def conv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):
'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps = 1.1e-5
conv_name_base = 'conv' + str(stage) + '_' + str(branch)
relu_name_base = 'relu' + str(stage) + '_' + str(branch)
# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter * 4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel, 1, 1, name=conv_name_base+'_x1', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1, 1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter, 3, 3, name=conv_name_base+'_x2', bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def transition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):
''' 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, name=conv_name_base+'_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
x = Activation('relu', name=relu_name_base)(x)
x = Convolution2D(int(nb_filter * compression), 1, 1, name=conv_name_base, bias=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 DenseNet121(nb_dense_block=4,
growth_rate=32,
nb_filter=64,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
classes=1000,
weights_path=None):
'''Instantiate the DenseNet 121 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps = 1.1e-5
# compute compression factor
compression = 1.0 - reduction
# Handle Dimension Ordering for different backends
global concat_axis
if K.image_dim_ordering() == 'tf':
concat_axis = 3
img_input = Input(shape=(224, 224, 3), name='data')
else:
concat_axis = 1
img_input = Input(shape=(3, 224, 224), name='data')
# From architecture for ImageNet (Table 1 in the paper)
nb_filter = 64
nb_layers = [6, 12, 24, 16] # For DenseNet-121
# Initial convolution
x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
x = Convolution2D(nb_filter,
7,
7,
subsample=(2, 2),
name='conv1',
bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=concat_axis, name='conv1_bn')(x)
x = Scale(axis=concat_axis, name='conv1_scale')(x)
x = Activation('relu', name='relu1')(x)
x = ZeroPadding2D((1, 1), name='pool1_zeropadding')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(x)
# Add dense blocks
for block_idx in range(nb_dense_block - 1):
stage = block_idx + 2
x, nb_filter = dense_block(x,
stage,
nb_layers[block_idx],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
# Add transition_block
x = transition_block(x,
stage,
nb_filter,
compression=compression,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
final_stage = stage + 1
x, nb_filter = dense_block(x,
final_stage,
nb_layers[-1],
nb_filter,
growth_rate,
dropout_rate=dropout_rate,
weight_decay=weight_decay)
x = BatchNormalization(epsilon=eps,
axis=concat_axis,
name='conv' + str(final_stage) + '_blk_bn')(x)
x = Scale(axis=concat_axis,
name='conv' + str(final_stage) + '_blk_scale')(x)
x = Activation('relu', name='relu' + str(final_stage) + '_blk')(x)
x = GlobalAveragePooling2D(name='pool' + str(final_stage))(x)
print(x.shape)
out = Dense(classes, name='fc6')(x)
out = Activation('softmax', name='prob')(out)
model = Model(img_input, out, name='densenet')
if weights_path is not None:
model.load_weights(weights_path)
model2 = Model(img_input, x)
return model2