def ResBlock(layer, filters, nconv, half):
in_ = layer
strides = [2, 2] if half else [1, 1]
layer = eddl.ReLu(BG(eddl.Conv(layer, filters, [3, 3], strides)))
for i in range(nconv - 1):
layer = eddl.ReLu(BG(eddl.Conv(layer, filters, [3, 3], [1, 1])))
if (half):
return eddl.Add(BG(eddl.Conv(in_, filters, [1, 1], [2, 2])), layer)
else:
return eddl.Add(layer, in_)
def UNetWithPadding(layer):
x = layer
depth = 32
x = LBC(x, depth, [3, 3], [1, 1], "same")
x = LBC(x, depth, [3, 3], [1, 1], "same")
x2 = eddl.MaxPool(x, [2, 2], [2, 2])
x2 = LBC(x2, 2*depth, [3, 3], [1, 1], "same")
x2 = LBC(x2, 2*depth, [3, 3], [1, 1], "same")
x3 = eddl.MaxPool(x2, [2, 2], [2, 2])
x3 = LBC(x3, 4*depth, [3, 3], [1, 1], "same")
x3 = LBC(x3, 4*depth, [3, 3], [1, 1], "same")
x4 = eddl.MaxPool(x3, [2, 2], [2, 2])
x4 = LBC(x4, 8*depth, [3, 3], [1, 1], "same")
x4 = LBC(x4, 8*depth, [3, 3], [1, 1], "same")
x5 = eddl.MaxPool(x4, [2, 2], [2, 2])
x5 = LBC(x5, 8*depth, [3, 3], [1, 1], "same")
x5 = LBC(x5, 8*depth, [3, 3], [1, 1], "same")
x5 = eddl.BatchNormalization(eddl.Conv(
eddl.UpSampling(x5, [2, 2]), 8*depth, [3, 3], [1, 1], "same"
), True)
x4 = eddl.Concat([x4, x5]) if USE_CONCAT else eddl.Add([x4, x5])
x4 = LBC(x4, 8*depth, [3, 3], [1, 1], "same")
x4 = LBC(x4, 8*depth, [3, 3], [1, 1], "same")
x4 = eddl.BatchNormalization(eddl.Conv(
eddl.UpSampling(x4, [2, 2]), 4*depth, [3, 3], [1, 1], "same"
), True)
x3 = eddl.Concat([x3, x4]) if USE_CONCAT else eddl.Add([x3, x4])
x3 = LBC(x3, 4*depth, [3, 3], [1, 1], "same")
x3 = LBC(x3, 4*depth, [3, 3], [1, 1], "same")
x3 = eddl.Conv(
eddl.UpSampling(x3, [2, 2]), 2*depth, [3, 3], [1, 1], "same"
)
x2 = eddl.Concat([x2, x3]) if USE_CONCAT else eddl.Add([x2, x3])
x2 = LBC(x2, 2*depth, [3, 3], [1, 1], "same")
x2 = LBC(x2, 2*depth, [3, 3], [1, 1], "same")
x2 = eddl.BatchNormalization(eddl.Conv(
eddl.UpSampling(x2, [2, 2]), depth, [3, 3], [1, 1], "same"
), True)
x = eddl.Concat([x, x2]) if USE_CONCAT else eddl.Add([x, x2])
x = LBC(x, depth, [3, 3], [1, 1], "same")
x = LBC(x, depth, [3, 3], [1, 1], "same")
x = eddl.BatchNormalization(eddl.Conv(x, 1, [1, 1]), True)
return x
def resnet_block(l0, nf, bn, reps, downsample):
for i in range(reps):
stri = 2 if (downsample and i == 0) else 1
l1 = eddl.GlorotUniform(
eddl.Conv(l0, nf, [1, 1], [stri, stri], "same", False))
if (bn):
l1 = eddl.BatchNormalization(l1, 0.99, 0.001, True, "")
l1 = eddl.ReLu(l1)
l1 = eddl.GlorotUniform(
eddl.Conv(l1, nf, [3, 3], [1, 1], "same", False))
if (bn):
l1 = eddl.BatchNormalization(l1, 0.99, 0.001, True, "")
l1 = eddl.ReLu(l1)
l1 = eddl.GlorotUniform(
eddl.Conv(l1, nf * 4, [1, 1], [1, 1], "same", False))
if (bn):
l1 = eddl.BatchNormalization(l1, 0.99, 0.001, True, "")
if (i == 0):
l0 = eddl.GlorotUniform(
eddl.Conv(l0, nf * 4, [1, 1], [stri, stri], "same", False))
l0 = eddl.Add([l0, l1])
l0 = eddl.ReLu(l0)
return l0
def ResBlock(layer, filters, half, expand=0):
in_ = layer
layer = eddl.ReLu(
BG(eddl.Conv(layer, filters, [1, 1], [1, 1], "same", False)))
strides = [2, 2] if half else [1, 1]
layer = eddl.ReLu(
BG(eddl.Conv(layer, filters, [3, 3], strides, "same", False)))
layer = eddl.ReLu(
BG(eddl.Conv(layer, 4 * filters, [1, 1], [1, 1], "same", False)))
if (half):
return eddl.ReLu(
eddl.Add(
BG(eddl.Conv(in_, 4 * filters, [1, 1], [2, 2], "same", False)),
layer))
else:
if expand:
return eddl.ReLu(
eddl.Add(
BG(
eddl.Conv(in_, 4 * filters, [1, 1], [1, 1], "same",
False)), layer))
else:
return eddl.ReLu(eddl.Add(in_, layer))
def dice_loss_pixel(inputs):
num = eddl.Mult(2, eddl.ReduceSum(eddl.Mult(inputs[0], inputs[1]), [0]))
den = eddl.ReduceSum(eddl.Add(inputs[0], inputs[1]), [0])
num = eddl.Add(num, 1)
den = eddl.Add(den, 1)
return eddl.Sub(1.0, eddl.Div(num, den))
def dice_loss_img(inputs):
num = eddl.Mult(2, eddl.ReduceSum(
eddl.Mult(inputs[0], inputs[1]), [0, 1, 2]
))
den = eddl.ReduceSum(eddl.Add(inputs[0], inputs[1]), [0, 1, 2])
return eddl.Sub(1.0, eddl.Div(num, den))
