def __init__(self, input_dims):
super().__init__()
x, y, z = input_dims
self.num_filters = [64, 128, 256, 512, 512]
self.convxd = nn.Conv2d
self.pooling = nn.MaxPool2d
self.norm = nn.BatchNorm2d
self.relu = nn.LeakyReLU
self.features = nn.Sequential(
conv_block(z,
self.num_filters[0],
False,
self.convxd,
self.norm,
self.pooling,
relu=self.relu),
conv_block(self.num_filters[0],
self.num_filters[1],
False,
self.convxd,
self.norm,
self.pooling,
relu=self.relu),
conv_block(self.num_filters[1],
self.num_filters[2],
True,
self.convxd,
self.norm,
self.pooling,
relu=self.relu),
conv_block(self.num_filters[2],
self.num_filters[3],
True,
self.convxd,
self.norm,
self.pooling,
relu=self.relu),
conv_block(self.num_filters[3],
self.num_filters[4],
True,
self.convxd,
self.norm,
self.pooling,
relu=self.relu),
)
a = (x // (2**np.shape(self.num_filters)[0])) * (
y // (2**np.shape(self.num_filters)[0])) * self.num_filters[-1]
a = int(a)
N = 4096
self.fc1 = nn.Sequential(nn.Linear(a, N), nn.ReLU(inplace=True),
nn.Dropout(0.5), nn.Linear(N, N),
nn.ReLU(inplace=True), nn.Dropout(0.5),
nn.Linear(N, 1))
def __init__(self, img_ch=3, output_ch=1):
super(AttU_Net, self).__init__()
n1 = 64
filters = [n1, n1 * 2, n1 * 4, n1 * 8, n1 * 16]
self.Maxpool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool3 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool4 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Conv1 = conv_block(img_ch, filters[0])
self.Conv2 = conv_block(filters[0], filters[1])
self.Conv3 = conv_block(filters[1], filters[2])
self.Conv4 = conv_block(filters[2], filters[3])
self.Conv5 = conv_block(filters[3], filters[4])
self.Up5 = up_conv(filters[4], filters[3])
self.Att5 = Attention_block(F_g=filters[3], F_l=filters[3], F_int=filters[2])
self.Up_conv5 = conv_block(filters[4], filters[3])
self.Up4 = up_conv(filters[3], filters[2])
self.Att4 = Attention_block(F_g=filters[2], F_l=filters[2], F_int=filters[1])
self.Up_conv4 = conv_block(filters[3], filters[2])
self.Up3 = up_conv(filters[2], filters[1])
self.Att3 = Attention_block(F_g=filters[1], F_l=filters[1], F_int=filters[0])
self.Up_conv3 = conv_block(filters[2], filters[1])
self.Up2 = up_conv(filters[1], filters[0])
self.Att2 = Attention_block(F_g=filters[0], F_l=filters[0], F_int=32)
self.Up_conv2 = conv_block(filters[1], filters[0])
self.Conv = nn.Conv2d(filters[0], output_ch, kernel_size=1, stride=1, padding=0)
def __init__(self, in_ch=3, out_ch=1):
super(U_Net, self).__init__()
n1 = 64
filters = [n1, n1 * 2, n1 * 4, n1 * 8, n1 * 16]
self.Maxpool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool3 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Maxpool4 = nn.MaxPool2d(kernel_size=2, stride=2)
self.Conv1 = conv_block(in_ch, filters[0])
self.Conv2 = conv_block(filters[0], filters[1])
self.Conv3 = conv_block(filters[1], filters[2])
self.Conv4 = conv_block(filters[2], filters[3])
self.Conv5 = conv_block(filters[3], filters[4])
self.Up5 = up_conv(filters[4], filters[3])
self.Up_conv5 = conv_block(filters[4], filters[3])
self.Up4 = up_conv(filters[3], filters[2])
self.Up_conv4 = conv_block(filters[3], filters[2])
self.Up3 = up_conv(filters[2], filters[1])
self.Up_conv3 = conv_block(filters[2], filters[1])
self.Up2 = up_conv(filters[1], filters[0])
self.Up_conv2 = conv_block(filters[1], filters[0])
self.Conv = nn.Conv2d(filters[0],
out_ch,
kernel_size=1,
stride=1,
padding=0)
def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
"""Build a ResNet graph.
architecture: Can be resnet50 or resnet101
stage5: Boolean. If False, stage5 of the network is not created
train_bn: Boolean. Train or freeze Batch Norm layers
"""
assert architecture in ["resnet50", "resnet101"]
# Stage 1
x = ZeroPadding2D((3, 3))(input_image)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
x = BatchNormalization(name='bn_conv1')(x, training=train_bn)
x = Activation('relu')(x)
C1 = x = MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
# Stage 2
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
# Stage 3
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
# Stage 4
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
block_count = {"resnet50": 5, "resnet101": 22}[architecture]
for i in range(block_count):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
C4 = x
# Stage 5
if stage5:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
else:
C5 = None
return [C1, C2, C3, C4, C5]