def VGG16(nb_classes, nb_rows, nb_cols):
print("Compiling model...")
model = Sequential()
model.add(ZeroPadding2D((1,1), input_shape=(1, nb_rows, nb_cols)))
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv2_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv2_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv3_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv3_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv3_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv4_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv4_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv4_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(1024, activation='relu', name='fc1'))
model.add(Dropout(0.5))
model.add(Dense(1024, activation='relu', name='fc2'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes, activation='softmax', name='prediction'))
sgd = SGD(lr=0.01, decay=0, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
return model
python类ZeroPadding2D()的实例源码
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def create_bi_cnn():
model = Sequential()
# 1
model.add(Conv2D(86, (5, 5), strides=3, activation = 'relu', input_shape=(260, 260, 1)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 2
model.add(ZeroPadding2D(1))
model.add(Conv2D(233, (5, 5), strides=2, activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 3
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 4
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 5
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 6
model.add(Conv2D(256, (4, 4), activation='relu'))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
# 7
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def create_bi_cnn():
model = Sequential()
# 1
model.add(Conv2D(86, (5, 5), strides=3, activation = 'relu', input_shape=(260, 260, 1)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 2
model.add(ZeroPadding2D(1))
model.add(Conv2D(233, (5, 5), strides=2, activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 3
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 4
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 5
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 6
model.add(Conv2D(256, (4, 4), activation='relu'))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
# 7
model.add(Dense(fea_dim, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def create_bi_cnn():
model = Sequential()
# 1
model.add(Conv2D(86, (5, 5), strides=3, activation = 'relu', input_shape=(260, 260, 1)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 2
model.add(ZeroPadding2D(1))
model.add(Conv2D(233, (5, 5), strides=2, activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 3
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 4
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 5
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 6
model.add(Conv2D(256, (4, 4), activation='relu'))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
# 7
model.add(Dense(fea_dim, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def create_bi_cnn():
model = Sequential()
# 1
model.add(Conv2D(86, (5, 5), strides=3, activation = 'relu', input_shape=(260, 260, 1)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 2
model.add(ZeroPadding2D(1))
model.add(Conv2D(233, (5, 5), strides=2, activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 3
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 4
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 5
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 6
model.add(Conv2D(256, (4, 4), activation='relu'))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
# 7
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def create_bi_cnn():
model = Sequential()
# 1
model.add(Conv2D(86, (5, 5), strides=3, activation = 'relu', input_shape=(260, 260, 1)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 2
model.add(ZeroPadding2D(1))
model.add(Conv2D(233, (5, 5), strides=2, activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 3
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 4
model.add(ZeroPadding2D(1))
model.add(Conv2D(332, (3, 3), activation = 'relu'))
# 5
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
# 6
model.add(Conv2D(256, (4, 4), activation='relu'))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
# 7
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def SmallNetwork(input_shape):
model = Sequential()
# 2 CNNs blocks comprised of 32 filters of size 3x3.
model.add(ZeroPadding2D((1, 1), input_shape=(img_width, img_height, 3)))
model.add(Convolution2D(32, 3, 3, activation='elu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(32, 3, 3, activation='elu'))
# Maxpooling
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
# 2 CNNs blocks comprised of 64 filters of size 3x3.
model.add(ZeroPadding2D((1, 1), input_shape=(img_width, img_height, 3)))
model.add(Convolution2D(64, 3, 3, activation='elu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='elu'))
# Maxpooling + Dropout to avoid overfitting
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Dropout(0.5))
# 2 CNNs blocks comprised of 128 filters of size 3x3.
model.add(ZeroPadding2D((1, 1), input_shape=(img_width, img_height, 3)))
model.add(Convolution2D(128, 3, 3, activation='elu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='elu'))
# Last Maxpooling. We went from an image (64, 64, 3), to an array of shape (8, 8, 128)
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
# Fully connected layers part.
model.add(Flatten(input_shape=input_shape))
model.add(Dense(256, activation='elu'))
# Dropout here to avoid overfitting
model.add(Dropout(0.5))
model.add(Dense(64, activation='elu'))
# Last Dropout to avoid overfitting
model.add(Dropout(0.5))
model.add(Dense(16, activation='elu'))
model.add(Dense(1))
return model
models.py 文件源码
项目：Ultras-Sound-Nerve-Segmentation---Kaggle
作者: Simoncarbo
项目源码
文件源码
阅读 23
收藏 0
点赞 0
评论 0
def convolutional(nbfilters,fsize1,fsize2,inp,pad = True,subsample = (1,1),batchnorm = True,other_activation = None):
# fsize1 and fsize2 must be the same, and must be odd numbers
if pad and fsize1 > 1: # double check
inp = layers.ZeroPadding2D(padding=(int((fsize1-1)/2), int((fsize2-1)/2)))(inp)
conv = layers.Convolution2D(nbfilters,fsize1,fsize2,border_mode = 'valid',subsample=subsample)(inp)
if batchnorm:
conv = layers.BatchNormalization(mode = 0,axis = 1)(conv)
if other_activation is not None:
conv = activation(other_activation)(conv)
else:
conv = activation()(conv)
return conv
models.py 文件源码
项目：Ultras-Sound-Nerve-Segmentation---Kaggle
作者: Simoncarbo
项目源码
文件源码
阅读 21
收藏 0
点赞 0
评论 0
def local(nbfilters,fsize1,fsize2,inp,pad = True,subsample = (1,1), batchnorm =True, fast = True):
if pad:
inp = layers.ZeroPadding2D(padding=(int((fsize1-1)/2), int((fsize2-1)/2)))(inp)
if not fast:
lconv = layers.LocallyConnected2D(nbfilters,fsize1,fsize2,border_mode = 'valid',subsample=subsample)
else:
lconv = layers_perso.LocallyConnected2D_fast(nbfilters,fsize1,fsize2,border_mode = 'valid',subsample=subsample)
conv = lconv((inp))
if batchnorm:
conv = layers_perso.BatchNormalization_local(lconv,conv)
return activation()(conv)
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def fcn_vggbase(input_shape=(None,None,3)):
img_input = Input(shape=input_shape)
x = ZeroPadding2D(padding=(100, 100), name='pad1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same',name='block5_pool')(x)
x = Conv2D(filters=4096, kernel_size=(7, 7), W_regularizer=l2(0.00005), activation='relu', padding='valid', name='fc6_lsun')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=4096, kernel_size=(1, 1), W_regularizer=l2(0.00005), activation='relu', padding='valid', name='fc7_lsun')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=5, kernel_size=(1, 1), strides=(1,1), kernel_initializer='he_normal', padding='valid', name='lsun_score')(x)
x = Conv2DTranspose(filters=5, kernel_initializer='he_normal', kernel_size=(64, 64), strides=(32, 32), padding='valid',use_bias=False, name='lsun_upscore2')(x)
output = _crop(img_input,offset=(32,32), name='score')(x)
model = Model(img_input, output)
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', VGG_WEIGHTS_PATH_NO_TOP, cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def fcn16s_vggbase(input_shape=None, nb_class=None):
img_input = Input(shape=input_shape)
x = ZeroPadding2D(padding=(100, 100), name='pad1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block4_pool')(x)
pool4 = x
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same',name='block5_pool')(x)
x = Conv2D(filters=4096, kernel_size=(7, 7), W_regularizer=l2(0.00005), activation='relu', padding='valid', name='fc6')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=4096, kernel_size=(1, 1), W_regularizer=l2(0.00005), activation='relu', padding='valid', name='fc7')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=nb_class, kernel_size=(1, 1), strides=(1,1), kernel_initializer='he_normal', padding='valid', name='p5score')(x)
x = Conv2DTranspose(filters=nb_class, kernel_size=(4,4), strides=(2,2), kernel_initializer='he_normal', padding='valid', name='p5upscore')(x)
pool4 = Conv2D(filters=nb_class, kernel_size=(1,1), kernel_initializer='he_normal', padding='valid', name='pool4_score')(pool4)
pool4_score = _crop(x, offset=(5,5), name='pool4_score2')(pool4)
m = merge([pool4_score,x], mode='sum')
upscore = Conv2DTranspose(filters=nb_class, kernel_size=(32,32), strides=(16,16), padding='valid', name='merged_score')(m)
score = _crop(img_input, offset=(27,27), name='output_score')(upscore)
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', VGG_WEIGHTS_PATH_NO_TOP, cache_subdir='models')
mdl = Model(img_input, score, name='fcn16s')
mdl.load_weights(weights_path, by_name=True)
return mdl
def dilated_FCN_addmodule(input_shape=None):
img_input = Input(shape=input_shape)
x = ZeroPadding2D(padding=(100, 100), name='pad1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same',name='block5_pool')(x)
x = Conv2D(filters=4096, kernel_initializer='he_normal', kernel_size=(7, 7), activation='relu', padding='valid', name='fc6')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=4096, kernel_initializer='he_normal', kernel_size=(1, 1), activation='relu', padding='valid', name='fc7')(x)
x = Dropout(0.85)(x)
x = Conv2D(filters=40,kernel_size=(1, 1), strides=(1,1), kernel_initializer='he_normal', padding='valid', name='score_fr')(x)
#x = Cropping2D(cropping=((19, 36),(19, 29)), name='score')(x)
x = ZeroPadding2D(padding=(33,33))(x)
x = Conv2D(2*40, (3,3), kernel_initializer='he_normal',activation='relu', name='dl_conv1')(x)
x = Conv2D(2*40, (3,3), kernel_initializer='he_normal',activation='relu', name='dl_conv2')(x)
x = Conv2D(4*40, (3,3), kernel_initializer='he_normal',dilation_rate=(2,2), activation='relu', name='dl_conv3')(x)
x = Conv2D(8*40, (3,3), kernel_initializer='he_normal',dilation_rate=(4,4), activation='relu', name='dl_conv4')(x)
x = Conv2D(16*40, (3,3), kernel_initializer='he_normal',dilation_rate=(8,8), activation='relu', name='dl_conv5')(x)
x = Conv2D(32*40, (3,3), kernel_initializer='he_normal',dilation_rate=(16,16), activation='relu', name='dl_conv6')(x)
x = Conv2D(32*40, (1,1), kernel_initializer='he_normal',name='dl_conv7')(x)
x = Conv2D(1*40, (1,1), kernel_initializer='he_normal',name='dl_final')(x)
x = Conv2DTranspose(filters=40, kernel_initializer='he_normal', kernel_size=(64, 64), strides=(32, 32), padding='valid',use_bias=False, name='upscore2')(x)
x = CroppingLike2D(img_input, offset='centered', name='score')(x)
mdl = Model(img_input, x, name='dilatedmoduleFCN')
#weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', VGG_WEIGHTS_PATH_NO_TOP, cache_subdir='models')
mdl.load_weights('logs/model_June13_sgd_60kitr.h5', by_name=True)
return mdl
def dilated_FCN_frontended(input_shape=None, weight_decay=None, nb_classes=40):
img_input = Input(shape=input_shape)
#x = ZeroPadding2D(padding=(100, 100), name='pad1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = Conv2D(512, (3,3), dilation_rate=(2,2), activation='relu', name='block5_conv1')(x)
x = Conv2D(512, (3,3), dilation_rate=(2,2), activation='relu', name='block5_conv2')(x)
x = Conv2D(512, (3,3), dilation_rate=(2,2), activation='relu', name='block5_conv3')(x)
x = Conv2D(4096, (3,3), kernel_initializer='he_normal', dilation_rate=(4,4), activation='relu', name='fc6')(x)
x = Dropout(0.5, name='drop6')(x)
x = Conv2D(4096, (1,1), kernel_initializer='he_normal', activation='relu', name='fc7')(x)
x = Dropout(0.5, name='drop7')(x)
x = Conv2D(nb_classes, (1,1), kernel_initializer='he_normal', activation='relu', name='fc_final')(x)
#x = Conv2DTranspose(nb_classes, kernel_size=(64,64), strides=(32,32), padding='valid', name='upscore2')(x)
x = ZeroPadding2D(padding=(33,33))(x)
x = Conv2D(2*nb_classes, (3,3), kernel_initializer='he_normal',activation='relu', name='dl_conv1')(x)
x = Conv2D(2*nb_classes, (3,3), kernel_initializer='he_normal',activation='relu', name='dl_conv2')(x)
x = Conv2D(4*nb_classes, (3,3), kernel_initializer='he_normal',dilation_rate=(2,2), activation='relu', name='dl_conv3')(x)
x = Conv2D(8*nb_classes, (3,3), kernel_initializer='he_normal',dilation_rate=(4,4), activation='relu', name='dl_conv4')(x)
x = Conv2D(16*nb_classes, (3,3), kernel_initializer='he_normal',dilation_rate=(8,8), activation='relu', name='dl_conv5')(x)
x = Conv2D(32*nb_classes, (3,3), kernel_initializer='he_normal',dilation_rate=(16,16), activation='relu', name='dl_conv6')(x)
x = Conv2D(32*nb_classes, (1,1), kernel_initializer='he_normal',name='dl_conv7')(x)
x = Conv2D(1*nb_classes, (1,1), kernel_initializer='he_normal',name='dl_final')(x)
x = Conv2DTranspose(nb_classes, kernel_initializer='he_normal', kernel_size=(64,64), strides=(8,8), padding='valid', name='upscore2')(x)
x = CroppingLike2D(img_input, offset='centered', name='score')(x)
#x = Cropping2D(cropping=((19,36), (19,29)), name='score')(x)
mdl = Model(input=img_input, output=x, name='dilated_fcn')
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', VGG_WEIGHTS_PATH_NO_TOP, cache_subdir='models')
mdl.load_weights(weights_path, by_name=True)
return mdl
def dilat_fets(input_shape=None, classes=40):
model_in = Input(shape=input_shape)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, dilation_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, dilation_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, dilation_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, dilation_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, activation='relu', name='fc-final')(h)
h = ZeroPadding2D(padding=(33, 33))(h)
h = Convolution2D(2 * classes, 3, 3, activation='relu', name='ct_conv1_1')(h)
h = Convolution2D(2 * classes, 3, 3, activation='relu', name='ct_conv1_2')(h)
h = AtrousConvolution2D(4 * classes, 3, 3, dilation_rate=(2, 2), activation='relu', name='ct_conv2_1')(h)
h = AtrousConvolution2D(8 * classes, 3, 3, dilation_rate=(4, 4), activation='relu', name='ct_conv3_1')(h)
h = AtrousConvolution2D(16 * classes, 3, 3, dilation_rate=(8, 8), activation='relu', name='ct_conv4_1')(h)
h = AtrousConvolution2D(32 * classes, 3, 3, dilation_rate=(16, 16), activation='relu', name='ct_conv5_1')(h)
h = Convolution2D(32 * classes, 3, 3, activation='relu', name='ct_fc1')(h)
h = Convolution2D(classes, 1, 1, name='ct_final')(h)
model = Model(input=model_in, output=logits, name='dilation_voc12')
return model
