def BaseCapsNet(input_shape, n_class, routings):
# assemble encoder
x = Input(shape=input_shape)
l = x
l = Conv2D(256, (9, 9), strides=(2, 2), activation='relu',
padding="same")(l)
l = BatchNormalization()(l)
l = Conv2D(256, (9, 9), strides=(2, 2), activation='relu',
padding="same")(l)
l = BatchNormalization()(l)
l = ConvertToCaps()(l)
l = Conv2DCaps(16,
6,
kernel_size=(3, 3),
strides=(2, 2),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = FlattenCaps()(l)
digits_caps = CapsuleLayer(num_capsule=10,
dim_capsule=8,
routings=routings,
channels=0,
name='digit_caps')(l)
l = CapsToScalars(name='capsnet')(digits_caps)
m_capsnet = models.Model(inputs=x, outputs=l, name='capsnet_model')
y = layers.Input(shape=(n_class, ))
masked_by_y = Mask()(
[digits_caps, y]
) # The true label is used to mask the output of capsule layer. For training
masked = Mask()(digits_caps)
# Decoder Network
decoder = models.Sequential(name='decoder')
decoder.add(Dense(input_dim=80, activation="relu", output_dim=8 * 8 * 16))
decoder.add(Reshape((8, 8, 16)))
decoder.add(BatchNormalization(momentum=0.8))
decoder.add(
layers.Deconvolution2D(64, 3, 3, subsample=(1, 1), border_mode='same'))
decoder.add(
layers.Deconvolution2D(32, 3, 3, subsample=(2, 2), border_mode='same'))
decoder.add(
layers.Deconvolution2D(16, 3, 3, subsample=(2, 2), border_mode='same'))
decoder.add(
layers.Deconvolution2D(3, 3, 3, subsample=(1, 1), border_mode='same'))
decoder.add(Activation("relu"))
decoder.add(layers.Reshape(target_shape=(32, 32, 3), name='out_recon'))
train_model = models.Model(
[x, y], [m_capsnet.output, decoder(masked_by_y)])
eval_model = models.Model(x, [m_capsnet.output, decoder(masked)])
train_model.summary()
return train_model, eval_model
def PureCapsNet(input_shape, n_class, routings):
# K.set_image_dim_ordering('th')
x = Input(shape=input_shape)
# Layer 1: Just a conventional Conv2D layer
conv1 = Conv2D(filters=128,
kernel_size=3,
strides=2,
padding='valid',
activation='relu',
name='conv1')(x)
conv2 = Conv2D(filters=128,
kernel_size=3,
strides=2,
padding='valid',
activation='relu',
name='conv2')(conv1)
conv3 = Conv2D(filters=128,
kernel_size=3,
strides=2,
padding='valid',
activation='relu',
name='conv3')(conv2)
# Layer 2: Conv2D layer with `squash` activation, then reshape to [None, num_capsule, dim_capsule]
primarycaps = PrimaryCap(conv3,
dim_capsule=C.DIM_CAPSULE,
n_channels=16,
kernel_size=9,
strides=2,
padding='valid')
# Layer 3: Capsule layer. Routing algorithm works here.
digitcaps = CapsuleLayer(num_capsule=n_class,
dim_capsule=C.DIM_CAPSULE,
routings=routings,
name='digitcaps')(primarycaps)
# Layer 4: This is an auxiliary layer to replace each capsule with its length. Just to match the true label's shape.
# If using tensorflow, this will not be necessary. :)
out_caps = Length(name='capsnet')(digitcaps)
# Models for training and evaluation (prediction)
train_model = models.Model(x, out_caps, name='PureCapsNet')
return train_model
def DeepCapsNetTwoPath(input_shape1,input_shape2, n_class, routings):
# assemble encoder
x33 = Input(shape=input_shape1)
x15 = Input(shape=input_shape2,name='2_0')
path1 = Conv2D(128, (5, 5), strides=(1, 1), activation='relu', padding="same",name='1_1')(x33) # common conv layer
path1=MaxPooling2D(pool_size=(2, 2),name='1_2')(path1)
path1=Dropout(0.5)(path1)
path1 = ConvertToCaps()(path1)
path1 = Conv2DCaps(16, 8, kernel_size=(5, 5), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1],name='1_3')(path1)
path1 = Conv2DCaps(16, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1],name='1_4')(path1)
path2 = Conv2D(128, (5, 5), strides=(1, 1), activation='relu', padding="same",name='2_1')(x15) # common conv layer
path2 = ConvertToCaps()(path2)
path2 = Conv2DCaps(16, 8, kernel_size=(5, 5), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1],name='2_2')(path2)
path2 = Conv2DCaps(16, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1],name='2_3')(path2)
x = layers.Add()([path1, path2])
l=x
# l = Conv2D(128, (5, 5), strides=(1, 1), activation='relu', padding="same")(l) # common conv layer
# # l = BatchNormalization()(l)
# l = ConvertToCaps()(l)
# l = Conv2DCaps(32, 4, kernel_size=(3, 3), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1])(l)
# l_skip = Conv2DCaps(32, 4, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = Conv2DCaps(32, 4, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = Conv2DCaps(32, 4, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = layers.Add()([l, l_skip])
l = Conv2DCaps(16, 8, kernel_size=(5, 5), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1],name='3_1')(l)
l_skip = Conv2DCaps(16, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1],name='3_2')(l)
l = Conv2DCaps(16, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1],name='3_3')(l)
l = layers.Add()([l, l_skip])
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1])(l)
# l_skip = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = layers.Add()([l, l_skip])
# l1 = l
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(2, 2), r_num=1, b_alphas=[1, 1, 1])(l)
# l_skip = ConvCapsuleLayer3D(kernel_size=3, num_capsule=32, num_atoms=8, strides=1, padding='same', routings=3)(l)
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = Conv2DCaps(32, 8, kernel_size=(3, 3), strides=(1, 1), r_num=1, b_alphas=[1, 1, 1])(l)
# l = layers.Add()([l, l_skip])
# l2 = l
la = FlattenCaps()(l)
# la = FlattenCaps()(l2)
# lb = FlattenCaps()(l1)
# l = layers.Concatenate(axis=-2)([la, lb])
# l = Dropout(0.4)(l)
digits_caps = CapsuleLayer(num_capsule=n_class, dim_capsule=16, routings=routings, channels=0, name='digit_caps')(la)
l = CapsToScalars(name='capsnet')(digits_caps)
m_capsnet = models.Model(inputs=[x33,x15], outputs=l, name='capsnet_model')
y = Input(shape=(n_class,))
masked_by_y = Mask_CID()([digits_caps, y])
masked = Mask_CID()(digits_caps)
# Decoder Network
decoder = models.Sequential(name='decoder')
decoder.add(Dense(input_dim=16, activation="relu", output_dim=8 *8 * 16))
decoder.add(Reshape((8, 8, 16)))
decoder.add(BatchNormalization(momentum=0.8))
decoder.add(Deconvolution2D(64, 3, 3, subsample=(1, 1), border_mode='same'))
decoder.add(Deconvolution2D(32, 3, 3, subsample=(2, 2), border_mode='same'))
decoder.add(Deconvolution2D(16, 3, 3, subsample=(1, 1), border_mode='same'))
decoder.add(Deconvolution2D(1, 3, 3, subsample=(2, 2), border_mode='valid'))
decoder.add(Activation("relu"))
decoder.add(Reshape(target_shape=(33, 33, 1), name='out_recon'))
train_model= models.Model([x33,x15, y], [m_capsnet.output, decoder(masked_by_y)])
eval_model = models.Model([x33,x15], [m_capsnet.output, decoder(masked)])
train_model.summary()
return train_model, eval_model
def MsECapsNet(input_shape, n_class, routings):
# K.set_image_dim_ordering('th')
x = Input(input_shape, name='input')
# Part1
conv1 = Conv2D(64, (3, 3), padding='same', name='conv1')(x)
bn1 = BatchNormalization(name='bn1')(conv1)
relu1 = ReLU()(bn1)
pool1 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(relu1)
aside_pool1 = MaxPool2D((2, 2),
strides=(2, 2),
padding='same',
name='aside_pool1')(x)
concat1 = concatenate([pool1, aside_pool1])
conv2 = Conv2D(128, (3, 3), padding='same', name='conv2')(pool1)
bn2 = BatchNormalization(name='bn2')(conv2)
relu2 = ReLU()(bn2)
pool2 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(relu2)
aside_pool2 = MaxPool2D((2, 2),
strides=(2, 2),
padding='same',
name='aside_pool2')(concat1)
concat2 = concatenate([pool2, aside_pool2])
conv3 = Conv2D(128, (3, 3), padding='same', name='conv3')(pool2)
bn3 = BatchNormalization(name='bn3')(conv3)
relu3 = ReLU()(bn3)
pool3 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(relu3)
aside_pool3 = MaxPool2D((2, 2),
strides=(2, 2),
padding='same',
name='aside_pool3')(concat2)
concat3 = concatenate([pool3, aside_pool3])
conv4 = Conv2D(128, (3, 3), padding='same', name='conv4')(pool3)
bn4 = BatchNormalization(name='bn4')(conv4)
relu4 = ReLU()(bn4)
pool4 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(relu4)
aside_pool4 = MaxPool2D((2, 2),
strides=(2, 2),
padding='same',
name='aside_pool4')(concat3)
concat4 = concatenate([pool4, aside_pool4])
conv5 = Conv2D(128, (3, 3), padding='same', name='conv5')(pool4)
bn5 = BatchNormalization(name='bn5')(conv5)
relu5 = ReLU()(bn5)
pool5 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool5')(relu5)
aside_pool5 = MaxPool2D((2, 2),
strides=(2, 2),
padding='same',
name='aside_pool5')(concat4)
concat5 = concatenate([pool5, aside_pool5])
# Part2-branch-a
primarycaps = PrimaryCap(concat5,
dim_capsule=8,
n_channels=32,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps')
digitcaps = CapsuleLayer(num_capsule=n_class,
dim_capsule=16,
routings=routings,
name='digitcaps')(primarycaps)
out_caps = Length(name='capsnet')(digitcaps)
# Part2-branch-b
flastten = Flatten()(concat5)
fc1 = Dense(n_class, activation='sigmoid', name='fc1')(flastten)
# Part3
add = Add(name='add')([out_caps, fc1])
train_model = models.Model(x, add, name='MsECapsNet')
return train_model
def DenseCapsNet(input_shape, n_class, routings):
# K.set_image_dim_ordering('th')
x = Input(input_shape, name='input')
# Part1
conv1 = Conv2D(64, (3, 3), padding='same', name='conv1')(x)
bn1 = BatchNormalization(name='bn1')(conv1)
relu1 = ReLU()(bn1)
pool1 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(relu1)
drop1 = Dropout(0.3, name='dropout1')(pool1)
conv2 = Conv2D(128, (3, 3), padding='same', name='conv2')(drop1)
bn2 = BatchNormalization(name='bn2')(conv2)
relu2 = ReLU()(bn2)
pool2 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(relu2)
drop2 = Dropout(0.3, name='dropout2')(pool2)
conv3 = Conv2D(128, (3, 3), padding='same', name='conv3')(drop2)
bn3 = BatchNormalization(name='bn3')(conv3)
relu3 = ReLU()(bn3)
pool3 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(relu3)
drop3 = Dropout(0.3, name='dropout3')(pool3)
conv4 = Conv2D(128, (3, 3), padding='same', name='conv4')(drop3)
bn4 = BatchNormalization(name='bn4')(conv4)
relu4 = ReLU()(bn4)
pool4 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(relu4)
drop4 = Dropout(0.3, name='dropout4')(pool4)
conv5 = Conv2D(128, (3, 3), padding='same', name='conv5')(drop4)
bn5 = BatchNormalization(name='bn5')(conv5)
relu5 = ReLU()(bn5)
pool5 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool5')(relu5)
drop5 = Dropout(0.3, name='dropout5')(pool5)
conv6 = Conv2D(128, (3, 3), padding='same', name='conv6')(drop5)
bn6 = BatchNormalization(name='bn6')(conv6)
relu6 = ReLU()(bn6)
pool6 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool6')(relu6)
drop6 = Dropout(0.3, name='dropout6')(pool6)
conv7 = Conv2D(128, (3, 3), padding='same', name='conv7')(drop6)
bn7 = BatchNormalization(name='bn7')(conv7)
relu7 = ReLU()(bn7)
pool7 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool7')(relu7)
drop7 = Dropout(0.3, name='dropout7')(pool7)
# Part2-branch-a
primarycaps = PrimaryCap(drop6,
dim_capsule=8,
n_channels=32,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps')
digitcaps = CapsuleLayer(num_capsule=n_class,
dim_capsule=16,
routings=routings,
name='digitcaps')(primarycaps)
out_caps = Length(name='capsnet')(digitcaps)
# # Part2-branch-b
densenet = DenseNet(img_input=drop2,
classes=50,
activation='sigmoid',
depth=40)
# # Part3
add = Add(name='add')([out_caps, densenet])
train_model = models.Model(x, add, name='DenseCapsNet')
return train_model
def MultiScaleCapsNet(input_shape, n_class, routings):
# K.set_image_dim_ordering('th')
x = Input(input_shape, name='input')
# Part1
conv1 = Conv2D(64, (3, 3), padding='same', name='conv1')(x)
bn1 = BatchNormalization(name='bn1')(conv1)
relu1 = ReLU()(bn1)
pool1 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(relu1)
drop1 = Dropout(0.3, name='dropout1')(pool1)
conv2 = Conv2D(128, (3, 3), padding='same', name='conv2')(drop1)
bn2 = BatchNormalization(name='bn2')(conv2)
relu2 = ReLU()(bn2)
pool2 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(relu2)
drop2 = Dropout(0.3, name='dropout2')(pool2)
conv3 = Conv2D(128, (3, 3), padding='same', name='conv3')(drop2)
bn3 = BatchNormalization(name='bn3')(conv3)
relu3 = ReLU()(bn3)
pool3 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(relu3)
drop3 = Dropout(0.3, name='dropout3')(pool3)
conv4 = Conv2D(128, (3, 3), padding='same', name='conv4')(drop3)
bn4 = BatchNormalization(name='bn4')(conv4)
relu4 = ReLU()(bn4)
pool4 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(relu4)
drop4 = Dropout(0.3, name='dropout4')(pool4)
conv5 = Conv2D(128, (3, 3), padding='same', name='conv5')(drop4)
bn5 = BatchNormalization(name='bn5')(conv5)
relu5 = ReLU()(bn5)
pool5 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool5')(relu5)
drop5 = Dropout(0.3, name='dropout5')(pool5)
conv6 = Conv2D(128, (3, 3), padding='same', name='conv6')(drop5)
bn6 = BatchNormalization(name='bn6')(conv6)
relu6 = ReLU()(bn6)
pool6 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool6')(relu6)
drop6 = Dropout(0.3, name='dropout6')(pool6)
conv7 = Conv2D(128, (3, 3), padding='same', name='conv7')(drop6)
bn7 = BatchNormalization(name='bn7')(conv7)
relu7 = ReLU()(bn7)
pool7 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool7')(relu7)
drop7 = Dropout(0.3, name='dropout7')(pool7)
conv8 = Conv2D(128, (3, 3), padding='same', name='conv8')(drop7)
bn8 = BatchNormalization(name='bn8')(conv8)
relu8 = ReLU()(bn8)
pool8 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool8')(relu8)
drop8 = Dropout(0.3, name='dropout8')(pool8)
# Part2-branch-a
primarycaps6 = PrimaryCap(drop6,
dim_capsule=8,
n_channels=16,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps6')
digitcaps6 = CapsuleLayer(num_capsule=n_class,
dim_capsule=32,
routings=routings,
name='digitcaps6')(primarycaps6)
out_caps6 = Length(name='capsnet6')(digitcaps6)
primarycaps7 = PrimaryCap(drop7,
dim_capsule=8,
n_channels=16,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps7')
digitcaps7 = CapsuleLayer(num_capsule=n_class,
dim_capsule=32,
routings=routings,
name='digitcaps7')(primarycaps7)
out_caps7 = Length(name='capsnet7')(digitcaps7)
primarycaps8 = PrimaryCap(drop8,
dim_capsule=8,
n_channels=16,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps8')
digitcaps8 = CapsuleLayer(num_capsule=n_class,
dim_capsule=32,
routings=routings,
name='digitcaps8')(primarycaps8)
out_caps8 = Length(name='capsnet8')(digitcaps8)
# Part2-branch-b
flastten = Flatten()(drop7)
fc1 = Dense(n_class, activation='sigmoid', name='fc1')(flastten)
# Part3
add = Add(name='add')([out_caps6, out_caps7, out_caps8, fc1])
train_model = models.Model(x, add, name='MultiScaleCapsNet')
return train_model
def TestMixCapsNet(input_shape, n_class, routings):
# K.set_image_dim_ordering('th')
x = Input(input_shape, name='input')
# Part1
conv1 = Conv2D(64, (3, 3), padding='same', name='conv1')(x)
bn1 = BatchNormalization(name='bn1')(conv1)
relu1 = ReLU()(bn1)
pool1 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(relu1)
drop1 = Dropout(0.3, name='dropout1')(pool1)
# cbam1 = cbam_block(drop1, 8)
conv2 = Conv2D(128, (3, 3), padding='same', name='conv2')(drop1)
# conv2 = Conv2D(128, (3, 3), padding='same', name='conv2')(cbam1)
bn2 = BatchNormalization(name='bn2')(conv2)
relu2 = ReLU()(bn2)
pool2 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(relu2)
drop2 = Dropout(0.3, name='dropout2')(pool2)
# cbam2 = cbam_block(drop2, 8)
conv3 = Conv2D(128, (3, 3), padding='same', name='conv3')(drop2)
# conv3 = Conv2D(128, (3, 3), padding='same', name='conv3')(cbam2)
bn3 = BatchNormalization(name='bn3')(conv3)
relu3 = ReLU()(bn3)
pool3 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(relu3)
drop3 = Dropout(0.3, name='dropout3')(pool3)
cbam3 = cbam_block(drop3, 8)
conv4 = Conv2D(128, (3, 3), padding='same', name='conv4')(drop3)
# conv4 = Conv2D(128, (3, 3), padding='same', name='conv4')(cbam3)
bn4 = BatchNormalization(name='bn4')(conv4)
relu4 = ReLU()(bn4)
pool4 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(relu4)
drop4 = Dropout(0.3, name='dropout4')(pool4)
# cbam4 = cbam_block(drop4, 8)
conv5 = Conv2D(128, (3, 3), padding='same', name='conv5')(drop4)
# conv5 = Conv2D(128, (3, 3), padding='same', name='conv5')(cbam4)
bn5 = BatchNormalization(name='bn5')(conv5)
relu5 = ReLU()(bn5)
pool5 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool5')(relu5)
drop5 = Dropout(0.3, name='dropout5')(pool5)
# cbam5 = cbam_block(drop5, 8)
conv6 = Conv2D(128, (3, 3), padding='same', name='conv6')(drop5)
# conv6 = Conv2D(128, (3, 3), padding='same', name='conv6')(cbam5)
bn6 = BatchNormalization(name='bn6')(conv6)
relu6 = ReLU()(bn6)
pool6 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool6')(relu6)
drop6 = Dropout(0.3, name='dropout6')(pool6)
# cbam6 = cbam_block(drop6, 8)
conv7 = Conv2D(128, (3, 3), padding='same', name='conv7')(drop6)
# conv7 = Conv2D(128, (3, 3), padding='same', name='conv7')(cbam6)
bn7 = BatchNormalization(name='bn7')(conv7)
relu7 = ReLU()(bn7)
pool7 = MaxPool2D((2, 2), strides=(2, 2), padding='same',
name='pool7')(relu7)
drop7 = Dropout(0.3, name='dropout7')(pool7)
# cbam7 = cbam_block(drop7, 8)
# Part2-branch-a
primarycaps = PrimaryCap(drop7,
dim_capsule=8,
n_channels=32,
kernel_size=3,
strides=2,
padding='same',
name='primarycaps')
digitcaps = CapsuleLayer(num_capsule=n_class,
dim_capsule=16,
routings=routings,
name='digitcaps')(primarycaps)
out_caps = Length(name='capsnet')(digitcaps)
# fc1 = Dense(n_class, activation='sigmoid', name='fc1')(out_caps)
# Part2-branch-b
flastten = Flatten()(drop7)
fc1 = Dense(n_class, activation='sigmoid', name='fc1')(flastten)
# flastten = Flatten()(drop7)
# fc1 = Dense(128, activation='relu', name='fc1')(flastten)
# fc2 = Dense(n_class, activation='sigmoid', name='fc2')(fc1)
# timedis = TimeDistributed(Flatten(), name='timedis')(drop7)
# gru1 = LSTM(64, return_sequences=True, name='gru1')(timedis)
# gru2 = LSTM(64, return_sequences=False, name='gru2')(gru1)
# fc1 = Dense(n_class, activation='sigmoid', name='fc1')(gru2)
# Part3
add = Add(name='add')([out_caps, fc1])
train_model = models.Model(x, add, name='TestMixCapsNet')
return train_model
def DeepCapsNet(input_shape, n_class, routings):
# assemble encoder
x = Input(shape=input_shape)
l = x
l = Conv2D(128, (3, 3), strides=(1, 1), activation='relu',
padding="same")(l) # common conv layer
l = BatchNormalization()(l)
l = ConvertToCaps()(l)
l = Conv2DCaps(32,
4,
kernel_size=(3, 3),
strides=(2, 2),
r_num=1,
b_alphas=[1, 1, 1])(l)
l_skip = Conv2DCaps(32,
4,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
4,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
4,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = layers.Add()([l, l_skip])
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(2, 2),
r_num=1,
b_alphas=[1, 1, 1])(l)
l_skip = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = layers.Add()([l, l_skip])
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(2, 2),
r_num=1,
b_alphas=[1, 1, 1])(l)
l_skip = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = layers.Add()([l, l_skip])
l1 = l
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(2, 2),
r_num=1,
b_alphas=[1, 1, 1])(l)
l_skip = ConvCapsuleLayer3D(kernel_size=3,
num_capsule=32,
num_atoms=8,
strides=1,
padding='same',
routings=3)(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = Conv2DCaps(32,
8,
kernel_size=(3, 3),
strides=(1, 1),
r_num=1,
b_alphas=[1, 1, 1])(l)
l = layers.Add()([l, l_skip])
l2 = l
la = FlattenCaps()(l2)
lb = FlattenCaps()(l1)
l = layers.Concatenate(axis=-2)([la, lb])
# l = Dropout(0.4)(l)
digits_caps = CapsuleLayer(num_capsule=n_class,
dim_capsule=32,
routings=routings,
channels=0,
name='digit_caps')(l)
l = CapsToScalars(name='capsnet')(digits_caps)
m_capsnet = models.Model(inputs=x, outputs=l, name='capsnet_model')
y = Input(shape=(n_class, ))
masked_by_y = Mask_CID()([digits_caps, y])
masked = Mask_CID()(digits_caps)
# Decoder Network
decoder = models.Sequential(name='decoder')
decoder.add(Dense(input_dim=32, activation="relu", output_dim=8 * 8 * 16))
decoder.add(Reshape((8, 8, 16)))
decoder.add(BatchNormalization(momentum=0.8))
decoder.add(Deconvolution2D(64, 3, 3, subsample=(1, 1),
border_mode='same'))
decoder.add(Deconvolution2D(32, 3, 3, subsample=(2, 2),
border_mode='same'))
decoder.add(Deconvolution2D(16, 3, 3, subsample=(2, 2),
border_mode='same'))
decoder.add(Deconvolution2D(8, 3, 3, subsample=(2, 2), border_mode='same'))
decoder.add(Deconvolution2D(3, 3, 3, subsample=(1, 1), border_mode='same'))
decoder.add(Activation("relu"))
decoder.add(Reshape(target_shape=(64, 64, 3), name='out_recon'))
train_model = models.Model(
[x, y], [m_capsnet.output, decoder(masked_by_y)])
eval_model = models.Model(x, [m_capsnet.output, decoder(masked)])
train_model.summary()
return train_model, eval_model
