featuremaps_savemem(
input_channels=128,
output_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
elif self.gcn_mode == 1:
self.global_reasoning_unit = GloRe_Unit_2D(num_in=128,
num_s=128,
num_n=64)
elif self.gcn_mode == 2:
self.featuremap_2_graph = gcn.My_Featuremaps_to_Graph(
input_channels=128,
hidden_layers=hidden_layers,
nodes=n_classes)
self.graph_conv1 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv2 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_conv3 = gcn.GraphConvolution(hidden_layers,
hidden_layers)
self.graph_2_fea = gcn.My_Graph_to_Featuremaps(
hidden_layers=hidden_layers, output_channels=128, dimension=2)
self.skip_conv = nn.Sequential(
*[nn.Conv2d(128, 128, kernel_size=1),
nn.ReLU(True)])
self.semantic = nn.Conv2d(256, n_classes, kernel_size=1, stride=1)
if final_sigmoid:
self.final_activation = nn.Sigmoid()
else:
self.final_activation = nn.Softmax(dim=1)
