def block_inception_b(input):
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = -1
branch_0 = conv2d_bn(input, 384, 1, 1)
branch_1 = conv2d_bn(input, 192, 1, 1)
branch_1 = conv2d_bn(branch_1, 224, 1, 7)
branch_1 = conv2d_bn(branch_1, 256, 7, 1)
branch_2 = conv2d_bn(input, 192, 1, 1)
branch_2 = conv2d_bn(branch_2, 192, 7, 1)
branch_2 = conv2d_bn(branch_2, 224, 1, 7)
branch_2 = conv2d_bn(branch_2, 224, 7, 1)
branch_2 = conv2d_bn(branch_2, 256, 1, 7)
branch_3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(input)
branch_3 = conv2d_bn(branch_3, 128, 1, 1)
x = concatenate([branch_0, branch_1, branch_2, branch_3],
axis=channel_axis)
return x
def __transition_block(ip, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
Args:
ip: keras tensor
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps
in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = BatchNormalization(axis=concat_axis, gamma_regularizer=l2(weight_decay),
beta_regularizer=l2(weight_decay))(ip)
x = Activation('relu')(x)
x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_uniform', padding='same', use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling2D((2, 2), strides=(2, 2))(x)
return x
def inception_block_3a(X):
X_3x3 = conv2d_bn(X,
layer='inception_5a_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
X_pool = AveragePooling2D(pool_size=(3, 3), strides=(
3, 3), data_format='channels_first')(X)
X_pool = conv2d_bn(X_pool,
layer='inception_5a_pool',
cv1_out=96,
cv1_filter=(1, 1),
padding=(1, 1))
X_1x1 = conv2d_bn(X,
layer='inception_5a_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception = concatenate([X_3x3, X_pool, X_1x1], axis=1)
return inception
def model_cam(model_input, gap_input, gap_spacial_size, num_classes, cam_conv_layer_name): """Build CAM model architecture # Arguments model_input: input tensor of CAM model gap_input: input tensor to cam gap layers gap_spacial_size: average pooling size cam_conv_layer_name: the name of new added conv layer """ x = Convolution2D(1024, 3, 3, activation='relu', border_mode='same', name=cam_conv_layer_name)(gap_input) # Add GAP layer x = AveragePooling2D((gap_spacial_size, gap_spacial_size))(x) x = Flatten()(x) predictions = Dense(num_classes, activation='softmax')(x) model = Model(input=model_input, output=predictions) return model
def get(input_shape, num_classes, residual_unit_cls, units_per_block):
"""As described in [1]"""
x = Input(shape=input_shape)
conv1 = Conv2D(filters=64,
kernel_size=(7, 7),
strides=(2, 2),
padding='same',
kernel_initializer='glorot_normal')(x)
norm1 = BatchNormalization(axis=3)(conv1)
relu1 = Activation('relu')(norm1)
current = MaxPooling2D(pool_size=(3, 3), strides=(2, 2),
padding='same')(relu1)
filters = 64
for i, units in enumerate(units_per_block):
current = ResidualBlock(units,
filters,
residual_unit_cls,
is_first_block=(i == 0))(current)
filters *= 2
relu1 = Activation('relu')(current)
avg_pool = AveragePooling2D(pool_size=(7, 7), strides=(1, 1))(relu1)
flatten1 = Flatten()(avg_pool)
dense = Dense(units=num_classes, activation='softmax')(flatten1)
return Model(inputs=x, outputs=dense)
def create_model(MAX_QRY_LENGTH = 50, MAX_DOC_LENGTH = 2900, NUM_OF_FEATS = 10, PSGS_SIZE = [(50, 1)], NUM_OF_FILTERS = 5, tau = 1):
alpha_size = len(PSGS_SIZE)
psgMat = Input(shape = (MAX_QRY_LENGTH, MAX_DOC_LENGTH, 1,), name="passage")
homoMat = Input(shape = (NUM_OF_FEATS, ), name="h_feats")
# Convolution2D, Meaning pooling and Max pooling.
# Conv2D, Mean pooling, Max pooling
M, K, r = [], [], []
for idx, PSG_SIZE in enumerate(PSGS_SIZE):
tau = PSG_SIZE[0] / 2
pool_size = (MAX_QRY_LENGTH - PSG_SIZE[0]) / tau + 1
# Convolution
m_1 = Convolution2D(filters=NUM_OF_FILTERS, kernel_size=PSG_SIZE, strides=tau, padding='valid', name="pConv2D_" + str(idx))(psgMat)
M.append(m_1)
# Mean pooling
k_1 = AveragePooling2D(pool_size=(pool_size, 1), strides=1, name="pAvePool_" + str(idx))(M[idx])
K.append(k_1)
# Max Pooling
r_1 = GlobalMaxPooling2D(name="pMaxPool_" + str(idx))(K[idx])
r.append(r_1)
concat_r = concatenate(r)
# Fusion Matrix and predict relevance
# get h(q, d)
# MLP(DENSE(len(r(q,d))))
phi_h = Dense(alpha_size, activation="softmax", name="TrainMat")(homoMat)
dot_prod = dot([concat_r, phi_h], axes = 1, name="rel_dot")
# tanh(dot(r.transpose * h))
pred = Activation("tanh", name="activation_tanh")(dot_prod)
# We now have everything we need to define our model.
model = Model(inputs = [psgMat, homoMat], outputs = pred)
model.summary()
'''
from keras.utils import plot_model
plot_model(model, to_file='model.png')
'''
return model
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None):
""" Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
# Arguments
x: input tensor
stage: index for dense block
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
"""
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_blk'
relu_name_base = 'relu' + str(stage) + '_blk'
pool_name_base = 'pool' + str(stage)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
momentum=1,
name=conv_name_base + '_batch_normalization',
trainable=False)(x, training=False)
x = Scale(axis=concat_axis,
name=conv_name_base + '_scale',
trainable=False)(x)
x = Activation('relu', name=relu_name_base)(x)
x = Conv2D(int(nb_filter * compression), (1, 1),
name=conv_name_base,
use_bias=False,
trainable=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name=pool_name_base)(x)
return x
def transition_block(ip,
nb_filter,
compression=1.0,
dropout_rate=None,
weight_decay=1E-4):
''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
Args:
ip: keras tensor
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
'''
concat_axis = 1 if K.image_dim_ordering() == "th" else -1
x = BatchNormalization(mode=0,
axis=concat_axis,
gamma_regularizer=l2(weight_decay),
beta_regularizer=l2(weight_decay))(ip)
x = Activation('relu')(x)
x = Convolution2D(int(nb_filter * compression),
1,
1,
init="he_uniform",
border_mode="same",
bias=False,
W_regularizer=l2(weight_decay))(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling2D((2, 2), strides=(2, 2))(x)
return x
def __func10__(self, input_shape):
from keras.layers import Input
from keras.models import Model
from keras.layers.pooling import AveragePooling2D
from keras.layers.core import Lambda
from keras import backend as K
from Executer import utils
inception_4e = Input(shape=input_shape)
inception_5a_pool = Lambda(lambda x: x**2,
name='power2_5a')(inception_4e)
inception_5a_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: x * 9,
name='mult9_5a')(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: K.sqrt(x),
name='sqrt_5a')(inception_5a_pool)
inception_5a_pool = utils.conv2d_bn(inception_5a_pool,
layer='inception_5a_pool',
cv1_out=96,
cv1_filter=(1, 1),
padding=(1, 1))
model = Model(inputs=inception_4e, outputs=inception_5a_pool)
return model
def __transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
Args:
ip: keras tensor
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps
in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
myLRelu = Lambda(lambda x: K.relu(x, 0.1))
x = myLRelu(x)
x = Conv2D(int(nb_filter * compression), (1, 1),
kernel_initializer='he_normal',
padding='same',
use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
x = AveragePooling2D((2, 2), strides=(2, 2))(x)
x = squeeze_excite_block(x)
return x
def New_model(n_class):
model_name = 'CNN_12'
N = 224
model = Sequential()
model.add(Convolution2D(32, (3, 3), input_shape=(N, N, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(Convolution2D(32, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Convolution2D(64, (3, 3)))
# model.add(ZeroPadding2D(padding=(1,1)))
# model.add(BatchNormalization())
# model.add(PReLU())
# model.add(Convolution2D(64, (3, 3)))
# model.add(ZeroPadding2D(padding=(1,1)))
# model.add(BatchNormalization())
# model.add(PReLU())
# model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Convolution2D(128, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(Convolution2D(128, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(256, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(Convolution2D(256, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(512, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(Convolution2D(512, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(1028, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(Convolution2D(1028, (3, 3)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(BatchNormalization())
model.add(PReLU())
model.add(AveragePooling2D(pool_size=(2, 2)))
model.add(Flatten())
# Dense = Fully connected layer
model.add(Dense(n_class))
model.add(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, model_name
def resnet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
RESNET50_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5' #'https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_resnet50.h5'
RESNET50_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5' #'https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_notop_resnet50.h5'
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == "channels_last":
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(64, (7, 7),
use_bias=False,
strides=(2, 2),
padding='same',
name='conv1/7x7_s2')(img_input)
x = BatchNormalization(axis=bn_axis, name='conv1/7x7_s2/bn')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = resnet_conv_block(x,
3, [64, 64, 256],
stage=2,
block=1,
strides=(1, 1))
x = resnet_identity_block(x, 3, [64, 64, 256], stage=2, block=2)
x = resnet_identity_block(x, 3, [64, 64, 256], stage=2, block=3)
x = resnet_conv_block(x, 3, [128, 128, 512], stage=3, block=1)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=2)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=3)
x = resnet_identity_block(x, 3, [128, 128, 512], stage=3, block=4)
x = resnet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5)
x = resnet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6)
x = resnet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1)
x = resnet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2)
x = resnet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='classifier')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name='vggface_resnet50')
model.summary()
'''
if weights == 'imagenet':
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
RESNET50_WEIGHTS_PATH,
cache_subdir='./models')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
RESNET50_WEIGHTS_PATH_NO_TOP,
cache_dir="./models")
model.load_weights(weights_path)
if K.backend() == "theano":
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='classifier')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.image_data_format() == "channels_first" and K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif weights is not None:
model.load_weights(weights)
'''
return model
def create_model():
myInput = Input(shape=(150, 150, 3))
x = ZeroPadding2D(padding=(3, 3), input_shape=(96, 96, 3))(myInput)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn1')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
x = Lambda(LRN2D, name='lrn_1')(x)
x = Conv2D(64, (1, 1), name='conv2')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn2')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = Conv2D(192, (3, 3), name='conv3')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn3')(x)
x = Activation('relu')(x)
x = Lambda(LRN2D, name='lrn_2')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
# Inception3a
inception_3a_3x3 = Conv2D(96, (1, 1), name='inception_3a_3x3_conv1')(x)
inception_3a_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_3x3_bn1')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3a_3x3)
inception_3a_3x3 = Conv2D(128, (3, 3),
name='inception_3a_3x3_conv2')(inception_3a_3x3)
inception_3a_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_3x3_bn2')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_5x5 = Conv2D(16, (1, 1), name='inception_3a_5x5_conv1')(x)
inception_3a_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_5x5_bn1')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3a_5x5)
inception_3a_5x5 = Conv2D(32, (5, 5),
name='inception_3a_5x5_conv2')(inception_3a_5x5)
inception_3a_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_5x5_bn2')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_pool = MaxPooling2D(pool_size=3, strides=2)(x)
inception_3a_pool = Conv2D(
32, (1, 1), name='inception_3a_pool_conv')(inception_3a_pool)
inception_3a_pool = BatchNormalization(
axis=3, epsilon=0.00001,
name='inception_3a_pool_bn')(inception_3a_pool)
inception_3a_pool = Activation('relu')(inception_3a_pool)
inception_3a_pool = ZeroPadding2D(padding=((3, 4), (3,
4)))(inception_3a_pool)
inception_3a_1x1 = Conv2D(64, (1, 1), name='inception_3a_1x1_conv')(x)
inception_3a_1x1 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_1x1_bn')(inception_3a_1x1)
inception_3a_1x1 = Activation('relu')(inception_3a_1x1)
inception_3a = concatenate([
inception_3a_3x3, inception_3a_5x5, inception_3a_pool, inception_3a_1x1
],
axis=3)
# Inception3b
inception_3b_3x3 = Conv2D(96, (1, 1),
name='inception_3b_3x3_conv1')(inception_3a)
inception_3b_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_3x3_bn1')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3b_3x3)
inception_3b_3x3 = Conv2D(128, (3, 3),
name='inception_3b_3x3_conv2')(inception_3b_3x3)
inception_3b_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_3x3_bn2')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_5x5 = Conv2D(32, (1, 1),
name='inception_3b_5x5_conv1')(inception_3a)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn1')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3b_5x5)
inception_3b_5x5 = Conv2D(64, (5, 5),
name='inception_3b_5x5_conv2')(inception_3b_5x5)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn2')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_3a)
inception_3b_pool = Conv2D(
64, (1, 1), name='inception_3b_pool_conv')(inception_3b_pool)
inception_3b_pool = BatchNormalization(
axis=3, epsilon=0.00001,
name='inception_3b_pool_bn')(inception_3b_pool)
inception_3b_pool = Activation('relu')(inception_3b_pool)
inception_3b_pool = ZeroPadding2D(padding=(4, 4))(inception_3b_pool)
inception_3b_1x1 = Conv2D(64, (1, 1),
name='inception_3b_1x1_conv')(inception_3a)
inception_3b_1x1 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_1x1_bn')(inception_3b_1x1)
inception_3b_1x1 = Activation('relu')(inception_3b_1x1)
inception_3b = concatenate([
inception_3b_3x3, inception_3b_5x5, inception_3b_pool, inception_3b_1x1
],
axis=3)
# Inception3c
inception_3c_3x3 = utils.conv2d_bn(inception_3b,
layer='inception_3c_3x3',
cv1_out=128,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
inception_3c_5x5 = utils.conv2d_bn(inception_3b,
layer='inception_3c_5x5',
cv1_out=32,
cv1_filter=(1, 1),
cv2_out=64,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
inception_3c_pool = MaxPooling2D(pool_size=3, strides=2)(inception_3b)
inception_3c_pool = ZeroPadding2D(padding=((0, 1), (0,
1)))(inception_3c_pool)
inception_3c = concatenate(
[inception_3c_3x3, inception_3c_5x5, inception_3c_pool], axis=3)
#inception 4a
inception_4a_3x3 = utils.conv2d_bn(inception_3c,
layer='inception_4a_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=192,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
inception_4a_5x5 = utils.conv2d_bn(inception_3c,
layer='inception_4a_5x5',
cv1_out=32,
cv1_filter=(1, 1),
cv2_out=64,
cv2_filter=(5, 5),
cv2_strides=(1, 1),
padding=(2, 2))
inception_4a_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_3c)
inception_4a_pool = utils.conv2d_bn(inception_4a_pool,
layer='inception_4a_pool',
cv1_out=128,
cv1_filter=(1, 1),
padding=(2, 2))
inception_4a_1x1 = utils.conv2d_bn(inception_3c,
layer='inception_4a_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception_4a = concatenate([
inception_4a_3x3, inception_4a_5x5, inception_4a_pool, inception_4a_1x1
],
axis=3)
#inception4e
inception_4e_3x3 = utils.conv2d_bn(inception_4a,
layer='inception_4e_3x3',
cv1_out=160,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
inception_4e_5x5 = utils.conv2d_bn(inception_4a,
layer='inception_4e_5x5',
cv1_out=64,
cv1_filter=(1, 1),
cv2_out=128,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
inception_4e_pool = MaxPooling2D(pool_size=3, strides=2)(inception_4a)
inception_4e_pool = ZeroPadding2D(padding=((0, 1), (0,
1)))(inception_4e_pool)
inception_4e = concatenate(
[inception_4e_3x3, inception_4e_5x5, inception_4e_pool], axis=3)
#inception5a
inception_5a_3x3 = utils.conv2d_bn(inception_4e,
layer='inception_5a_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
inception_5a_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_4e)
inception_5a_pool = utils.conv2d_bn(inception_5a_pool,
layer='inception_5a_pool',
cv1_out=96,
cv1_filter=(1, 1),
padding=(1, 1))
inception_5a_1x1 = utils.conv2d_bn(inception_4e,
layer='inception_5a_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception_5a = concatenate(
[inception_5a_3x3, inception_5a_pool, inception_5a_1x1], axis=3)
#inception_5b
inception_5b_3x3 = utils.conv2d_bn(inception_5a,
layer='inception_5b_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
inception_5b_pool = MaxPooling2D(pool_size=3, strides=2)(inception_5a)
inception_5b_pool = utils.conv2d_bn(inception_5b_pool,
layer='inception_5b_pool',
cv1_out=96,
cv1_filter=(1, 1))
inception_5b_pool = ZeroPadding2D(padding=(1, 1))(inception_5b_pool)
inception_5b_1x1 = utils.conv2d_bn(inception_5a,
layer='inception_5b_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception_5b = concatenate(
[inception_5b_3x3, inception_5b_pool, inception_5b_1x1], axis=3)
av_pool = AveragePooling2D(pool_size=(3, 3), strides=(1, 1))(inception_5b)
reshape_layer = Flatten()(av_pool)
dense_layer = Dense(128, name='dense_layer')(reshape_layer)
norm_layer = Lambda(lambda x: K.l2_normalize(x, axis=1),
name='norm_layer')(dense_layer)
return Model(inputs=[myInput], outputs=norm_layer)
def faceRecoModel(input_shape):
"""
Implementation of the Inception model used for FaceNet
Arguments:
input_shape -- shape of the images of the dataset
Returns:
model -- a Model() instance in Keras
"""
# Define the input as a tensor with shape input_shape
X_input = Input(input_shape)
# Zero-Padding
X = ZeroPadding2D((3, 3))(X_input)
# First Block
X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(X)
X = BatchNormalization(axis=1, name='bn1')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
X = MaxPooling2D((3, 3), strides=2)(X)
# Second Block
X = Conv2D(64, (1, 1), strides=(1, 1), name='conv2')(X)
X = BatchNormalization(axis=1, epsilon=0.00001, name='bn2')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
# Second Block
X = Conv2D(192, (3, 3), strides=(1, 1), name='conv3')(X)
X = BatchNormalization(axis=1, epsilon=0.00001, name='bn3')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
X = MaxPooling2D(pool_size=3, strides=2)(X)
# Inception 1: a/b/c
X = inception_block_1a(X)
X = inception_block_1b(X)
X = inception_block_1c(X)
# Inception 2: a/b
X = inception_block_2a(X)
X = inception_block_2b(X)
# Inception 3: a/b
X = inception_block_3a(X)
X = inception_block_3b(X)
# Top layer
X = AveragePooling2D(pool_size=(3, 3),
strides=(1, 1),
data_format='channels_first')(X)
X = Flatten()(X)
X = Dense(128, name='dense_layer')(X)
# L2 normalization
X = Lambda(lambda x: K.l2_normalize(x, axis=1))(X)
# Create model instance
model = Model(inputs=X_input, outputs=X, name='FaceRecoModel')
return model
def _build_model(self):
self._create_submodels()
# AUTOENCODER #########################################################################################
outer_input_shape = list(self.input_shape)
outer_input_shape[0] *= 2
outer_input_shape[1] *= 2
ae_input = Input(shape=outer_input_shape,
dtype="float32",
name=self.name_prefix + "Autoencoder_Input")
if self.config.tiles_use_global:
GT_fields = Lambda(lambda x: x[:, ..., 3:],
name="Slice_gt_input_{}".format(0))(ae_input)
GT_fields = AveragePooling2D(pool_size=(2, 2))(GT_fields)
# 1. slice
cur_input = Lambda(
lambda x: x[:, 0:self.config.res_y, 0:self.config.res_x, :3],
name="Slice_ae_input_{}".format(0))(ae_input)
if self.config.tiles_use_global:
cur_input = concatenate([cur_input, GT_fields], axis=3)
z0 = self._encoder(cur_input)
output_0 = self._decoder(z0)
# 2. slice
cur_input = Lambda(
lambda x: x[:, 0:self.config.res_y, self.config.res_x:, :3],
name="Slice_ae_input_{}".format(1))(ae_input)
if self.config.tiles_use_global:
cur_input = concatenate([cur_input, GT_fields], axis=3)
z = self._encoder(cur_input)
output_1 = self._decoder(z)
# 3. slice
cur_input = Lambda(
lambda x: x[:, self.config.res_y:, 0:self.config.res_x, :3],
name="Slice_ae_input_{}".format(2))(ae_input)
if self.config.tiles_use_global:
cur_input = concatenate([cur_input, GT_fields], axis=3)
z = self._encoder(cur_input)
output_2 = self._decoder(z)
# 4. slice
cur_input = Lambda(
lambda x: x[:, self.config.res_y:, self.config.res_x:, :3],
name="Slice_ae_input_{}".format(3))(ae_input)
if self.config.tiles_use_global:
cur_input = concatenate([cur_input, GT_fields], axis=3)
z = self._encoder(cur_input)
output_3 = self._decoder(z)
final_out_0 = concatenate([output_0, output_1], axis=2)
final_out_1 = concatenate([output_2, output_3], axis=2)
final_out = concatenate([final_out_0, final_out_1], axis=1)
# print("final_out: {}".format(final_out.shape))
# if self.use_c:
# final_out_c = Lambda(curl, arguments={'data_format': 'NHWC'})(final_out)
# if self.use_c and ("density" in self.config.data_type or "levelset" in self.config.data_type):
# # cut of density part of "out" tensor and concatenate with the "velo_out" tensor
# final_out = Concatenate(axis=-1)([final_out_c, Lambda(K.expand_dims, arguments={'axis': -1})(Lambda(lambda x: x[...,-1])(final_out))])
# print("use_c final_out: {}".format(final_out.shape))
p_pred = self._p_pred(z0)
print("p_pred: {}".format(p_pred.shape))
output_list = [final_out, p_pred]
if self.config.tile_multitile_border > 0:
# Tile Loss
border_region_start = (outer_input_shape[0] //
2) - 1 - self.config.tile_multitile_border
border_region_end = (outer_input_shape[0] //
2) + self.config.tile_multitile_border
tile_output0 = Lambda(
lambda x: x[:, border_region_start:border_region_end, :, :],
name="TileBorderLoss_{}".format(0))(final_out)
border_region_start = (outer_input_shape[1] //
2) - 1 - self.config.tile_multitile_border
border_region_end = (outer_input_shape[1] //
2) + self.config.tile_multitile_border
tile_output1 = Lambda(
lambda x: x[:, :, border_region_start:border_region_end, :],
name="TileBorderLoss_{}".format(1))(final_out)
output_list.append(tile_output0)
output_list.append(tile_output1)
if len(self.gpus) > 1:
with tf.device('/cpu:0'):
self.model = Model(name=self.name_prefix + "Autoencoder",
inputs=ae_input,
outputs=output_list)
else:
self.model = Model(name=self.name_prefix + "Autoencoder",
inputs=ae_input,
outputs=output_list)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_5x5 = Conv2D(32, (1, 1),
name='inception_3b_5x5_conv1')(inception_3a)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn1')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3b_5x5)
inception_3b_5x5 = Conv2D(64, (5, 5),
name='inception_3b_5x5_conv2')(inception_3b_5x5)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn2')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_pool = Lambda(lambda x: x**2, name='power2_3b')(inception_3a)
inception_3b_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: x * 9, name='mult9_3b')(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: K.sqrt(x),
name='sqrt_3b')(inception_3b_pool)
inception_3b_pool = Conv2D(64, (1, 1),
name='inception_3b_pool_conv')(inception_3b_pool)
inception_3b_pool = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_pool_bn')(inception_3b_pool)
inception_3b_pool = Activation('relu')(inception_3b_pool)
inception_3b_pool = ZeroPadding2D(padding=(4, 4))(inception_3b_pool)
inception_3b_1x1 = Conv2D(64, (1, 1),
name='inception_3b_1x1_conv')(inception_3a)
inception_3b_1x1 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_1x1_bn')(inception_3b_1x1)
inception_3b_1x1 = Activation('relu')(inception_3b_1x1)
def build(input_shape,
num_outputs,
block_fn,
repetitions,
logits_and_block_endpoints=False,
original_resnet=False,
input_tensor=None):
if input_shape is None and input_tensor is None:
raise Exception(
"Input shape should be a tuple (nb_channels, nb_rows, nb_cols)"
)
assert K.image_dim_ordering() == 'tf'
if input_tensor is None:
input = Input(shape=input_shape, name="input_image")
else:
input = input_tensor
resnet_blocks_endpoints = []
if original_resnet:
conv1 = _conv_bn_relu(filters=64,
kernel_size=(7, 7),
strides=(2, 2),
name="resnet_initial_conv1")(input)
conv1 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding="same",
name="resnet_initial_pool1")(conv1)
else:
conv1 = _conv_bn_relu(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
name="resnet_initial_conv1")(input)
conv1 = _conv_bn_relu(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
name="resnet_initial_conv2")(conv1)
if logits_and_block_endpoints:
resnet_blocks_endpoints.append(conv1)
conv1 = MaxPooling2D(pool_size=(2, 2),
padding="same",
name="resnet_initial_pool1")(conv1)
block = conv1
filters = 64
for i, r in enumerate(repetitions):
block = _residual_block(block_fn,
filters=filters,
repetitions=r,
is_first_layer=(i == 0))(block)
filters *= 2
if logits_and_block_endpoints:
"""Save each residual block."""
resnet_blocks_endpoints.append(block)
if logits_and_block_endpoints:
return resnet_blocks_endpoints, input
block = Graph_utils._bn_relu()(block)
block_shape = K.int_shape(block)
pool2 = AveragePooling2D(pool_size=(block_shape[1], block_shape[2]),
strides=(1, 1))(block)
flatten1 = Flatten()(pool2)
dense = Dense(units=num_outputs,
kernel_initializer="he_normal",
activation="softmax")(flatten1)
model = Model(inputs=input, outputs=dense)
return model
def max_avg_pool2d(x):
max_x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(x)
mean_x = AveragePooling2D(pool_size=(2, 2), strides=(2, 2))(x)
return Add()([max_x, mean_x]) # concatenate on channel
def build_model():
'''
#先定義好框架
#第一步從input吃起
'''
input_img = Input(shape=(48, 48, 1))
'''
先來看一下keras document 的Conv2D
keras.layers.Conv2D(filters, kernel_size, strides=(1,1), padding='valid',
data_format=None, dilation_rate=(1,1), activation=None,
ues_bias=True, kernel_initializer='glorot_uniform',
bias_initializer='zeros', kernel_regularizer=None,
bias_regularizer=None, activity_regularizer=None,
kernel_constraint=None, bias_constraint=None)
'''
# 64個(5*5)filters
# no padding不會在原有輸入的基礎上添加新的像素
# 將input放在最後面括號內，也是一種置入"self"參數的方式
block1 = Conv2D(64, (5, 5), padding='valid', activation='relu')(input_img)
# 在邊界加上為0的padding，重新變回48*48
# 表示輸入中維度的順序，channels_last對應輸入尺寸為(batch, height, width, channels)
block1 = ZeroPadding2D(padding=(2, 2), data_format='channels_last')(block1)
# Maxpooling也可以設stride
block1 = MaxPooling2D(pool_size=(5, 5), strides=(2, 2))(block1)
block2 = Conv2D(64, (3, 3), activation='relu')(block1)
block2 = ZeroPadding2D(padding=(1, 1), data_format='channels_last')(block2)
block3 = Conv2D(64, (3, 3), activation='relu')(block2)
block3 = AveragePooling2D(pool_size=(3, 3), strides=(2, 2))(block3)
block3 = ZeroPadding2D(padding=(1, 1), data_format='channels_last')(block3)
block4 = Conv2D(128, (3, 3), activation='relu')(block3)
block4 = ZeroPadding2D(padding=(1, 1), data_format='channels_last')(block4)
block5 = Conv2D(128, (3, 3), activation='relu')(block4)
block5 = ZeroPadding2D(padding=(1, 1), data_format='channels_last')(block5)
block5 = AveragePooling2D(pool_size=(3, 3), strides=(2, 2))(block5)
block5 = Flatten()(block5)
fc1 = Dense(1024, activation=('relu'))(block5)
fc1 = Dropout(0.5)(fc1)
fc2 = Dense(1024, activation='relu')(fc1)
fc2 = Dropout(0.5)(fc2)
predict = Dense(7)(fc2)
predict = Activation('softmax')(predict)
model = Model(inputs=input_img, outputs=predict)
# opt = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
# opt = Adam(lr=1e-3)
opt = Adadelta(lr=0.1, rho=0.95, epsilon=1e-08)
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
# 輸出整個模型的摘要資訊，包含簡單的結構表與參數統計
model.summary()
return model
conv6_resized = K.reshape(conv6_resized,
(-1, num_input_channels, 256 * 256))
classmap = K.dot(WT, conv6_resized).reshape((-1, nb_classes, 256, 256))
get_cmap = K.function([inc], classmap)
return get_cmap([X])
if __name__ == '__main__':
model = VGGCAM(20)
model.summary()
model = load_model('VOC-CLS.model')
x = model.input
y = model.layers[-8].output
# Add another conv layer with ReLU + GAP
y = Convolution2D(1024, 3, 3, activation='relu', border_mode="same")(y)
y = AveragePooling2D((16, 16))(y)
y = Flatten()(y)
# Add the W layer
y = Dense(20, activation='softmax')(y)
voc_cam = Model(x, y)
voc_cam.summary()
voc_cam.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
train_generator = loadData(image_path="/home/andrew/VOC-CLS/")
weight_path = "voc_cam_"
# checkpointer = ModelCheckpoint(filepath=weight_path + 'weights.{epoch:02d}-{loss:.4f}.hdf5',
# monitor='loss', verbose=1, save_best_only=True, period=2)
#
# voc_cam.fit_generator(generator=train_generator, nb_epoch=100, samples_per_epoch=14000,
block1 = build_resnet_block(hb1, nb_reps = 3, nb_conv = nb_conv,
nb_filters = nb_filters,
hbp = hbp, wd = wd, data_format = data_format)
hb2 = HB_2d_conv(hbp, shift = -2)(block1)
block2 = build_resnet_block(hb2, nb_reps = 3, nb_conv = nb_conv,
nb_filters = 2 * nb_filters,
hbp = hbp, wd = wd, stride = 2,
data_format = data_format)
hb3 = HB_2d_conv(hbp, shift = -3)(block2)
block3 = build_resnet_block(hb3, nb_reps = 3,
nb_conv = nb_conv, nb_filters = 4 * nb_filters,
hbp = hbp, wd = wd, stride = 2,
data_format = data_format)
bn_pre_pool = BatchNormalization(axis = 1)(block3)
rectifier_pre_pool = Lambda(rectifier)(bn_pre_pool)
pool = AveragePooling2D(pool_size=(8, 8), data_format = data_format)(rectifier_pre_pool)
flat = Flatten()(pool)
dense = Dense(nb_classes, activation = 'softmax',
kernel_regularizer = regularizers.l2(wd),
use_bias = False)(flat)
model = Model(inputs = inp, outputs = dense)
datagen = ImageDataGenerator(width_shift_range = 0.15,
height_shift_range = 0.15,
zoom_range = 0.0,
rotation_range = 0,
horizontal_flip = True,
fill_mode='reflect',
data_format = data_format)
sgd = SGD(lr = 0.1, momentum = 0.9, decay = 0.00, nesterov = True)
def loadModel(url = 'https://drive.google.com/uc?id=1LSe1YCV1x-BfNnfb7DFZTNpv_Q9jITxn'):
myInput = Input(shape=(96, 96, 3))
x = ZeroPadding2D(padding=(3, 3), input_shape=(96, 96, 3))(myInput)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn1')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
x = Lambda(lambda x: tf.nn.lrn(x, alpha=1e-4, beta=0.75), name='lrn_1')(x)
x = Conv2D(64, (1, 1), name='conv2')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn2')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = Conv2D(192, (3, 3), name='conv3')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn3')(x)
x = Activation('relu')(x)
x = Lambda(lambda x: tf.nn.lrn(x, alpha=1e-4, beta=0.75), name='lrn_2')(x) #x is equal added
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
# Inception3a
inception_3a_3x3 = Conv2D(96, (1, 1), name='inception_3a_3x3_conv1')(x)
inception_3a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_3x3_bn1')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3a_3x3)
inception_3a_3x3 = Conv2D(128, (3, 3), name='inception_3a_3x3_conv2')(inception_3a_3x3)
inception_3a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_3x3_bn2')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_5x5 = Conv2D(16, (1, 1), name='inception_3a_5x5_conv1')(x)
inception_3a_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_5x5_bn1')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3a_5x5)
inception_3a_5x5 = Conv2D(32, (5, 5), name='inception_3a_5x5_conv2')(inception_3a_5x5)
inception_3a_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_5x5_bn2')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_pool = MaxPooling2D(pool_size=3, strides=2)(x)
inception_3a_pool = Conv2D(32, (1, 1), name='inception_3a_pool_conv')(inception_3a_pool)
inception_3a_pool = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_pool_bn')(inception_3a_pool)
inception_3a_pool = Activation('relu')(inception_3a_pool)
inception_3a_pool = ZeroPadding2D(padding=((3, 4), (3, 4)))(inception_3a_pool)
inception_3a_1x1 = Conv2D(64, (1, 1), name='inception_3a_1x1_conv')(x)
inception_3a_1x1 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3a_1x1_bn')(inception_3a_1x1)
inception_3a_1x1 = Activation('relu')(inception_3a_1x1)
inception_3a = concatenate([inception_3a_3x3, inception_3a_5x5, inception_3a_pool, inception_3a_1x1], axis=3)
# Inception3b
inception_3b_3x3 = Conv2D(96, (1, 1), name='inception_3b_3x3_conv1')(inception_3a)
inception_3b_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_3x3_bn1')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3b_3x3)
inception_3b_3x3 = Conv2D(128, (3, 3), name='inception_3b_3x3_conv2')(inception_3b_3x3)
inception_3b_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_3x3_bn2')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_5x5 = Conv2D(32, (1, 1), name='inception_3b_5x5_conv1')(inception_3a)
inception_3b_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_5x5_bn1')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3b_5x5)
inception_3b_5x5 = Conv2D(64, (5, 5), name='inception_3b_5x5_conv2')(inception_3b_5x5)
inception_3b_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_5x5_bn2')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_pool = Lambda(lambda x: x**2, name='power2_3b')(inception_3a)
inception_3b_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3))(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: x*9, name='mult9_3b')(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: K.sqrt(x), name='sqrt_3b')(inception_3b_pool)
inception_3b_pool = Conv2D(64, (1, 1), name='inception_3b_pool_conv')(inception_3b_pool)
inception_3b_pool = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_pool_bn')(inception_3b_pool)
inception_3b_pool = Activation('relu')(inception_3b_pool)
inception_3b_pool = ZeroPadding2D(padding=(4, 4))(inception_3b_pool)
inception_3b_1x1 = Conv2D(64, (1, 1), name='inception_3b_1x1_conv')(inception_3a)
inception_3b_1x1 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3b_1x1_bn')(inception_3b_1x1)
inception_3b_1x1 = Activation('relu')(inception_3b_1x1)
inception_3b = concatenate([inception_3b_3x3, inception_3b_5x5, inception_3b_pool, inception_3b_1x1], axis=3)
# Inception3c
inception_3c_3x3 = Conv2D(128, (1, 1), strides=(1, 1), name='inception_3c_3x3_conv1')(inception_3b)
inception_3c_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3c_3x3_bn1')(inception_3c_3x3)
inception_3c_3x3 = Activation('relu')(inception_3c_3x3)
inception_3c_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3c_3x3)
inception_3c_3x3 = Conv2D(256, (3, 3), strides=(2, 2), name='inception_3c_3x3_conv'+'2')(inception_3c_3x3)
inception_3c_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3c_3x3_bn'+'2')(inception_3c_3x3)
inception_3c_3x3 = Activation('relu')(inception_3c_3x3)
inception_3c_5x5 = Conv2D(32, (1, 1), strides=(1, 1), name='inception_3c_5x5_conv1')(inception_3b)
inception_3c_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3c_5x5_bn1')(inception_3c_5x5)
inception_3c_5x5 = Activation('relu')(inception_3c_5x5)
inception_3c_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3c_5x5)
inception_3c_5x5 = Conv2D(64, (5, 5), strides=(2, 2), name='inception_3c_5x5_conv'+'2')(inception_3c_5x5)
inception_3c_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_3c_5x5_bn'+'2')(inception_3c_5x5)
inception_3c_5x5 = Activation('relu')(inception_3c_5x5)
inception_3c_pool = MaxPooling2D(pool_size=3, strides=2)(inception_3b)
inception_3c_pool = ZeroPadding2D(padding=((0, 1), (0, 1)))(inception_3c_pool)
inception_3c = concatenate([inception_3c_3x3, inception_3c_5x5, inception_3c_pool], axis=3)
#inception 4a
inception_4a_3x3 = Conv2D(96, (1, 1), strides=(1, 1), name='inception_4a_3x3_conv'+'1')(inception_3c)
inception_4a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_3x3_bn'+'1')(inception_4a_3x3)
inception_4a_3x3 = Activation('relu')(inception_4a_3x3)
inception_4a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_4a_3x3)
inception_4a_3x3 = Conv2D(192, (3, 3), strides=(1, 1), name='inception_4a_3x3_conv'+'2')(inception_4a_3x3)
inception_4a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_3x3_bn'+'2')(inception_4a_3x3)
inception_4a_3x3 = Activation('relu')(inception_4a_3x3)
inception_4a_5x5 = Conv2D(32, (1,1), strides=(1,1), name='inception_4a_5x5_conv1')(inception_3c)
inception_4a_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_5x5_bn1')(inception_4a_5x5)
inception_4a_5x5 = Activation('relu')(inception_4a_5x5)
inception_4a_5x5 = ZeroPadding2D(padding=(2,2))(inception_4a_5x5)
inception_4a_5x5 = Conv2D(64, (5,5), strides=(1,1), name='inception_4a_5x5_conv'+'2')(inception_4a_5x5)
inception_4a_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_5x5_bn'+'2')(inception_4a_5x5)
inception_4a_5x5 = Activation('relu')(inception_4a_5x5)
inception_4a_pool = Lambda(lambda x: x**2, name='power2_4a')(inception_3c)
inception_4a_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3))(inception_4a_pool)
inception_4a_pool = Lambda(lambda x: x*9, name='mult9_4a')(inception_4a_pool)
inception_4a_pool = Lambda(lambda x: K.sqrt(x), name='sqrt_4a')(inception_4a_pool)
inception_4a_pool = Conv2D(128, (1,1), strides=(1,1), name='inception_4a_pool_conv'+'')(inception_4a_pool)
inception_4a_pool = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_pool_bn'+'')(inception_4a_pool)
inception_4a_pool = Activation('relu')(inception_4a_pool)
inception_4a_pool = ZeroPadding2D(padding=(2, 2))(inception_4a_pool)
inception_4a_1x1 = Conv2D(256, (1, 1), strides=(1, 1), name='inception_4a_1x1_conv'+'')(inception_3c)
inception_4a_1x1 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4a_1x1_bn'+'')(inception_4a_1x1)
inception_4a_1x1 = Activation('relu')(inception_4a_1x1)
inception_4a = concatenate([inception_4a_3x3, inception_4a_5x5, inception_4a_pool, inception_4a_1x1], axis=3)
#inception4e
inception_4e_3x3 = Conv2D(160, (1,1), strides=(1,1), name='inception_4e_3x3_conv'+'1')(inception_4a)
inception_4e_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4e_3x3_bn'+'1')(inception_4e_3x3)
inception_4e_3x3 = Activation('relu')(inception_4e_3x3)
inception_4e_3x3 = ZeroPadding2D(padding=(1, 1))(inception_4e_3x3)
inception_4e_3x3 = Conv2D(256, (3,3), strides=(2,2), name='inception_4e_3x3_conv'+'2')(inception_4e_3x3)
inception_4e_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4e_3x3_bn'+'2')(inception_4e_3x3)
inception_4e_3x3 = Activation('relu')(inception_4e_3x3)
inception_4e_5x5 = Conv2D(64, (1,1), strides=(1,1), name='inception_4e_5x5_conv'+'1')(inception_4a)
inception_4e_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4e_5x5_bn'+'1')(inception_4e_5x5)
inception_4e_5x5 = Activation('relu')(inception_4e_5x5)
inception_4e_5x5 = ZeroPadding2D(padding=(2, 2))(inception_4e_5x5)
inception_4e_5x5 = Conv2D(128, (5,5), strides=(2,2), name='inception_4e_5x5_conv'+'2')(inception_4e_5x5)
inception_4e_5x5 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_4e_5x5_bn'+'2')(inception_4e_5x5)
inception_4e_5x5 = Activation('relu')(inception_4e_5x5)
inception_4e_pool = MaxPooling2D(pool_size=3, strides=2)(inception_4a)
inception_4e_pool = ZeroPadding2D(padding=((0, 1), (0, 1)))(inception_4e_pool)
inception_4e = concatenate([inception_4e_3x3, inception_4e_5x5, inception_4e_pool], axis=3)
#inception5a
inception_5a_3x3 = Conv2D(96, (1,1), strides=(1,1), name='inception_5a_3x3_conv'+'1')(inception_4e)
inception_5a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5a_3x3_bn'+'1')(inception_5a_3x3)
inception_5a_3x3 = Activation('relu')(inception_5a_3x3)
inception_5a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_5a_3x3)
inception_5a_3x3 = Conv2D(384, (3,3), strides=(1,1), name='inception_5a_3x3_conv'+'2')(inception_5a_3x3)
inception_5a_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5a_3x3_bn'+'2')(inception_5a_3x3)
inception_5a_3x3 = Activation('relu')(inception_5a_3x3)
inception_5a_pool = Lambda(lambda x: x**2, name='power2_5a')(inception_4e)
inception_5a_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3))(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: x*9, name='mult9_5a')(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: K.sqrt(x), name='sqrt_5a')(inception_5a_pool)
inception_5a_pool = Conv2D(96, (1,1), strides=(1,1), name='inception_5a_pool_conv'+'')(inception_5a_pool)
inception_5a_pool = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5a_pool_bn'+'')(inception_5a_pool)
inception_5a_pool = Activation('relu')(inception_5a_pool)
inception_5a_pool = ZeroPadding2D(padding=(1,1))(inception_5a_pool)
inception_5a_1x1 = Conv2D(256, (1,1), strides=(1,1), name='inception_5a_1x1_conv'+'')(inception_4e)
inception_5a_1x1 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5a_1x1_bn'+'')(inception_5a_1x1)
inception_5a_1x1 = Activation('relu')(inception_5a_1x1)
inception_5a = concatenate([inception_5a_3x3, inception_5a_pool, inception_5a_1x1], axis=3)
#inception_5b
inception_5b_3x3 = Conv2D(96, (1,1), strides=(1,1), name='inception_5b_3x3_conv'+'1')(inception_5a)
inception_5b_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5b_3x3_bn'+'1')(inception_5b_3x3)
inception_5b_3x3 = Activation('relu')(inception_5b_3x3)
inception_5b_3x3 = ZeroPadding2D(padding=(1,1))(inception_5b_3x3)
inception_5b_3x3 = Conv2D(384, (3,3), strides=(1,1), name='inception_5b_3x3_conv'+'2')(inception_5b_3x3)
inception_5b_3x3 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5b_3x3_bn'+'2')(inception_5b_3x3)
inception_5b_3x3 = Activation('relu')(inception_5b_3x3)
inception_5b_pool = MaxPooling2D(pool_size=3, strides=2)(inception_5a)
inception_5b_pool = Conv2D(96, (1,1), strides=(1,1), name='inception_5b_pool_conv'+'')(inception_5b_pool)
inception_5b_pool = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5b_pool_bn'+'')(inception_5b_pool)
inception_5b_pool = Activation('relu')(inception_5b_pool)
inception_5b_pool = ZeroPadding2D(padding=(1, 1))(inception_5b_pool)
inception_5b_1x1 = Conv2D(256, (1,1), strides=(1,1), name='inception_5b_1x1_conv'+'')(inception_5a)
inception_5b_1x1 = BatchNormalization(axis=3, epsilon=0.00001, name='inception_5b_1x1_bn'+'')(inception_5b_1x1)
inception_5b_1x1 = Activation('relu')(inception_5b_1x1)
inception_5b = concatenate([inception_5b_3x3, inception_5b_pool, inception_5b_1x1], axis=3)
av_pool = AveragePooling2D(pool_size=(3, 3), strides=(1, 1))(inception_5b)
reshape_layer = Flatten()(av_pool)
dense_layer = Dense(128, name='dense_layer')(reshape_layer)
norm_layer = Lambda(lambda x: K.l2_normalize(x, axis=1), name='norm_layer')(dense_layer)
# Final Model
model = Model(inputs=[myInput], outputs=norm_layer)
#-----------------------------------
home = str(Path.home())
if os.path.isfile(home+'/.deepface/weights/openface_weights.h5') != True:
print("openface_weights.h5 will be downloaded...")
output = home+'/.deepface/weights/openface_weights.h5'
gdown.download(url, output, quiet=False)
#-----------------------------------
model.load_weights(home+'/.deepface/weights/openface_weights.h5')
#-----------------------------------
return model
horizontal_flip=True,
fill_mode="nearest")
valAug = ImageDataGenerator()
mean = np.array([123.68, 116.779, 103.939], dtype="float32")
trainAug.mean = mean
valAug.mean = mean
#Carga la red ResNet-50
baseModel = ResNet50(weights="imagenet",
include_top=False,
input_tensor=Input(shape=(224, 224, 3)))
headModel = baseModel.output
headModel = AveragePooling2D(pool_size=(7, 7))(headModel)
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(len(lb.classes_), activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)
for layer in baseModel.layers:
layer.trainable = False
#Compila el modelo
print("[INFO] Compilando el modelo...")
opt = SGD(lr=1e-4, momentum=0.9, decay=1e-4 / args["epochs"])
model.compile(loss="categorical_crossentropy",
optimizer=opt,
def inception_v4_model(img_rows,
img_cols,
color_type=1,
num_classes=None,
dropout_keep_prob=0.2):
'''
Inception V4 Model for Keras
Model Schema is based on
https://github.com/kentsommer/keras-inceptionV4
ImageNet Pretrained Weights
Theano: https://github.com/kentsommer/keras-inceptionV4/releases/download/2.0/inception-v4_weights_th_dim_ordering_th_kernels.h5
TensorFlow: https://github.com/kentsommer/keras-inceptionV4/releases/download/2.0/inception-v4_weights_tf_dim_ordering_tf_kernels.h5
Parameters:
img_rows, img_cols - resolution of inputs
channel - 1 for grayscale, 3 for color
num_classes - number of class labels for our classification task
'''
# Input Shape is 299 x 299 x 3 (tf) or 3 x 299 x 299 (th)
if K.image_dim_ordering() == 'th':
inputs = Input((3, 299, 299))
else:
inputs = Input((299, 299, 3))
# Make inception base
net = inception_v4_base(inputs)
# Final pooling and prediction
# 8 x 8 x 1536
net_old = AveragePooling2D((8, 8), border_mode='valid')(net)
# 1 x 1 x 1536
net_old = Dropout(dropout_keep_prob)(net_old)
net_old = Flatten()(net_old)
# 1536
predictions = Dense(output_dim=1001, activation='softmax')(net_old)
model = Model(inputs, predictions, name='inception_v4')
weights_path = inception4_weights
# if K.image_dim_ordering() == 'th':
# # Use pre-trained weights for Theano backend
# weights_path = 'imagenet_models/inception-v4_weights_th_dim_ordering_th_kernels.h5'
# else:
# # Use pre-trained weights for Tensorflow backend
# weights_path = 'imagenet_models/inception-v4_weights_tf_dim_ordering_tf_kernels.h5'
model.load_weights(weights_path, by_name=True)
# Truncate and replace softmax layer for transfer learning
# Cannot use model.layers.pop() since model is not of Sequential() type
# The method below works since pre-trained weights are stored in layers but not in the model
net_ft = AveragePooling2D((8, 8), border_mode='valid')(net)
net_ft = Dropout(dropout_keep_prob)(net_ft)
net_ft = Flatten()(net_ft)
predictions_ft = Dense(output_dim=num_classes,
activation='softmax')(net_ft)
model = Model(inputs, predictions_ft, name='inception_v4')
# Learning rate is changed to 0.001
# sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
# model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
return model
def Baseline(nb_classes,
img_dim,
depth,
nb_dense_block,
growth_rate,
nb_filter,
dropout_rate=None,
weight_decay=1E-4,
compression=0.5):
if K.image_dim_ordering() == "th":
concat_axis = 1
elif K.image_dim_ordering() == "tf":
concat_axis = -1
model_input = Input(shape=(224, 224, 3))
#init block
print("init block...")
#==================================================================================
# x = ConvBNAct(model_input,32,3,3)
# x = ConvBNAct(x,64,3,3)
# if dropout_rate:
# x = Dropout(dropout_rate)(x)
# x_1 = AveragePooling2D((2, 2), strides=(2,2))(x)
#==================================================================================
x = Convolution2D(32,
5,
5,
init="he_uniform",
border_mode="same",
bias=False,
W_regularizer=l2(weight_decay),
subsample=(2, 2))(model_input)
x = BatchNormalization(mode=0,
axis=-1,
gamma_regularizer=l2(weight_decay),
beta_regularizer=l2(weight_decay))(x)
x_1 = Activation('relu')(x)
#==================================================================================
#main flow
print("main flow...")
#==================================================================================
#nb_groups = 32
#slices = [4,8,16]
nb_block = 4
c_init = 8
c_factor = [1, 1, 2, 4]
cs = [64, 128, 256, 512]
#stage 1
#---------------------------------------------------------------
for g in range(nb_block):
print("nb block%d" % g)
merge_adapting_unit = []
merge_path = []
merge_block = []
c = c_init * c_factor[g]
# merge_block.append(x)
for i in range(int(cs[g] / c)):
print("nb block %d nb group %d" % (g, i))
# res_1 = x
x = Convolution2D(c,
1,
1,
init="he_uniform",
border_mode="same",
bias=False,
W_regularizer=l2(weight_decay))(x_1)
merge_block.append(x)
x = BatchNormalization(mode=0,
axis=-1,
gamma_regularizer=l2(weight_decay),
beta_regularizer=l2(weight_decay))(x)
x = Activation('relu')(x)
# x = ConvBNAct(x_1,slices[g],1,1)
#merge_unit = []
#merge_unit.append(x)
x = BottleNeck(x, c, 0.5)
#x = BottleNeck(x,c,0.5)
#merge_unit.append(x)
#x = merge(merge_unit, mode='sum')
#merge_unit = []
#merge_unit.append(x)
x = BottleNeck(x, c, 0.5)
x = BottleNeck(x, c, 0.5)
#merge_unit.append(x)
#x = merge(merge_unit, mode='sum')
merge_path.append(x)
x = merge(merge_path, mode='concat', concat_axis=concat_axis)
block_input = merge(merge_block,
mode='concat',
concat_axis=concat_axis)
x_1 = merge([x, block_input], mode='sum')
if g != nb_block - 1:
merge_adapting_unit.append(x_1)
x = BottleNeck(x_1, int(cs[g]), 0.5)
x = BottleNeck(x, int(cs[g]), 0.5)
merge_adapting_unit.append(x)
x = merge(merge_adapting_unit, mode='sum')
# x = BottleNeck(x,slices[g]*nb_groups*2,0.5)
x_1 = AveragePooling2D((2, 2), strides=(2, 2))(x)
#end flow
print("end flow...")
#==================================================================================
merge_end = []
merge_end.append(x_1)
x = BottleNeck(x_1, int(cs[g]), 0.5)
x = BottleNeck(x, int(cs[g]), 0.5)
merge_end.append(x)
x = merge(merge_end, mode='sum')
x = GlobalAveragePooling2D(dim_ordering="tf")(x)
x = Dense(nb_classes,
activation='softmax',
W_regularizer=l2(weight_decay),
b_regularizer=l2(weight_decay))(x)
Baseline = Model(input=[model_input], output=[x], name="Baseline")
#==================================================================================
#==================================================================================
#==================================================================================
#==================================================================================
#==================================================================================
#==================================================================================
return Baseline
def bounding_box_prediction_layers(inputs, bboxes_per_cell, batch_size):
endpoints = {}
branch88 = Conv2D(96, (1, 1), strides=1, padding='same')(inputs)
branch88 = Conv2D(96, (3, 3), strides=1, padding='same')(branch88)
endpoints['branch88_locs'] = Conv2D(bboxes_per_cell * 4, (1, 1),
strides=1,
padding='same')(branch88)
endpoints['branch88_confs'] = Conv2D(bboxes_per_cell, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch88)
branch66 = Conv2D(96, (3, 3), strides=1, padding='same')(inputs)
branch66 = Conv2D(96, (3, 3), strides=1, padding='valid')(branch66)
endpoints['branch66_locs'] = Conv2D(bboxes_per_cell * 4, (1, 1),
strides=1,
padding='same')(branch66)
endpoints['branch66_confs'] = Conv2D(bboxes_per_cell, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch66)
rightBranchBase = Conv2D(256, (3, 3), strides=(2, 2),
padding='same')(inputs)
branch44 = Conv2D(128, (3, 3), strides=1, padding='same')(rightBranchBase)
endpoints['branch44_locs'] = Conv2D(bboxes_per_cell * 4, (1, 1),
strides=1,
padding='same')(branch44)
endpoints['branch44_confs'] = Conv2D(bboxes_per_cell, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch44)
branch33 = Conv2D(128, (1, 1), strides=1, padding='same')(rightBranchBase)
branch33 = Conv2D(96, (2, 2), strides=1, padding='valid')(branch33)
endpoints['branch33_locs'] = Conv2D(bboxes_per_cell * 4, (1, 1),
strides=1,
padding='same')(branch33)
endpoints['branch33_confs'] = Conv2D(bboxes_per_cell, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch33)
branch22 = Conv2D(128, (1, 1), strides=1, padding='same')(rightBranchBase)
branch22 = Conv2D(96, (3, 3), strides=1, padding='valid')(branch22)
endpoints['branch22_locs'] = Conv2D(bboxes_per_cell * 4, (1, 1),
strides=1,
padding='same')(branch22)
endpoints['branch22_confs'] = Conv2D(bboxes_per_cell, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch22)
branch11 = AveragePooling2D((8, 8), strides=(1, 1),
padding='valid')(inputs)
endpoints['branch11_locs'] = Conv2D(4, (1, 1), strides=1,
padding='same')(branch11)
endpoints['branch11_confs'] = Conv2D(1, (1, 1),
strides=1,
padding='same',
activation='sigmoid')(branch11)
# batch_size = tf.shape(inputs)[0]
locs88 = Reshape((-1, 4))(endpoints['branch88_locs'])
confs88 = Reshape((-1, 1))(endpoints['branch88_confs'])
locs66 = Reshape((-1, 4))(endpoints['branch66_locs'])
confs66 = Reshape((-1, 1))(endpoints['branch66_confs'])
locs44 = Reshape((-1, 4))(endpoints['branch44_locs'])
confs44 = Reshape((-1, 1))(endpoints['branch44_confs'])
locs33 = Reshape((-1, 4))(endpoints['branch33_locs'])
confs33 = Reshape((-1, 1))(endpoints['branch33_confs'])
locs22 = Reshape((-1, 4))(endpoints['branch22_locs'])
confs22 = Reshape((-1, 1))(endpoints['branch22_confs'])
locs11 = Reshape((-1, 4))(endpoints['branch11_locs'])
confs11 = Reshape((-1, 1))(endpoints['branch11_confs'])
locs = Concatenate(axis=1)(
[locs88, locs66, locs44, locs33, locs22, locs11])
confs = Concatenate(axis=1)(
[confs88, confs66, confs44, confs33, confs22, confs11])
loc_confs = Concatenate(axis=2)([locs, confs])
return loc_confs
#with tf.device('/device:GPU:3'):
#x5 = ResidualR(256, 256, x4pool) #12x12x256
#x5 = ResidualR(256, 256, x5)
#x5 = ResidualR(256, 256, x5) #12x12x256
x5 = Conv2D(512, (3, 3), padding='same',
kernel_initializer='he_normal')(x4pool)
x5 = BatchNormalization()(x5)
x5 = layers.LeakyReLU()(x5)
#x5pool = MaxPooling2D(pool_size=(2,2))(x5)
#x6 = ResidualR(256, 512, x5pool) #6x6x512
#x6 = ResidualR(512, 512, x6)
#x6 = ResidualR(512, 512, x6) #6x6x512
block_shape = K.int_shape(x5)
xpool = AveragePooling2D(pool_size=(block_shape[1], block_shape[2]),
strides=(1, 1))(x5)
#xpool = MaxPooling2D(pool_size=(2,2))(x6)
flatten = layers.Flatten()(xpool)
#dense1 = layers.Dense(512)(flatten)
#dense1 = layers.LeakyReLU()(dense1)
#dense1 = layers.Dropout(0.5)(dense1)
#dense2 = layers.Dense(1024)(dense1)
#dense2 = layers.LeakyReLU()(dense2)
#dense2 = layers.Dropout(0.5)(dense2)
output = Dense(20,
use_bias=False,
kernel_regularizer=l2(5e-4),
LR_DECAY = 0.07
N_CLASSES = 10
BN_DECAY = 0.999
BN_EPS = 0.001
STEER_COR = 0.2
TOP_CROP = 50
BOT_CROP = 22
# Generators
tr_gen = batch_generator(tr_samples, batch_size=BATCH_SIZE)
va_gen = batch_generator(va_samples, batch_size=BATCH_SIZE)
# Preprocessing
model = Sequential()
#model.add(Cropping2D(cropping=((TOP_CROP, BOT_CROP), (0, 0)), input_shape=(H, W, C)))
model.add(AveragePooling2D(input_shape=(H, W, C)))
model.add(Lambda(lambda x: x / 255 - 0.5)) # normalize
# Conv1
model.add(
Convolution2D(24,
5,
5,
init='glorot_uniform',
border_mode='same',
subsample=(2, 2)))
model.add(BatchNormalization())
model.add(Activation('relu'))
# Conv2
model.add(Convolution2D(36, 5, 5, init='glorot_uniform', subsample=(2, 2)))
model.add(BatchNormalization())
model.add(Activation('relu'))
def builtModel():
myInput = Input(shape=(96, 96, 3))
x = ZeroPadding2D(padding=(3, 3), input_shape=(96, 96, 3))(myInput)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn1')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
x = Lambda(lambda x: tf.nn.lrn(x, alpha=1e-4, beta=0.75), name='lrn_1')(x)
x = Conv2D(64, (1, 1), name='conv2')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn2')(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = Conv2D(192, (3, 3), name='conv3')(x)
x = BatchNormalization(axis=3, epsilon=0.00001, name='bn3')(x)
x = Activation('relu')(x)
Lambda(lambda x: tf.nn.lrn(x, alpha=1e-4, beta=0.75), name='lrn_2')(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = MaxPooling2D(pool_size=3, strides=2)(x)
# Inception3a
inception_3a_3x3 = Conv2D(96, (1, 1), name='inception_3a_3x3_conv1')(x)
inception_3a_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_3x3_bn1')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3a_3x3)
inception_3a_3x3 = Conv2D(128, (3, 3),
name='inception_3a_3x3_conv2')(inception_3a_3x3)
inception_3a_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_3x3_bn2')(inception_3a_3x3)
inception_3a_3x3 = Activation('relu')(inception_3a_3x3)
inception_3a_5x5 = Conv2D(16, (1, 1), name='inception_3a_5x5_conv1')(x)
inception_3a_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_5x5_bn1')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3a_5x5)
inception_3a_5x5 = Conv2D(32, (5, 5),
name='inception_3a_5x5_conv2')(inception_3a_5x5)
inception_3a_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_5x5_bn2')(inception_3a_5x5)
inception_3a_5x5 = Activation('relu')(inception_3a_5x5)
inception_3a_pool = MaxPooling2D(pool_size=3, strides=2)(x)
inception_3a_pool = Conv2D(
32, (1, 1), name='inception_3a_pool_conv')(inception_3a_pool)
inception_3a_pool = BatchNormalization(
axis=3, epsilon=0.00001,
name='inception_3a_pool_bn')(inception_3a_pool)
inception_3a_pool = Activation('relu')(inception_3a_pool)
inception_3a_pool = ZeroPadding2D(padding=((3, 4), (3,
4)))(inception_3a_pool)
inception_3a_1x1 = Conv2D(64, (1, 1), name='inception_3a_1x1_conv')(x)
inception_3a_1x1 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3a_1x1_bn')(inception_3a_1x1)
inception_3a_1x1 = Activation('relu')(inception_3a_1x1)
inception_3a = concatenate([
inception_3a_3x3, inception_3a_5x5, inception_3a_pool, inception_3a_1x1
],
axis=3)
# Inception3b
inception_3b_3x3 = Conv2D(96, (1, 1),
name='inception_3b_3x3_conv1')(inception_3a)
inception_3b_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_3x3_bn1')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3b_3x3)
inception_3b_3x3 = Conv2D(128, (3, 3),
name='inception_3b_3x3_conv2')(inception_3b_3x3)
inception_3b_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_3x3_bn2')(inception_3b_3x3)
inception_3b_3x3 = Activation('relu')(inception_3b_3x3)
inception_3b_5x5 = Conv2D(32, (1, 1),
name='inception_3b_5x5_conv1')(inception_3a)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn1')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3b_5x5)
inception_3b_5x5 = Conv2D(64, (5, 5),
name='inception_3b_5x5_conv2')(inception_3b_5x5)
inception_3b_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_5x5_bn2')(inception_3b_5x5)
inception_3b_5x5 = Activation('relu')(inception_3b_5x5)
inception_3b_pool = Lambda(lambda x: x**2, name='power2_3b')(inception_3a)
inception_3b_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: x * 9,
name='mult9_3b')(inception_3b_pool)
inception_3b_pool = Lambda(lambda x: K.sqrt(x),
name='sqrt_3b')(inception_3b_pool)
inception_3b_pool = Conv2D(
64, (1, 1), name='inception_3b_pool_conv')(inception_3b_pool)
inception_3b_pool = BatchNormalization(
axis=3, epsilon=0.00001,
name='inception_3b_pool_bn')(inception_3b_pool)
inception_3b_pool = Activation('relu')(inception_3b_pool)
inception_3b_pool = ZeroPadding2D(padding=(4, 4))(inception_3b_pool)
inception_3b_1x1 = Conv2D(64, (1, 1),
name='inception_3b_1x1_conv')(inception_3a)
inception_3b_1x1 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3b_1x1_bn')(inception_3b_1x1)
inception_3b_1x1 = Activation('relu')(inception_3b_1x1)
inception_3b = concatenate([
inception_3b_3x3, inception_3b_5x5, inception_3b_pool, inception_3b_1x1
],
axis=3)
# Inception3c
inception_3c_3x3 = Conv2D(128, (1, 1),
strides=(1, 1),
name='inception_3c_3x3_conv1')(inception_3b)
inception_3c_3x3 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3c_3x3_bn1')(inception_3c_3x3)
inception_3c_3x3 = Activation('relu')(inception_3c_3x3)
inception_3c_3x3 = ZeroPadding2D(padding=(1, 1))(inception_3c_3x3)
inception_3c_3x3 = Conv2D(256, (3, 3),
strides=(2, 2),
name='inception_3c_3x3_conv' +
'2')(inception_3c_3x3)
inception_3c_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_3c_3x3_bn' +
'2')(inception_3c_3x3)
inception_3c_3x3 = Activation('relu')(inception_3c_3x3)
inception_3c_5x5 = Conv2D(32, (1, 1),
strides=(1, 1),
name='inception_3c_5x5_conv1')(inception_3b)
inception_3c_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_3c_5x5_bn1')(inception_3c_5x5)
inception_3c_5x5 = Activation('relu')(inception_3c_5x5)
inception_3c_5x5 = ZeroPadding2D(padding=(2, 2))(inception_3c_5x5)
inception_3c_5x5 = Conv2D(64, (5, 5),
strides=(2, 2),
name='inception_3c_5x5_conv' +
'2')(inception_3c_5x5)
inception_3c_5x5 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_3c_5x5_bn' +
'2')(inception_3c_5x5)
inception_3c_5x5 = Activation('relu')(inception_3c_5x5)
inception_3c_pool = MaxPooling2D(pool_size=3, strides=2)(inception_3b)
inception_3c_pool = ZeroPadding2D(padding=((0, 1), (0,
1)))(inception_3c_pool)
inception_3c = concatenate(
[inception_3c_3x3, inception_3c_5x5, inception_3c_pool], axis=3)
#inception 4a
inception_4a_3x3 = Conv2D(96, (1, 1),
strides=(1, 1),
name='inception_4a_3x3_conv' + '1')(inception_3c)
inception_4a_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4a_3x3_bn' +
'1')(inception_4a_3x3)
inception_4a_3x3 = Activation('relu')(inception_4a_3x3)
inception_4a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_4a_3x3)
inception_4a_3x3 = Conv2D(192, (3, 3),
strides=(1, 1),
name='inception_4a_3x3_conv' +
'2')(inception_4a_3x3)
inception_4a_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4a_3x3_bn' +
'2')(inception_4a_3x3)
inception_4a_3x3 = Activation('relu')(inception_4a_3x3)
inception_4a_5x5 = Conv2D(32, (1, 1),
strides=(1, 1),
name='inception_4a_5x5_conv1')(inception_3c)
inception_4a_5x5 = BatchNormalization(
axis=3, epsilon=0.00001, name='inception_4a_5x5_bn1')(inception_4a_5x5)
inception_4a_5x5 = Activation('relu')(inception_4a_5x5)
inception_4a_5x5 = ZeroPadding2D(padding=(2, 2))(inception_4a_5x5)
inception_4a_5x5 = Conv2D(64, (5, 5),
strides=(1, 1),
name='inception_4a_5x5_conv' +
'2')(inception_4a_5x5)
inception_4a_5x5 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4a_5x5_bn' +
'2')(inception_4a_5x5)
inception_4a_5x5 = Activation('relu')(inception_4a_5x5)
inception_4a_pool = Lambda(lambda x: x**2, name='power2_4a')(inception_3c)
inception_4a_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_4a_pool)
inception_4a_pool = Lambda(lambda x: x * 9,
name='mult9_4a')(inception_4a_pool)
inception_4a_pool = Lambda(lambda x: K.sqrt(x),
name='sqrt_4a')(inception_4a_pool)
inception_4a_pool = Conv2D(128, (1, 1),
strides=(1, 1),
name='inception_4a_pool_conv' +
'')(inception_4a_pool)
inception_4a_pool = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4a_pool_bn' +
'')(inception_4a_pool)
inception_4a_pool = Activation('relu')(inception_4a_pool)
inception_4a_pool = ZeroPadding2D(padding=(2, 2))(inception_4a_pool)
inception_4a_1x1 = Conv2D(256, (1, 1),
strides=(1, 1),
name='inception_4a_1x1_conv' + '')(inception_3c)
inception_4a_1x1 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4a_1x1_bn' +
'')(inception_4a_1x1)
inception_4a_1x1 = Activation('relu')(inception_4a_1x1)
inception_4a = concatenate([
inception_4a_3x3, inception_4a_5x5, inception_4a_pool, inception_4a_1x1
],
axis=3)
#inception4e
inception_4e_3x3 = Conv2D(160, (1, 1),
strides=(1, 1),
name='inception_4e_3x3_conv' + '1')(inception_4a)
inception_4e_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4e_3x3_bn' +
'1')(inception_4e_3x3)
inception_4e_3x3 = Activation('relu')(inception_4e_3x3)
inception_4e_3x3 = ZeroPadding2D(padding=(1, 1))(inception_4e_3x3)
inception_4e_3x3 = Conv2D(256, (3, 3),
strides=(2, 2),
name='inception_4e_3x3_conv' +
'2')(inception_4e_3x3)
inception_4e_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4e_3x3_bn' +
'2')(inception_4e_3x3)
inception_4e_3x3 = Activation('relu')(inception_4e_3x3)
inception_4e_5x5 = Conv2D(64, (1, 1),
strides=(1, 1),
name='inception_4e_5x5_conv' + '1')(inception_4a)
inception_4e_5x5 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4e_5x5_bn' +
'1')(inception_4e_5x5)
inception_4e_5x5 = Activation('relu')(inception_4e_5x5)
inception_4e_5x5 = ZeroPadding2D(padding=(2, 2))(inception_4e_5x5)
inception_4e_5x5 = Conv2D(128, (5, 5),
strides=(2, 2),
name='inception_4e_5x5_conv' +
'2')(inception_4e_5x5)
inception_4e_5x5 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_4e_5x5_bn' +
'2')(inception_4e_5x5)
inception_4e_5x5 = Activation('relu')(inception_4e_5x5)
inception_4e_pool = MaxPooling2D(pool_size=3, strides=2)(inception_4a)
inception_4e_pool = ZeroPadding2D(padding=((0, 1), (0,
1)))(inception_4e_pool)
inception_4e = concatenate(
[inception_4e_3x3, inception_4e_5x5, inception_4e_pool], axis=3)
#inception5a
inception_5a_3x3 = Conv2D(96, (1, 1),
strides=(1, 1),
name='inception_5a_3x3_conv' + '1')(inception_4e)
inception_5a_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5a_3x3_bn' +
'1')(inception_5a_3x3)
inception_5a_3x3 = Activation('relu')(inception_5a_3x3)
inception_5a_3x3 = ZeroPadding2D(padding=(1, 1))(inception_5a_3x3)
inception_5a_3x3 = Conv2D(384, (3, 3),
strides=(1, 1),
name='inception_5a_3x3_conv' +
'2')(inception_5a_3x3)
inception_5a_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5a_3x3_bn' +
'2')(inception_5a_3x3)
inception_5a_3x3 = Activation('relu')(inception_5a_3x3)
inception_5a_pool = Lambda(lambda x: x**2, name='power2_5a')(inception_4e)
inception_5a_pool = AveragePooling2D(pool_size=(3, 3),
strides=(3, 3))(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: x * 9,
name='mult9_5a')(inception_5a_pool)
inception_5a_pool = Lambda(lambda x: K.sqrt(x),
name='sqrt_5a')(inception_5a_pool)
inception_5a_pool = Conv2D(96, (1, 1),
strides=(1, 1),
name='inception_5a_pool_conv' +
'')(inception_5a_pool)
inception_5a_pool = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5a_pool_bn' +
'')(inception_5a_pool)
inception_5a_pool = Activation('relu')(inception_5a_pool)
inception_5a_pool = ZeroPadding2D(padding=(1, 1))(inception_5a_pool)
inception_5a_1x1 = Conv2D(256, (1, 1),
strides=(1, 1),
name='inception_5a_1x1_conv' + '')(inception_4e)
inception_5a_1x1 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5a_1x1_bn' +
'')(inception_5a_1x1)
inception_5a_1x1 = Activation('relu')(inception_5a_1x1)
inception_5a = concatenate(
[inception_5a_3x3, inception_5a_pool, inception_5a_1x1], axis=3)
#inception_5b
inception_5b_3x3 = Conv2D(96, (1, 1),
strides=(1, 1),
name='inception_5b_3x3_conv' + '1')(inception_5a)
inception_5b_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5b_3x3_bn' +
'1')(inception_5b_3x3)
inception_5b_3x3 = Activation('relu')(inception_5b_3x3)
inception_5b_3x3 = ZeroPadding2D(padding=(1, 1))(inception_5b_3x3)
inception_5b_3x3 = Conv2D(384, (3, 3),
strides=(1, 1),
name='inception_5b_3x3_conv' +
'2')(inception_5b_3x3)
inception_5b_3x3 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5b_3x3_bn' +
'2')(inception_5b_3x3)
inception_5b_3x3 = Activation('relu')(inception_5b_3x3)
inception_5b_pool = MaxPooling2D(pool_size=3, strides=2)(inception_5a)
inception_5b_pool = Conv2D(96, (1, 1),
strides=(1, 1),
name='inception_5b_pool_conv' +
'')(inception_5b_pool)
inception_5b_pool = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5b_pool_bn' +
'')(inception_5b_pool)
inception_5b_pool = Activation('relu')(inception_5b_pool)
inception_5b_pool = ZeroPadding2D(padding=(1, 1))(inception_5b_pool)
inception_5b_1x1 = Conv2D(256, (1, 1),
strides=(1, 1),
name='inception_5b_1x1_conv' + '')(inception_5a)
inception_5b_1x1 = BatchNormalization(axis=3,
epsilon=0.00001,
name='inception_5b_1x1_bn' +
'')(inception_5b_1x1)
inception_5b_1x1 = Activation('relu')(inception_5b_1x1)
inception_5b = concatenate(
[inception_5b_3x3, inception_5b_pool, inception_5b_1x1], axis=3)
av_pool = AveragePooling2D(pool_size=(3, 3), strides=(1, 1))(inception_5b)
reshape_layer = Flatten()(av_pool)
dense_layer = Dense(128, name='dense_layer')(reshape_layer)
norm_layer = Lambda(lambda x: K.l2_normalize(x, axis=1),
name='norm_layer')(dense_layer)
# Final Model
model = Model(inputs=[myInput], outputs=norm_layer)
return model
def inceptionv2(input,
dropout_keep_prob=0.8,
num_classes=1000,
is_training=True,
scope='InceptionV2',
supermd=False):
with tf.name_scope(scope, "InceptionV2", [input]):
conv1_7x7_s2 = Conv2D(64, (7, 7),
strides=(2, 2),
padding='same',
activation='relu',
name='conv1/7x7_s2',
kernel_regularizer=l2(0.0002))(input)
conv1_zero_pad = ZeroPadding2D(padding=(1, 1))(conv1_7x7_s2)
pool1_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool1/3x3_s2')(conv1_zero_pad)
pool1_norm1 = BatchNormalization(axis=3,
scale=False,
name='pool1/norm1')(pool1_3x3_s2)
conv2_3x3_reduce = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='conv2/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool1_norm1)
conv2_3x3 = Conv2D(192, (3, 3),
padding='same',
activation='relu',
name='conv2/3x3',
kernel_regularizer=l2(0.0002))(conv2_3x3_reduce)
conv2_norm2 = BatchNormalization(axis=3,
scale=False,
name='conv2/norm2')(conv2_3x3)
conv2_zero_pad = ZeroPadding2D(padding=(1, 1))(conv2_norm2)
pool2_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool2/3x3_s2')(conv2_zero_pad)
inception_3a_1x1 = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='inception_3a/1x1',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_3a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3 = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_3a/3x3',
kernel_regularizer=l2(0.0002))(inception_3a_3x3_reduce)
inception_3a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_3a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_5x5_a = Conv2D(
96, (3, 3),
padding='same',
activation='relu',
name='inception_3a/5x5_a',
kernel_regularizer=l2(0.0002))(inception_3a_5x5_reduce)
inception_3a_5x5_b = Conv2D(
96, (3, 3),
padding='same',
activation='relu',
name='inception_3a/5x5_b',
kernel_regularizer=l2(0.0002))(inception_3a_5x5_a)
inception_3a_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3a/pool')(pool2_3x3_s2)
inception_3a_pool_proj = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3a_pool)
inception_3a_output = concatenate([
inception_3a_1x1, inception_3a_3x3, inception_3a_5x5_b,
inception_3a_pool_proj
],
axis=3,
name='inception_3a/output')
inception_3b_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/1x1',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3 = Conv2D(
192, (3, 3),
padding='same',
activation='relu',
name='inception_3b/3x3',
kernel_regularizer=l2(0.0002))(inception_3b_3x3_reduce)
inception_3b_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_5x5_a = Conv2D(
96, (3, 3),
padding='same',
activation='relu',
name='inception_3b/5x5_a',
kernel_regularizer=l2(0.0002))(inception_3b_5x5_reduce)
inception_3b_5x5_b = Conv2D(
96, (3, 3),
padding='same',
activation='relu',
name='inception_3b/5x5_b',
kernel_regularizer=l2(0.0002))(inception_3b_5x5_a)
inception_3b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3b/pool')(inception_3a_output)
inception_3b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_3b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3b_pool)
inception_3b_output = concatenate([
inception_3b_1x1, inception_3b_3x3, inception_3b_5x5_b,
inception_3b_pool_proj
],
axis=3,
name='inception_3b/output')
inception_3b_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_3b_output)
pool3_3x3_s2 = MaxPooling2D(
pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool3/3x3_s2')(inception_3b_output_zero_pad)
inception_4a_1x1 = Conv2D(192, (1, 1),
padding='same',
activation='relu',
name='inception_4a/1x1',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_4a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3 = Conv2D(
208, (3, 3),
padding='same',
activation='relu',
name='inception_4a/3x3',
kernel_regularizer=l2(0.0002))(inception_4a_3x3_reduce)
inception_4a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_4a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_5x5_a = Conv2D(
48, (3, 3),
padding='same',
activation='relu',
name='inception_4a/5x5_a',
kernel_regularizer=l2(0.0002))(inception_4a_5x5_reduce)
inception_4a_5x5_b = Conv2D(
48, (3, 3),
padding='same',
activation='relu',
name='inception_4a/5x5_b',
kernel_regularizer=l2(0.0002))(inception_4a_5x5_a)
inception_4a_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4a/pool')(pool3_3x3_s2)
inception_4a_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4a_pool)
inception_4a_output = concatenate([
inception_4a_1x1, inception_4a_3x3, inception_4a_5x5_b,
inception_4a_pool_proj
],
axis=3,
name='inception_4a/output')
loss1_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss1/ave_pool')(inception_4a_output)
loss1_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss1/conv',
kernel_regularizer=l2(0.0002))(loss1_ave_pool)
loss1_flat = Flatten()(loss1_conv)
loss1_fc = Dense(1024,
activation='relu',
name='loss1/fc',
kernel_regularizer=l2(0.0002))(loss1_flat)
loss1_drop_fc = Dropout(dropout_keep_prob)(loss1_fc,
training=is_training)
if supermd:
loss1_classifier_a = Dense(
4, name='loss1/classifiera',
kernel_regularizer=l2(0.0002))(loss1_drop_fc)
loss1_classifier_a, loss1_classifier_a2 = tf.split(
loss1_classifier_a, [1, 3], 1)
loss1_classifier_a2 = Activation('relu')(loss1_classifier_a2)
loss1_classifier_b = Dense(
3, name='loss1/classifierb',
kernel_regularizer=l2(0.0002))(loss1_classifier_a2)
loss1_classifier_b, loss1_classifier_b2 = tf.split(
loss1_classifier_b, [1, 2], 1)
loss1_classifier_b2 = Activation('relu')(loss1_classifier_b2)
loss1_classifier_c = Dense(
2, name='loss1/classifierc',
kernel_regularizer=l2(0.0002))(loss1_classifier_b2)
loss1_classifier = concatenate(
[loss1_classifier_a, loss1_classifier_b, loss1_classifier_c],
axis=-1)
else:
loss1_classifier = Dense(
num_classes,
name='loss1/classifier',
kernel_regularizer=l2(0.0002))(loss1_drop_fc)
inception_4b_1x1 = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4b/1x1',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_reduce = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3 = Conv2D(
224, (3, 3),
padding='same',
activation='relu',
name='inception_4b/3x3',
kernel_regularizer=l2(0.0002))(inception_4b_3x3_reduce)
inception_4b_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_5x5_a = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4b/5x5_a',
kernel_regularizer=l2(0.0002))(inception_4b_5x5_reduce)
inception_4b_5x5_b = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4b/5x5_b',
kernel_regularizer=l2(0.0002))(inception_4b_5x5_a)
inception_4b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4b/pool')(inception_4a_output)
inception_4b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4b_pool)
inception_4b_output = concatenate([
inception_4b_1x1, inception_4b_3x3, inception_4b_5x5_b,
inception_4b_pool_proj
],
axis=3,
name='inception_4b_output')
inception_4c_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/1x1',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3 = Conv2D(
256, (3, 3),
padding='same',
activation='relu',
name='inception_4c/3x3',
kernel_regularizer=l2(0.0002))(inception_4c_3x3_reduce)
inception_4c_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4c/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_5x5_a = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4c/5x5_a',
kernel_regularizer=l2(0.0002))(inception_4c_5x5_reduce)
inception_4c_5x5_b = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4c/5x5_b',
kernel_regularizer=l2(0.0002))(inception_4c_5x5_a)
inception_4c_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4c/pool')(inception_4b_output)
inception_4c_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4c/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4c_pool)
inception_4c_output = concatenate([
inception_4c_1x1, inception_4c_3x3, inception_4c_5x5_b,
inception_4c_pool_proj
],
axis=3,
name='inception_4c/output')
inception_4d_1x1 = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4d/1x1',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_reduce = Conv2D(
144, (1, 1),
padding='same',
activation='relu',
name='inception_4d/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3 = Conv2D(
288, (3, 3),
padding='same',
activation='relu',
name='inception_4d/3x3',
kernel_regularizer=l2(0.0002))(inception_4d_3x3_reduce)
inception_4d_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4d/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_5x5_a = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4d/5x5_a',
kernel_regularizer=l2(0.0002))(inception_4d_5x5_reduce)
inception_4d_5x5_b = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='inception_4d/5x5_b',
kernel_regularizer=l2(0.0002))(inception_4d_5x5_a)
inception_4d_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4d/pool')(inception_4c_output)
inception_4d_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4d/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4d_pool)
inception_4d_output = concatenate([
inception_4d_1x1, inception_4d_3x3, inception_4d_5x5_b,
inception_4d_pool_proj
],
axis=3,
name='inception_4d/output')
loss2_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss2/ave_pool')(inception_4d_output)
loss2_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss2/conv',
kernel_regularizer=l2(0.0002))(loss2_ave_pool)
loss2_flat = Flatten()(loss2_conv)
loss2_fc = Dense(1024,
activation='relu',
name='loss2/fc',
kernel_regularizer=l2(0.0002))(loss2_flat)
loss2_drop_fc = Dropout(dropout_keep_prob)(loss2_fc,
training=is_training)
if supermd:
loss2_classifier_a = Dense(
4, name='loss2/classifiera',
kernel_regularizer=l2(0.0002))(loss2_drop_fc)
loss2_classifier_a, loss2_classifier_a2 = tf.split(
loss2_classifier_a, [1, 3], 1)
loss2_classifier_a2 = Activation('relu')(loss2_classifier_a2)
loss2_classifier_b = Dense(
3, name='loss2/classifierb',
kernel_regularizer=l2(0.0002))(loss2_classifier_a2)
loss2_classifier_b, loss2_classifier_b2 = tf.split(
loss2_classifier_b, [1, 2], 1)
loss2_classifier_b2 = Activation('relu')(loss2_classifier_b2)
loss2_classifier_c = Dense(
2, name='loss2/classifierc',
kernel_regularizer=l2(0.0002))(loss2_classifier_b2)
loss2_classifier = concatenate(
[loss2_classifier_a, loss2_classifier_b, loss2_classifier_c],
axis=-1)
else:
loss2_classifier = Dense(
num_classes,
name='loss2/classifier',
kernel_regularizer=l2(0.0002))(loss2_drop_fc)
inception_4e_1x1 = Conv2D(
256, (1, 1),
padding='same',
activation='relu',
name='inception_4e/1x1',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4e/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3 = Conv2D(
320, (3, 3),
padding='same',
activation='relu',
name='inception_4e/3x3',
kernel_regularizer=l2(0.0002))(inception_4e_3x3_reduce)
inception_4e_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4e/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_5x5_a = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_4e/5x5_a',
kernel_regularizer=l2(0.0002))(inception_4e_5x5_reduce)
inception_4e_5x5_b = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_4e/5x5_b',
kernel_regularizer=l2(0.0002))(inception_4e_5x5_a)
inception_4e_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4e/pool')(inception_4d_output)
inception_4e_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4e/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4e_pool)
inception_4e_output = concatenate([
inception_4e_1x1, inception_4e_3x3, inception_4e_5x5_b,
inception_4e_pool_proj
],
axis=3,
name='inception_4e/output')
inception_4e_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_4e_output)
pool4_3x3_s2 = MaxPooling2D(
pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool4/3x3_s2')(inception_4e_output_zero_pad)
inception_5a_1x1 = Conv2D(256, (1, 1),
padding='same',
activation='relu',
name='inception_5a/1x1',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_5a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3 = Conv2D(
320, (3, 3),
padding='same',
activation='relu',
name='inception_5a/3x3',
kernel_regularizer=l2(0.0002))(inception_5a_3x3_reduce)
inception_5a_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_5a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_5x5_a = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_5a/5x5_a',
kernel_regularizer=l2(0.0002))(inception_5a_5x5_reduce)
inception_5a_5x5_b = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_5a/5x5_b',
kernel_regularizer=l2(0.0002))(inception_5a_5x5_a)
inception_5a_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5a/pool')(pool4_3x3_s2)
inception_5a_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5a_pool)
inception_5a_output = concatenate([
inception_5a_1x1, inception_5a_3x3, inception_5a_5x5_b,
inception_5a_pool_proj
],
axis=3,
name='inception_5a/output')
inception_5b_1x1 = Conv2D(
384, (1, 1),
padding='same',
activation='relu',
name='inception_5b/1x1',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_reduce = Conv2D(
192, (1, 1),
padding='same',
activation='relu',
name='inception_5b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3 = Conv2D(
384, (3, 3),
padding='same',
activation='relu',
name='inception_5b/3x3',
kernel_regularizer=l2(0.0002))(inception_5b_3x3_reduce)
inception_5b_5x5_reduce = Conv2D(
48, (1, 1),
padding='same',
activation='relu',
name='inception_5b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_5x5_a = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_5b/5x5_a',
kernel_regularizer=l2(0.0002))(inception_5b_5x5_reduce)
inception_5b_5x5_b = Conv2D(
128, (3, 3),
padding='same',
activation='relu',
name='inception_5b/5x5_b',
kernel_regularizer=l2(0.0002))(inception_5b_5x5_a)
inception_5b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5b/pool')(inception_5a_output)
inception_5b_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5b_pool)
inception_5b_output = concatenate([
inception_5b_1x1, inception_5b_3x3, inception_5b_5x5_b,
inception_5b_pool_proj
],
axis=3,
name='inception_5b/output')
net = inception_5b_output
# Modified for 299x299
pool5_10x10_s1 = AveragePooling2D(
pool_size=(10, 10), strides=(1, 1),
name='pool5/10x10_s2')(inception_5b_output)
loss3_flat = Flatten()(pool5_10x10_s1)
pool5_drop_10x10_s1 = Dropout(dropout_keep_prob)(loss3_flat,
training=is_training)
if supermd:
loss3_classifier_aw = Dense(4,
name='loss3/classifiera',
kernel_regularizer=l2(0.0002))
loss3_classifier_a = loss3_classifier_aw(pool5_drop_10x10_s1)
loss3_classifier_a, loss3_classifier_a2 = tf.split(
loss3_classifier_a, [1, 3], 1)
loss3_classifier_a2 = Activation('relu')(loss3_classifier_a2)
loss3_classifier_bw = Dense(3,
name='loss3/classifierb',
kernel_regularizer=l2(0.0002))
loss3_classifier_b = loss3_classifier_bw(loss3_classifier_a2)
loss3_classifier_b, loss3_classifier_b2 = tf.split(
loss3_classifier_b, [1, 2], 1)
loss3_classifier_b2 = Activation('relu')(loss3_classifier_b2)
loss3_classifier_cw = Dense(2,
name='loss3/classifierc',
kernel_regularizer=l2(0.0002))
loss3_classifier_c = loss3_classifier_cw(loss3_classifier_b2)
loss3_classifier = concatenate(
[loss3_classifier_a, loss3_classifier_b, loss3_classifier_c],
axis=-1)
w_variables = loss3_classifier_aw.get_weights()
else:
loss3_classifier_w = Dense(num_classes,
name='loss3/classifier',
kernel_regularizer=l2(0.0002))
loss3_classifier = loss3_classifier_w(pool5_drop_10x10_s1)
w_variables = loss3_classifier_w.get_weights()
logits = tf.cond(
tf.equal(is_training, tf.constant(True)), lambda: tf.add(
loss3_classifier,
tf.scalar_mul(tf.constant(0.3),
tf.add(loss1_classifier, loss2_classifier))),
lambda: loss3_classifier)
return logits, net, tf.convert_to_tensor(w_variables[0])
