def prediction(x,i,num_priors,min_s,max_s,aspect,num_classes,img_size):
a=Conv2D(num_priors*4,(3,3),padding='same',name=str(i)+'_mbox_loc')(x)
mbox_loc_flat=Flatten(name=str(i)+'_mbox_loc_flat')(a)
b=Conv2D(num_priors*num_classes,(3,3),padding='same',name=str(i)+'_mbox_conf')(x)
mbox_conf_flat=Flatten(name=str(i)+'_mbox_conf_flat')(b)
mbox_priorbox=PriorBox(img_size,min_size=min_s,max_size=max_s,aspect_ratios=aspect,variances=[0.1,0.1,0.2,0.2],name=str(i)+'_mbox_priorbox')(x)
return mbox_loc_flat,mbox_conf_flat,mbox_priorbox
def SSD300(input_shape, num_classes=21,weights=None):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
if weights==None:
vgg_weights = 'imagenet'
else:
vgg_weights = None
### VGG layers
vgg = VGG16(input_tensor=input_tensor,weights=vgg_weights,
input_shape=input_shape, include_top=False)
for layer in vgg.layers:
layer.trainable = False
#block 1
net['conv1_1'] = vgg.layers[1](net['input'])
net['conv1_2'] = vgg.layers[2](net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool1')(net['conv1_2'])
#block 2
net['conv2_1'] = vgg.layers[4](net['pool1'])
net['conv2_2'] = vgg.layers[5](net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool2')(net['conv2_2'])
# block 3
net['conv3_1'] = vgg.layers[7](net['pool2'])
net['conv3_2'] = vgg.layers[8](net['conv3_1'])
net['conv3_3'] = vgg.layers[9](net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool3')(net['conv3_3'])
# block 4
net['conv4_1'] = vgg.layers[11](net['pool3'])
net['conv4_2'] = vgg.layers[12](net['conv4_1'])
net['conv4_3'] = vgg.layers[13](net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool4')(net['conv4_3'])
# block 5
net['conv5_1'] = vgg.layers[15](net['pool4'])
net['conv5_2'] = vgg.layers[16](net['conv5_1'])
net['conv5_3'] = vgg.layers[17](net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3), strides=(1, 1), border_mode='same',
name='pool5')(net['conv5_3'])
### Beginning of SSD layers
# FC6
net['fc6'] = AtrousConvolution2D(1024, 3, 3, atrous_rate=(6, 6),
activation='relu', border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024, 1, 1, activation='relu',
border_mode='same', name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256, 1, 1, activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
### Prediction layers at different depths
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size, 30.0, aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4, 3, 3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes, 3, 3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size, 60.0, max_size=114.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size, 114.0, max_size=168.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size, 168.0, max_size=222.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size, 222.0, max_size=276.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size, 276.0, max_size=330.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = merge([net['conv4_3_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']],
mode='concat', concat_axis=1, name='mbox_loc')
net['mbox_conf'] = merge([net['conv4_3_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']],
mode='concat', concat_axis=1, name='mbox_conf')
net['mbox_priorbox'] = merge([net['conv4_3_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'],
net['pool6_mbox_priorbox']],
mode='concat', concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge([net['mbox_loc'],
net['mbox_conf'],
net['mbox_priorbox']],
mode='concat', concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
if weights:
model.load_weights(weights)
return model
def RGBD_SSD300(input_shape, depth_input_shape, num_classes=21):
vgg16 = VGG16(weights='imagenet', include_top=False)
weights = vgg16.get_weights()
input_layer = Input(shape=input_shape)
depth_input_layer = Input(shape=depth_input_shape)
conv1_1 = Conv2D(64, (3, 3),
name='rgb_conv1_1',
padding='same',
activation='relu',
weights=[weights[0], weights[1]])(input_layer)
depth_conv1_1 = Conv2D(
64,
(3, 3),
name='depth_conv1_1',
padding='same',
activation='relu',
# weights=[weights[0], weights[1]]
)(depth_input_layer)
conv1_2 = Conv2D(64, (3, 3),
name='conv1_2',
padding='same',
activation='relu',
weights=[weights[2], weights[3]])(conv1_1)
depth_conv1_2 = Conv2D(64, (3, 3),
name='depth_conv1_2',
padding='same',
activation='relu',
weights=[weights[2], weights[3]])(depth_conv1_1)
pool1 = MaxPooling2D(
name='pool1',
pool_size=(2, 2),
strides=(2, 2),
padding='same',
)(conv1_2)
depth_pool1 = MaxPooling2D(
name='depth_pool1',
pool_size=(2, 2),
strides=(2, 2),
padding='same',
)(depth_conv1_2)
# Block 2
conv2_1 = Conv2D(128, (3, 3),
name='conv2_1',
padding='same',
activation='relu',
weights=[weights[4], weights[5]])(pool1)
depth_conv2_1 = Conv2D(128, (3, 3),
name='depth_conv2_1',
padding='same',
activation='relu',
weights=[weights[4], weights[5]])(depth_pool1)
conv2_2 = Conv2D(128, (3, 3),
name='conv2_2',
padding='same',
activation='relu',
weights=[weights[6], weights[7]])(conv2_1)
depth_conv2_2 = Conv2D(128, (3, 3),
name='depth_conv2_2',
padding='same',
activation='relu',
weights=[weights[6], weights[7]])(depth_conv2_1)
pool2 = MaxPooling2D(name='pool2',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv2_2)
depth_pool2 = MaxPooling2D(name='depth_pool2',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(depth_conv2_2)
# Block 3
conv3_1 = Conv2D(256, (3, 3),
name='conv3_1',
padding='same',
activation='relu',
weights=[weights[8], weights[9]])(pool2)
depth_conv3_1 = Conv2D(256, (3, 3),
name='depth_conv3_1',
padding='same',
activation='relu',
weights=[weights[8], weights[9]])(depth_pool2)
conv3_2 = Conv2D(256, (3, 3),
name='conv3_2',
padding='same',
activation='relu',
weights=[weights[10], weights[11]])(conv3_1)
depth_conv3_2 = Conv2D(256, (3, 3),
name='depth_conv3_2',
padding='same',
activation='relu',
weights=[weights[10], weights[11]])(depth_conv3_1)
conv3_3 = Conv2D(256, (3, 3),
name='conv3_3',
padding='same',
activation='relu',
weights=[weights[12], weights[13]])(conv3_2)
depth_conv3_3 = Conv2D(256, (3, 3),
name='depth_conv3_3',
padding='same',
activation='relu',
weights=[weights[12], weights[13]])(depth_conv3_2)
pool3 = MaxPooling2D(name='pool3',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv3_3)
depth_pool3 = MaxPooling2D(name='depth_pool3',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(depth_conv3_3)
# Block 4
conv4_1 = Conv2D(512, (3, 3),
name='conv4_1',
padding='same',
activation='relu',
weights=[weights[14], weights[15]])(pool3)
depth_conv4_1 = Conv2D(512, (3, 3),
name='depth_conv4_1',
padding='same',
activation='relu',
weights=[weights[14], weights[15]])(depth_pool3)
conv4_2 = Conv2D(512, (3, 3),
name='conv4_2',
padding='same',
activation='relu',
weights=[weights[16], weights[17]])(conv4_1)
depth_conv4_2 = Conv2D(512, (3, 3),
name='depth_conv4_2',
padding='same',
activation='relu',
weights=[weights[16], weights[17]])(depth_conv4_1)
conv4_3 = Conv2D(512, (3, 3),
name='conv4_3',
padding='same',
activation='relu',
weights=[weights[18], weights[19]])(conv4_2)
depth_conv4_3 = Conv2D(512, (3, 3),
name='depth_conv4_3',
padding='same',
activation='relu',
weights=[weights[18], weights[19]])(depth_conv4_2)
pool4 = MaxPooling2D(name='pool4',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv4_3)
depth_pool4 = MaxPooling2D(name='depth_pool4',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(depth_conv4_3)
# Block 5
conv5_1 = Conv2D(512, (3, 3),
name='conv5_1',
padding='same',
activation='relu',
weights=[weights[20], weights[21]])(pool4)
depth_conv5_1 = Conv2D(512, (3, 3),
name='depth_conv5_1',
padding='same',
activation='relu',
weights=[weights[20], weights[21]])(depth_pool4)
conv5_2 = Conv2D(512, (3, 3),
name='conv5_2',
padding='same',
activation='relu',
weights=[weights[22], weights[23]])(conv5_1)
depth_conv5_2 = Conv2D(512, (3, 3),
name='depth_conv5_2',
padding='same',
activation='relu',
weights=[weights[22], weights[23]])(depth_conv5_1)
conv5_3 = Conv2D(512, (3, 3),
name='conv5_3',
padding='same',
activation='relu',
weights=[weights[24], weights[25]])(conv5_2)
depth_conv5_3 = Conv2D(512, (3, 3),
name='depth_conv5_3',
padding='same',
activation='relu',
weights=[weights[24], weights[25]])(depth_conv5_2)
pool5 = MaxPooling2D(name='pool5',
pool_size=(3, 3),
strides=(1, 1),
padding='same')(conv5_3)
depth_pool5 = MaxPooling2D(name='depth_pool5',
pool_size=(3, 3),
strides=(1, 1),
padding='same')(depth_conv5_3)
concat_pool5 = concatenate([pool5, depth_pool5],
axis=1,
name='concat_pool5')
# FC6
fc6 = Conv2D(1024, (3, 3),
name='fc6',
dilation_rate=(6, 6),
padding='same',
activation='relu')(pool5)
fc6 = Dropout(0.5, name='drop6')(fc6)
# FC7
fc7 = Conv2D(1024, (1, 1), name='fc7', padding='same',
activation='relu')(fc6)
fc7 = Dropout(0.5, name='drop7')(fc7)
# Block 6
conv6_1 = Conv2D(256, (1, 1),
name='conv6_1',
padding='same',
activation='relu')(fc7)
conv6_2 = Conv2D(512, (3, 3),
name='conv6_2',
strides=(2, 2),
padding='same',
activation='relu')(conv6_1)
# Block 7
conv7_1 = Conv2D(128, (1, 1),
name='conv7_1',
padding='same',
activation='relu')(conv6_2)
conv7_1z = ZeroPadding2D(name='conv7_1z')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
name='conv7_2',
padding='valid',
strides=(2, 2),
activation='relu')(conv7_1z)
# Block 8
conv8_1 = Conv2D(128, (1, 1),
name='conv8_1',
padding='same',
activation='relu')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
name='conv8_2',
padding='same',
strides=(2, 2),
activation='relu')(conv8_1)
# Last Pool
pool6 = GlobalAveragePooling2D(name='pool6')(conv8_2)
# Prediction from conv4_3
num_priors = 3
img_size = (input_shape[1], input_shape[0])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
concat_conv4_3 = concatenate([conv4_3, depth_conv4_3], axis=3)
conv4_3_norm = Normalize(20, name='conv4_3_norm')(concat_conv4_3)
conv4_3_norm_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='conv4_3_norm_mbox_loc',
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_loc_flat = Flatten(
name='conv4_3_norm_mbox_loc_flat')(conv4_3_norm_mbox_loc)
conv4_3_norm_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
name=name,
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_conf_flat = Flatten(
name='conv4_3_norm_mbox_conf_flat')(conv4_3_norm_mbox_conf)
conv4_3_norm_mbox_priorbox = PriorBox(img_size,
30.0,
name='conv4_3_norm_mbox_priorbox',
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2,
0.2])(conv4_3_norm)
# Prediction from fc7
num_priors = 6
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
fc7_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(fc7)
fc7_mbox_conf_flat = Flatten(name='fc7_mbox_conf_flat')(fc7_mbox_conf)
fc7_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='fc7_mbox_loc',
padding='same')(fc7)
fc7_mbox_loc_flat = Flatten(name='fc7_mbox_loc_flat')(fc7_mbox_loc)
fc7_mbox_priorbox = PriorBox(img_size,
60.0,
name='fc7_mbox_priorbox',
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2])(fc7)
# Prediction from conv6_2
num_priors = 6
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv6_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv6_2)
conv6_2_mbox_conf_flat = Flatten(
name='conv6_2_mbox_conf_flat')(conv6_2_mbox_conf)
conv6_2_mbox_loc = Conv2D(num_priors * 4, (
3,
3,
),
name='conv6_2_mbox_loc',
padding='same')(conv6_2)
conv6_2_mbox_loc_flat = Flatten(
name='conv6_2_mbox_loc_flat')(conv6_2_mbox_loc)
conv6_2_mbox_priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(conv6_2)
# Prediction from conv7_2
num_priors = 6
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv7_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv7_2)
conv7_2_mbox_conf_flat = Flatten(
name='conv7_2_mbox_conf_flat')(conv7_2_mbox_conf)
conv7_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(conv7_2)
conv7_2_mbox_loc_flat = Flatten(
name='conv7_2_mbox_loc_flat')(conv7_2_mbox_loc)
conv7_2_mbox_priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(conv7_2)
# Prediction from conv8_2
num_priors = 6
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv8_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv8_2)
conv8_2_mbox_conf_flat = Flatten(
name='conv8_2_mbox_conf_flat')(conv8_2_mbox_conf)
conv8_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(conv8_2)
conv8_2_mbox_loc_flat = Flatten(
name='conv8_2_mbox_loc_flat')(conv8_2_mbox_loc)
conv8_2_mbox_priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(conv8_2)
# Prediction from pool6
num_priors = 6
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
pool6_mbox_loc_flat = Dense(num_priors * 4,
name='pool6_mbox_loc_flat')(pool6)
pool6_mbox_conf_flat = Dense(num_priors * num_classes, name=name)(pool6)
pool6_reshaped = Reshape(target_shape, name='pool6_reshaped')(pool6)
pool6_mbox_priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(pool6_reshaped)
# Gather all predictions
mbox_loc = concatenate([
conv4_3_norm_mbox_loc_flat, fc7_mbox_loc_flat, conv6_2_mbox_loc_flat,
conv7_2_mbox_loc_flat, conv8_2_mbox_loc_flat, pool6_mbox_loc_flat
],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([
conv4_3_norm_mbox_conf_flat, fc7_mbox_conf_flat,
conv6_2_mbox_conf_flat, conv7_2_mbox_conf_flat, conv8_2_mbox_conf_flat,
pool6_mbox_conf_flat
],
axis=1,
name='mbox_conf')
mbox_priorbox = concatenate([
conv4_3_norm_mbox_priorbox, fc7_mbox_priorbox, conv6_2_mbox_priorbox,
conv7_2_mbox_priorbox, conv8_2_mbox_priorbox, pool6_mbox_priorbox
],
axis=1,
name='mbox_priorbox')
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
mbox_loc = Reshape((num_boxes, 4), name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax', name='mbox_conf_final')(mbox_conf)
predictions = concatenate([mbox_loc, mbox_conf, mbox_priorbox],
axis=2,
name='predictions')
model = Model(inputs=[input_layer, depth_input_layer], outputs=predictions)
return model
def __init__(self, input_shape, num_classes=21):
super(SSD300, self).__init__()
self.input_shape = input_shape
self.num_classes = num_classes
img_size = (self.input_shape[1], self.input_shape[0])
# vgg16
self.block1_conv_3x3x64 = ConvLayers2D(layers=2,
filters=64,
kernel_size=3,
pool=True,
name="block1_conv_3x3x64")
self.block2_conv_3x3x128 = ConvLayers2D(layers=2,
filters=128,
kernel_size=3,
pool=True,
name="block2_conv_3x3x128")
self.block3_conv_3x3x256 = ConvLayers2D(layers=3,
filters=256,
kernel_size=3,
pool=True,
name="block3_conv_3x3x256")
self.block4_conv_3x3x512 = ConvLayers2D(layers=3,
filters=512,
kernel_size=3,
pool=True,
name="block4_conv_3x3x512")
self.block5_conv_3x3x512 = ConvLayers2D(layers=3,
filters=512,
kernel_size=3,
pool=True,
pool_size=(3, 3),
pool_strides=(1, 1),
name="block5_conv_3x3x512")
self.block6_conv_3x3x1024 = Conv2D(1024, (3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
name='block6_conv_3x3x1024')
self.block6_conv_1x1x1024 = Conv2D(1024, (1, 1),
activation='relu',
padding='same',
name='block6_conv_1x1x1024')
self.block7_conv_1x1x256 = Conv2D(256, (1, 1),
activation='relu',
padding='same',
name='block7_conv_1x1x256')
self.block7_conv_3x3x512 = Conv2D(512, (3, 3),
subsample=(2, 2),
activation='relu',
padding='same',
name='block7_conv_3x3x512')
self.block8_conv_1x1x128 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='block8_conv_1x1x128')
self.block8_conv_3x3x256 = Conv2D(256, (3, 3),
subsample=(2, 2),
activation='relu',
padding='valid',
name='block8_conv_3x3x256')
self.block9_conv_1x1x128 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='block9_conv_1x1x128')
self.block9_conv_3x3x256 = Conv2D(256, (3, 3),
subsample=(2, 2),
activation='relu',
padding='same',
name='block9_conv_3x3x256')
self.block10_conv_1x1x128 = Conv2D(128,
1,
1,
activation='relu',
padding='same',
name='block10_conv_1x1x128')
self.block10_conv_3x3x256 = Conv2D(256, (3, 3),
subsample=(2, 2),
activation='relu',
padding='same',
name='block10_conv_3x3x256')
self.flatten = Flatten()
num_priors = 3
self.block4_norm_mbox_loc = Conv2D(num_priors * 4,
3,
3,
padding='same',
name='block4_norm_mbox_loc')
self.block4_norm_mbox_conf = Conv2D(num_priors * self.num_classes,
3,
3,
padding='same',
name='block4_norm_mbox_conf')
self.block4_norm_mbox_priorbox = PriorBox(
img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='block4_norm_mbox_priorbox')
self.block4_norm = Normalize(20, name='block4_norm')
num_priors = 6
self.block6_mbox_loc = Conv2D(num_priors * 4,
3,
3,
padding='same',
name='block6_mbox_loc')
self.block6_mbox_conf = Conv2D(num_priors * num_classes,
3,
3,
padding='same',
name='block6_mbox_conf')
self.block6_mbox_priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='block6_mbox_priorbox')
self.block7_mbox_loc = Conv2D(num_priors * 4,
3,
3,
padding='same',
name='block7_mbox_loc')
self.block7_mbox_conf = Conv2D(num_priors * num_classes,
3,
3,
padding='same',
name='block7_mbox_conf')
self.block7_mbox_priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='block7_mbox_priorbox')
self.block8_mbox_loc = Conv2D(num_priors * 4,
3,
3,
padding='same',
name='block8_mbox_loc')
self.block8_mbox_conf = Conv2D(num_priors * num_classes,
3,
3,
padding='same',
name='block8_mbox_conf')
self.block8_mbox_priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='block8_mbox_priorbox')
self.block9_mbox_loc = Conv2D(num_priors * 4,
3,
3,
padding='same',
name='block9_mbox_loc')
self.block9_mbox_conf = Conv2D(num_priors * num_classes,
3,
3,
padding='same',
name='block9_mbox_conf')
self.block9_mbox_priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='block9_mbox_priorbox')
self.block10_mbox_loc_flat = Dense(num_priors * 4,
name='block10_mbox_loc_flat')
self.block10_mbox_conf_flat = Dense(num_priors * num_classes,
name='block10_mbox_conf_flat')
self.block10_reshape = Reshape((1, 1, 256), name='block10_reshape')
self.block10_mbox_priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='block10_mbox_priorbox')
self.concat_conf = Concatenate(axis=1, name='mbox_conf')
self.concat_loc = Concatenate(axis=1, name='mbox_loc')
self.concat_priorbox = Concatenate(axis=1, name='mbox_priorbox')
self.concat_predictions = Concatenate(axis=2, name='mbox_predictions')
self.reshape_loc = Reshape((4, 4), name='mbox_loc_final')
self.reshape_conf = Reshape((4, self.num_classes),
name='mbox_conf_logits')
self.activate_softmax = Activation('softmax', name='mbox_conf_softmax')
def SSD300(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1 卷积层块
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
# 二维卷积层对二维输入进行滑动窗卷积
# keras.layers.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None,
# dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform',
# bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None,
# kernel_constraint=None, bias_constraint=None)
net['conv1_1'] = Convolution2D(
64,
3,
3, # 64个过滤器；kernel_size:3，卷积窗口大小；strides:步长；
activation='relu', # 激活函数：ReLU
border_mode='same', # 过滤模式：same/valid
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
# 对空间数据的最大池化
# keras.layers.MaxPooling2D(pool_size=(2, 2), strides=None, padding='valid', data_format=None)
# strides 默认为 None，为 None 时大小等于
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool1')(net['conv1_2'])
# Block 2 卷积层块
net['conv2_1'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool2')(net['conv2_2'])
# Block 3 卷积层块
net['conv3_1'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool3')(net['conv3_3'])
# Block 4 卷积层块
net['conv4_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool4')(net['conv4_3'])
# Block 5 卷积层块
net['conv5_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
border_mode='same',
name='pool5')(net['conv5_3'])
# FC6 该层对二维输入进行Atrous卷积，也即膨胀卷积或带孔洞的卷积。
net['fc6'] = AtrousConvolution2D(1024,
3,
3,
atrous_rate=(6, 6),
activation='relu',
border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024,
1,
1,
activation='relu',
border_mode='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
# keras.layers.BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001, center=True, scale=True,
# beta_initializer='zeros', gamma_initializer='ones', moving_mean_initializer='zeros', moving_variance_initializer='ones',
# beta_regularizer=None, gamma_regularizer=None, beta_constraint=None, gamma_constraint=None)
# axis: 整数，需要标准化的轴 （通常是特征轴）
# 批量标准化层 (Ioffe and Szegedy, 2014)。在每一个批次的数据中标准化前一层的激活项， 即，应用一个维持激活项平均值接近 0，标准差接近 1 的转换。
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = merge([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
mode='concat',
concat_axis=1,
name='mbox_loc')
net['mbox_conf'] = merge([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
mode='concat',
concat_axis=1,
name='mbox_conf')
net['mbox_priorbox'] = merge([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
mode='concat',
concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
mode='concat',
concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
return model
def SSD(input_shape, num_classes):
"""SSD512 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (512, 512, 3) or (3, 512, 512)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
# Block 1
input_shape = (input_shape[1], input_shape[0], 3)
input = Input(input_shape)
resnet50 = ResNet50(input_shape=input_shape,include_top=False, weights='imagenet')
FeatureExtractor = Model(inputs=resnet50.input, outputs=resnet50.get_layer('add_7').output)
pool3 = FeatureExtractor(input)
conv4_0 = Conv2DTranspose(512, (2, 2), name='conv4_0', activation='relu', border_mode='valid')(pool3) #for VGG16,19,Resnet50
# Block 4
conv4_1 = Conv2D(512, (3, 3),activation='relu',padding='same',name='conv4_1')(conv4_0)
conv4_2 = Conv2D(512, (3, 3),activation='relu',padding='same',name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),activation='relu',padding='same',name='conv4_3')(conv4_2)
pool4 = MaxPooling2D((2, 2), strides=(2, 2), padding='same',name='pool4')(conv4_3)
# Block 5
conv5_1 = Conv2D(512, (3, 3),
name='conv5_1',
padding='same',
activation='relu')(pool4)
conv5_2 = Conv2D(512, (3, 3),
name='conv5_2',
padding='same',
activation='relu')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
name='conv5_3',
padding='same',
activation='relu')(conv5_2)
pool5 = MaxPooling2D(name='pool5',
pool_size=(3, 3),
strides=(1, 1),
padding='same')(conv5_3)
# FC6
fc6 = Conv2D(1024, (3, 3),
name='fc6',
dilation_rate=(6, 6),
padding='same',
activation='relu'
)(pool5) #5
# x = Dropout(0.5, name='drop6')(x)
# FC7
fc7 = Conv2D(1024, (1, 1),
name='fc7',
padding='same',
activation='relu'
)(fc6)
# x = Dropout(0.5, name='drop7')(x)
# Block 6
conv6_1 = Conv2D(256, (1, 1),
name='conv6_1',
padding='same',
activation='relu')(fc7)
conv6_2 = Conv2D(512, (3, 3),
name='conv6_2',
strides=(2, 2),
padding='same',
activation='relu')(conv6_1)
# Block 7
conv7_1 = Conv2D(128, (1, 1),
name='conv7_1',
padding='same',
activation='relu')(conv6_2)
conv7_1z = ZeroPadding2D(name='conv7_1z')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
name='conv7_2',
padding='valid',
strides=(2, 2),
activation='relu')(conv7_1z)
# Block 8
conv8_1 = Conv2D(128, (1, 1),
name='conv8_1',
padding='same',
activation='relu')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
name='conv8_2',
padding='same',
strides=(2, 2),
activation='relu')(conv8_1)
# Last Pool
pool6 = GlobalAveragePooling2D(name='pool6')(conv8_2) #8_2
# Prediction from conv4_3
num_priors = 3
img_size = (input_shape[1], input_shape[0])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv4_3_norm = Normalize(20, name='conv4_3_norm')(conv4_3) #4_3
conv4_3_norm_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='conv4_3_norm_mbox_loc',
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_loc_flat = Flatten(name='conv4_3_norm_mbox_loc_flat')(conv4_3_norm_mbox_loc)
conv4_3_norm_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
name=name,
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_conf_flat = Flatten(name='conv4_3_norm_mbox_conf_flat')(conv4_3_norm_mbox_conf)
conv4_3_norm_mbox_priorbox = PriorBox(img_size, 30.0,
name='conv4_3_norm_mbox_priorbox',
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2])(conv4_3_norm)
# Prediction from fc7
num_priors = 6
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
fc7_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(fc7)
fc7_mbox_conf_flat = Flatten(name='fc7_mbox_conf_flat')(fc7_mbox_conf)
fc7_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='fc7_mbox_loc',
padding='same')(fc7)
fc7_mbox_loc_flat = Flatten(name='fc7_mbox_loc_flat')(fc7_mbox_loc)
fc7_mbox_priorbox = PriorBox(img_size, 60.0,
name='fc7_mbox_priorbox',
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2]
)(fc7)
# Prediction from conv6_2
num_priors = 6
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv6_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv6_2)
conv6_2_mbox_conf_flat = Flatten(name='conv6_2_mbox_conf_flat')(conv6_2_mbox_conf)
conv6_2_mbox_loc = Conv2D(num_priors * 4, (3, 3,),
name='conv6_2_mbox_loc',
padding='same')(conv6_2)
conv6_2_mbox_loc_flat = Flatten(name='conv6_2_mbox_loc_flat')(conv6_2_mbox_loc)
conv6_2_mbox_priorbox = PriorBox(img_size, 114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(conv6_2)
# Prediction from conv7_2
num_priors = 6
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv7_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv7_2)
conv7_2_mbox_conf_flat = Flatten(name='conv7_2_mbox_conf_flat')(conv7_2_mbox_conf)
conv7_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(conv7_2)
conv7_2_mbox_loc_flat = Flatten(name='conv7_2_mbox_loc_flat')(conv7_2_mbox_loc)
conv7_2_mbox_priorbox = PriorBox(img_size, 168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(conv7_2)
# Prediction from conv8_2
num_priors = 6
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv8_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv8_2)
conv8_2_mbox_conf_flat = Flatten(name='conv8_2_mbox_conf_flat')(conv8_2_mbox_conf)
conv8_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(conv8_2)
conv8_2_mbox_loc_flat = Flatten(name='conv8_2_mbox_loc_flat')(conv8_2_mbox_loc)
conv8_2_mbox_priorbox = PriorBox(img_size, 222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(conv8_2)
# Prediction from pool6
num_priors = 6
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
pool6_mbox_loc_flat = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(pool6)
pool6_mbox_conf_flat = Dense(num_priors * num_classes, name=name)(pool6)
pool6_reshaped = Reshape(target_shape,
name='pool6_reshaped')(pool6)
pool6_mbox_priorbox = PriorBox(img_size, 276.0, max_size=330.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(pool6_reshaped)
# Gather all predictions
mbox_loc = concatenate([conv4_3_norm_mbox_loc_flat,
fc7_mbox_loc_flat,
conv6_2_mbox_loc_flat,
conv7_2_mbox_loc_flat,
conv8_2_mbox_loc_flat,
pool6_mbox_loc_flat],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([conv4_3_norm_mbox_conf_flat,
fc7_mbox_conf_flat,
conv6_2_mbox_conf_flat,
conv7_2_mbox_conf_flat,
conv8_2_mbox_conf_flat,
pool6_mbox_conf_flat],
axis=1,
name='mbox_conf')
mbox_priorbox = concatenate([conv4_3_norm_mbox_priorbox,
fc7_mbox_priorbox,
conv6_2_mbox_priorbox,
conv7_2_mbox_priorbox,
conv8_2_mbox_priorbox,
pool6_mbox_priorbox],
axis=1,
name='mbox_priorbox')
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
mbox_loc = Reshape((num_boxes, 4),
name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax',
name='mbox_conf_final')(mbox_conf)
predictions = concatenate([mbox_loc,
mbox_conf,
mbox_priorbox],
axis=2,
name='predictions')
model = Model(input, outputs=predictions)
return model
def SSD_300(
input_shape,
num_classes=17 + 1,
min_scale=None,
max_scale=None,
aspect_ratios_per_layer=[[2.0], [2.0, 3.0], [2.0, 3.0], [2.0, 3.0],
[2.0, 3.0], [2.0, 3.0]],
variances=[0.1, 0.1, 0.2, 0.2],
scales=[30, 60, 114, 168, 222, 276, 330],
# scales = [100, 168, 222, 276, 330],
clip_boxes=True):
'''
Arguments:
input_shape (tuple): The height and width and channel of the input images.
min_scale (float): A float in [0, 1], the scaling factor for the size of the generated anchor boxes
as a fraction of the shorter side of the input image.
max_scale (float): A float in [0, 1], the next larger scaling factor. Only relevant if
`self.two_boxes_for_ar1 == True`.
aspect_ratios_per_layer (list, optional): The list of aspect ratios for which default boxes are to be
generated for this layer.
clip_boxes (bool, optional): If `True`, clips the anchor box coordinates to stay within image boundaries.
variances (list, optional): A list of 4 floats >0. The anchor box offset for each coordinate will be divided by
its respective variance value.
'''
n_predictor_layers = 6 # The number of predictor conv layers in the network is 6 for the original SSD300.
if aspect_ratios_per_layer:
if len(aspect_ratios_per_layer) != n_predictor_layers:
raise ValueError(
"It must be either aspect_ratios_per_layer is None or len(aspect_ratios_per_layer) == {}, but len(aspect_ratios_per_layer) == {}."
.format(n_predictor_layers, len(aspect_ratios_per_layer)))
if scales:
if len(scales) != n_predictor_layers + 1:
raise ValueError(
"It must be either scales is None or len(scales) == {}, but len(scales) == {}."
.format(n_predictor_layers + 1, len(scales)))
else: # If no explicit list of scaling factors was passed, compute the list of scaling factors from `min_scale` and `max_scale`
scales = np.linspace(min_scale, max_scale, n_predictor_layers + 1)
net = {}
img_height, img_width, img_channels = input_shape[0], input_shape[
1], input_shape[2]
image_size = (input_shape[1], input_shape[0])
# Block 1
input_tensor = Input(shape=(img_height, img_width, img_channels))
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(32,
kernel_size=3,
activation='relu',
padding='same')(net['input'])
net['conv1_2'] = Convolution2D(64,
kernel_size=3,
strides=2,
activation='relu',
padding='valid',
name='conv1_2')(net['conv1_1'])
# Block 2
net['res2_1'] = Residual_Block(32, net['conv1_2'], name='res2_1')
net['conv3_1'] = Convolution2D(128,
kernel_size=3,
activation='relu',
padding='valid',
strides=2,
name='conv3_1')(net['res2_1'])
# Block 3
net['res4_1'] = Residual_Block(64, net['conv3_1'], name='res4_1')
net['res4_2'] = Residual_Block(64, net['res4_1'], name='res4_2')
net['conv4_3'] = Convolution2D(256,
kernel_size=3,
activation='relu',
padding='valid',
strides=2,
name='conv4_3')(net['res4_2'])
# Block 4
net['res5_1'] = Residual_Block(128, net['conv4_3'], name='res5_1')
net['res5_2'] = Residual_Block(128, net['res5_1'], name='res5_2')
net['res5_3'] = Residual_Block(128, net['res5_2'], name='res5_3')
net['res5_4'] = Residual_Block(128, net['res5_3'], name='res5_4')
net['res5_5'] = Residual_Block(128, net['res5_4'], name='res5_5')
net['res5_6'] = Residual_Block(128, net['res5_5'], name='res5_6')
net['res5_7'] = Residual_Block(128, net['res5_6'], name='res5_7')
net['res5_8'] = Residual_Block(128, net['res5_7'], name='res5_8')
net['conv5_9'] = Convolution2D(512,
kernel_size=3,
activation='relu',
padding='valid',
strides=2,
name='conv5_9')(net['res5_8'])
# Block 5
net['res6_1'] = Residual_Block(256, net['conv5_9'], name='res6_1')
net['res6_2'] = Residual_Block(256, net['res6_1'], name='res6_2')
net['res6_3'] = Residual_Block(256, net['res6_2'], name='res6_3')
net['res6_4'] = Residual_Block(256, net['res6_3'], name='res6_4')
net['res6_5'] = Residual_Block(
256, net['res6_4'], name='res6_5') # prediction from 6_5 layer 26
net['res6_6'] = Residual_Block(256, net['res6_5'], name='res6_6')
net['res6_7'] = Residual_Block(256, net['res6_6'], name='res6_7')
net['res6_8'] = Residual_Block(256, net['res6_7'], name='res6_8')
net['conv6_9'] = Convolution2D(1024,
kernel_size=3,
activation='relu',
padding='valid',
strides=2,
name='conv6_9')(net['res6_8'])
# Block 6
net['res7_1'] = Residual_Block(512, net['conv6_9'], name='res7_1')
net['res7_2'] = Residual_Block(
512, net['res7_1'], name='res7_2') # prediction from 7_2 layer 34
net['res7_3'] = Residual_Block(512, net['res7_2'], name='res7_3')
net['res7_4'] = Residual_Block(
512, net['res7_3'], name='res7_4') # prediction from 7_4 layer 34
# Last pool
net['pool7_5'] = GlobalAveragePooling2D(name='pool7_5')(net['res7_4'])
# Prediction from conv5_9
net['conv5_9_norm'] = Normalize(20)(net['conv5_9'])
num_priors = 3
net['conv5_9_norm_mbox_loc'] = Convolution2D(num_priors * 4,
kernel_size=3,
padding='same')(
net['conv5_9_norm'])
net['conv5_9_norm_mbox_loc_flat'] = Flatten()(net['conv5_9_norm_mbox_loc'])
net['conv5_9_norm_mbox_conf'] = Convolution2D(num_priors * num_classes,
kernel_size=3,
padding='same')(
net['conv5_9_norm'])
net['conv5_9_norm_mbox_conf_flat'] = Flatten()(
net['conv5_9_norm_mbox_conf'])
net['conv5_9_norm_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[0],
aspect_ratios=aspect_ratios_per_layer[0],
variances=variances)(net['conv5_9_norm'])
# Prediction from res6_5
num_priors = 6
net['res6_5_mbox_loc'] = Convolution2D(num_priors * 4,
kernel_size=3,
padding='same')(net['res6_5'])
net['res6_5_mbox_loc_flat'] = Flatten()(net['res6_5_mbox_loc'])
net['res6_5_mbox_conf'] = Convolution2D(num_priors * num_classes,
kernel_size=3,
padding='same')(net['res6_5'])
net['res6_5_mbox_conf_flat'] = Flatten()(net['res6_5_mbox_conf'])
net['res6_5_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[1],
max_size=scales[2],
aspect_ratios=aspect_ratios_per_layer[1],
variances=variances)(net['res6_5'])
# Prediction from conv6_9
num_priors = 6
net['conv6_9_mbox_loc'] = Convolution2D(num_priors * 4,
kernel_size=3,
padding='same')(net['conv6_9'])
net['conv6_9_mbox_loc_flat'] = Flatten()(net['conv6_9_mbox_loc'])
net['conv6_9_mbox_conf'] = Convolution2D(num_priors * num_classes,
kernel_size=3,
padding='same')(net['conv6_9'])
net['conv6_9_mbox_conf_flat'] = Flatten()(net['conv6_9_mbox_conf'])
net['conv6_9_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[2],
max_size=scales[3],
aspect_ratios=aspect_ratios_per_layer[2],
variances=variances)(net['conv6_9'])
# Prediction from res7_2
num_priors = 6
net['res7_2_mbox_loc'] = Convolution2D(num_priors * 4,
kernel_size=3,
padding='same')(net['res7_2'])
net['res7_2_mbox_loc_flat'] = Flatten()(net['res7_2_mbox_loc'])
net['res7_2_mbox_conf'] = Convolution2D(num_priors * num_classes,
kernel_size=3,
padding='same')(net['res7_2'])
net['res7_2_mbox_conf_flat'] = Flatten()(net['res7_2_mbox_conf'])
net['res7_2_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[3],
max_size=scales[4],
aspect_ratios=aspect_ratios_per_layer[3],
variances=variances)(net['res7_2'])
# Prediction from res7_4
num_priors = 6
net['res7_4_mbox_loc'] = Convolution2D(num_priors * 4,
kernel_size=3,
padding='same')(net['res7_4'])
net['res7_4_mbox_loc_flat'] = Flatten()(net['res7_4_mbox_loc'])
net['res7_4_mbox_conf'] = Convolution2D(num_priors * num_classes,
kernel_size=3,
padding='same')(net['res7_4'])
net['res7_4_mbox_conf_flat'] = Flatten()(net['res7_4_mbox_conf'])
net['res7_4_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[4],
max_size=scales[5],
aspect_ratios=aspect_ratios_per_layer[4],
variances=variances)(net['res7_4'])
# Prediction from pool7_5
num_priors = 6
net['pool7_5_mbox_loc_flat'] = Dense(num_priors * 4)(net['pool7_5'])
net['pool7_5_mbox_conf_flat'] = Dense(num_priors * num_classes)(
net['pool7_5'])
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 1024)
else:
target_shape = (1024, 1, 1)
net['pool7_5_reshaped'] = Reshape(target_shape)(net['pool7_5'])
net['pool7_5_mbox_priorbox'] = PriorBox(
image_size,
min_size=scales[5],
max_size=scales[6],
aspect_ratios=aspect_ratios_per_layer[5],
variances=variances)(net['pool7_5_reshaped'])
# Combine predictions
# We predict 4 box coordinates for each box, hence the localization predictors have depth `n_boxes * 4`
# Output shape of the localization layers: `(batch, height, width, n_boxes * 4)`
net['mbox_loc'] = concatenate([
net['conv5_9_norm_mbox_loc_flat'], net['res6_5_mbox_loc_flat'],
net['conv6_9_mbox_loc_flat'], net['res7_2_mbox_loc_flat'],
net['res7_4_mbox_loc_flat'], net['pool7_5_mbox_loc_flat']
],
axis=1)
# We precidt `n_classes` confidence values for each box, hence the confidence predictors have depth `n_boxes * n_classes`
# Output shape of the confidence layers: `(batch, height, width, n_boxes * n_classes)`
net['mbox_conf'] = concatenate([
net['conv5_9_norm_mbox_conf_flat'], net['res6_5_mbox_conf_flat'],
net['conv6_9_mbox_conf_flat'], net['res7_2_mbox_conf_flat'],
net['res7_4_mbox_conf_flat'], net['pool7_5_mbox_conf_flat']
],
axis=1)
# Output shape of anchors: `(batch, height, width, n_boxes, 8)`
net['mbox_prior'] = concatenate([
net['conv5_9_norm_mbox_priorbox'], net['res6_5_mbox_priorbox'],
net['conv6_9_mbox_priorbox'], net['res7_2_mbox_priorbox'],
net['res7_4_mbox_priorbox'], net['pool7_5_mbox_priorbox']
],
axis=1)
# Calculating number of boxes to isolate it using Reshape
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], '_int_shape'):
num_boxes = net['mbox_loc']._int_shape[-1] // 4
# Concatenate all predictions from different layers
# Axis 0 (batch) and axis 2 (n_classes or 4, respectively) are identical for all layer predictions,
# so we want to concatenate along axis 1, the number of boxes per layer
# Output shape of `mbox_loc`: (batch, n_boxes_total, 4)
net['mbox_loc'] = Reshape((num_boxes, 4))(net['mbox_loc'])
# Output shape of `mbox_conf`: (batch, n_boxes_total, n_classes)
net['mbox_conf'] = Reshape((num_boxes, num_classes))(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_prior']], axis=2)
model = Model(net['input'], net['predictions'])
# model = Model(net['input'], net['pool7_5']) # for debugging
return model
def SSD300(input_shape, num_classes=2):
net = {}
# Block 1
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
padding='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = Conv2D(1024, (3, 3),
activation="relu",
name="fc6",
dilation_rate=(6, 6),
padding="same")(net['pool5'])
# net['fc6'] = AtrousConvolution2D(1024, (3, 3), atrous_rate=(6, 6),
# activation='relu', padding='same',
# name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Conv2D(1024, (1, 1),
activation='relu',
padding='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Conv2D(256, (1, 1),
activation='relu',
padding='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Conv2D(512, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (3, 3), padding='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Conv2D(num_priors * 4, (3, 3), padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (3, 3), padding='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Conv2D(num_priors * 4, (3, 3), padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (3, 3), padding='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Conv2D(num_priors * 4, (3, 3), padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (3, 3), padding='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.common.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = concatenate(
[ #net['conv4_3_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'], net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'], net['conv8_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']
],
# mode='concat', concat_
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate(
[ #net['conv4_3_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'], net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'], net['conv8_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']
],
# mode='concat', concat_
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate(
[ #net['conv4_3_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'], net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'], net['conv8_2_mbox_priorbox'],
net['pool6_mbox_priorbox']
],
# mode='concat', concat_
axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
# mode='concat', concat_
axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
# model = Model(net['input'], net['mbox_loc'])
# plot_model(model, to_file='model.png')
return model
def SSD(input_shape=(300, 300, 3), num_classes=21, segmentation_head=False, depth_head=False):
"""SSD architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3).
num_classes: Number of classes including background.
conv3_4 conv4_6 fc7 conv6_2 conv7_2 pool6
+ + + + + +
| | | | | |
| | v v | |
| | | |
| | +----------------+ | |
| +--> | | <----+ |
| | Concatenate | |
+----------> | | <-----------+
+-------+--------+
|
v
prediction
# References
SSD: https://arxiv.org/abs/1512.02325
Rainbow SSD: https://arxiv.org/abs/1705.09587
"""
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
####################################################################################
# zerro-padding need for backward compatibility
x = ZeroPadding2D((3, 3))(input_tensor)
model = ResNet50(include_top=False, input_tensor=x)
# resnet_out = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='pool5v')(model.get_layer('activation_49').output)
resnet_out = MaxPooling2D((3, 3), strides=(1, 1), padding='same',
name='pool5v')(model.get_layer('activation_49').output)
net['conv3_4'] = model.get_layer("activation_22").output
net['conv4_6'] = model.get_layer("activation_40").output
# END ResNet50
#####################################################################################
# FC6
net['fc6'] = Conv2D(1024, (3, 3), dilation_rate=(6, 6),
activation='relu', padding='same',
name='fc6')(resnet_out)
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Conv2D(1024, (1, 1), activation='relu',
padding='same', name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Conv2D(256, (1, 1), activation='relu',
padding='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Conv2D(512, (3, 3), strides=(2, 2),
activation='relu', padding='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Conv2D(128, (1, 1), activation='relu',
padding='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = Conv2D(256, (3, 3), strides=(2, 2),
activation='relu', padding='same',
name='conv7_2')(net['conv7_1'])
# Block 8
net['conv8_1'] = Conv2D(128, (1, 1), activation='relu',
padding='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Conv2D(256, (3, 3), strides=(2, 2),
activation='relu', padding='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
###########################################################################
# Segmentation PSP ########################################################
if depth_head:
# depth map
x = Conv2D(512, (3, 3), strides=(1, 1), padding="same", name="depth_conv1_3", use_bias=False)(psp)
x = BatchNormalization(momentum=0.95, epsilon=1e-5, name="depth_conv1_3_bn")(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
x = Conv2D(512, (3, 3), strides=(1, 1), padding="same", name="depth_conv2_3", use_bias=False)(x)
x = BatchNormalization(momentum=0.95, epsilon=1e-5, name="depth_conv2_3_bn")(x)
x = Activation('relu')(x)
x = Conv2D(1, (3, 3), strides=(1, 1), padding="same", name="depth_conv2_3", use_bias=False)(x)
x = Lambda(Interp, arguments={'shape': (input_shape[0], input_shape[1])})(x)
depth_map = Activation('relu', name="depth_map")(x)
###########################################################################
asp0 = [1. / 2, 1, 1., 2.]
asp1 = [1. / 3, 1. / 2, 1, 1., 2., 3.]
scales = [0.1, 0.2, 0.38, 0.56, 0.74, 0.92, 1.1]
if segmentation_head:
net['psp1'] = Lambda(Interp, arguments={'shape': (60, 60)})(model.output)
###########################################################################
# CLASSIFIER:1 LAYER: conv3_4 #############################################
num_priors = len(asp0)
cl1_input = Normalize(20, name='conv3_4_norm')(net['conv3_4'])
x = Conv2D(num_priors * 4, (3, 3), strides=(1, 1), dilation_rate=(2, 2),
padding='same', name='conv3_4_norm_mbox_loc')(cl1_input)
x = Flatten(name='conv3_4_norm_mbox_loc_flat')(x)
net['conv3_4_norm_mbox_loc_flat'] = x
x = Conv2D(num_priors * num_classes, (3, 3), padding='same', name="conv3_4_norm_mbox_conf")(cl1_input)
if segmentation_head:
net['psp6'] = Lambda(Interp, arguments={'shape': (60, 60)})(x)
# net['psp6'] = interp_block(y, 1, (60,60), str_lvl=6)
x = Flatten(name='conv3_4_norm_mbox_conf_flat')(x)
net['conv3_4_norm_mbox_conf_flat'] = x
x = PriorBox(img_size, scales[0] * img_size[0], aspect_ratios=asp0,
variances=[0.1, 0.1, 0.2, 0.2],
name='conv3_4_norm_mbox_priorbox')(cl1_input)
net['conv3_4_norm_mbox_priorbox'] = x
###########################################################################
# CLASSIFIER:2 LAYER: conv4_6 #############################################
num_priors = len(asp1)
cl2_input = net['conv4_6']
x = Conv2D(num_priors * 4, (3, 3), padding='same', name='fc7_mbox_loc')(cl2_input)
x = Flatten(name='fc7_mbox_loc_flat')(x)
net['fc7_mbox_loc_flat'] = x
x = Conv2D(num_priors * num_classes, (3, 3), padding='same', name="fc7_mbox_conf")(cl2_input)
if segmentation_head:
net['psp5'] = Lambda(Interp, arguments={'shape': (60, 60)})(x)
# net['psp5'] = interp_block(y, 2, (60,60), str_lvl=4)
x = Flatten(name='fc7_mbox_conf_flat')(x)
net['fc7_mbox_conf_flat'] = x
x = PriorBox(img_size, scales[1] * img_size[0], max_size=scales[2] * img_size[0], aspect_ratios=asp1,
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')(cl2_input)
net['fc7_mbox_priorbox'] = x
###########################################################################
# CLASSIFIER:3 LAYER: fc7 #################################################
num_priors = len(asp1)
cl3_input = Conv2D(512, (1, 1), activation='relu', padding='same', name='fc7_mbox_pre')(net['fc7'])
x = Conv2D(num_priors * 4, (3, 3), padding='same', name='conv6_2_mbox_loc')(cl3_input)
x = Flatten(name='conv6_2_mbox_loc_flat')(x)
net['conv6_2_mbox_loc_flat'] = x
x = Conv2D(num_priors * num_classes, (3, 3), padding='same', name="conv6_2_mbox_conf")(cl3_input)
if segmentation_head:
net['psp4'] = Lambda(Interp, arguments={'shape': (60, 60)})(x)
# net['psp4'] = interp_block(y, 3, (60,60), str_lvl=3)
x = Flatten(name='conv6_2_mbox_conf_flat')(x)
net['conv6_2_mbox_conf_flat'] = x
x = PriorBox(img_size, scales[2] * img_size[0], max_size=scales[3] * img_size[0], aspect_ratios=asp1,
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(cl3_input)
net['conv6_2_mbox_priorbox'] = x
###########################################################################
# CLASSIFIER:4 LAYER: conv6_2 #############################################
num_priors = len(asp1)
cl4_input = Conv2D(256, (1, 1), activation='relu', padding='same', name='conv6_2_mbox_pre')(net['conv6_2'])
x = Conv2D(num_priors * 4, (3, 3), padding='same', name='conv7_2_mbox_loc')(cl4_input)
x = Flatten(name='conv7_2_mbox_loc_flat')(x)
net['conv7_2_mbox_loc_flat'] = x
x = Conv2D(num_priors * num_classes, (3, 3), padding='same', name="conv7_2_mbox_conf")(cl4_input)
if segmentation_head:
net['psp3'] = Lambda(Interp, arguments={'shape': (60, 60)})(x)
# net['psp3'] = interp_block(y, 4, (60,60), str_lvl=2)
x = Flatten(name='conv7_2_mbox_conf_flat')(x)
net['conv7_2_mbox_conf_flat'] = x
x = PriorBox(img_size, scales[3] * img_size[0], max_size=scales[4] * img_size[0], aspect_ratios=asp1,
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(cl4_input)
net['conv7_2_mbox_priorbox'] = x
###########################################################################
# CLASSIFIER:5 LAYER: conv7_2 #############################################
num_priors = len(asp1)
cl5_input = net['conv7_2']
x = Conv2D(num_priors * 4, (3, 3), padding='same', name='conv8_2_mbox_loc')(cl5_input)
x = Flatten(name='conv8_2_mbox_loc_flat')(x)
net['conv8_2_mbox_loc_flat'] = x
x = Conv2D(num_priors * num_classes, (3, 3), padding='same', name="conv8_2_mbox_conf")(cl5_input)
if segmentation_head:
net['psp2'] = Lambda(Interp, arguments={'shape': (60, 60)})(x)
# net['psp2'] = interp_block(y, 6, (60,60), str_lvl=1)
x = Flatten(name='conv8_2_mbox_conf_flat')(x)
net['conv8_2_mbox_conf_flat'] = x
x = PriorBox(img_size, scales[4] * img_size[0], max_size=scales[5] * img_size[0], aspect_ratios=asp1,
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(cl5_input)
net['conv8_2_mbox_priorbox'] = x
###########################################################################
# CLASSIFIER:6 LAYER: pool6 ###############################################
num_priors = len(asp0)
cl6_input = net['pool6']
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(cl6_input)
net['pool6_mbox_loc_flat'] = x
x = Dense(num_priors * num_classes, name="pool6_mbox_conf_flat")(cl6_input)
net['pool6_mbox_conf_flat'] = x
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
x = Reshape(target_shape, name='pool6_reshaped')(cl6_input)
x = PriorBox(img_size, scales[5] * img_size[0], max_size=scales[6] * img_size[0], aspect_ratios=asp0,
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(x)
net['pool6_mbox_priorbox'] = x
###########################################################################
# Gather all predictions
net['mbox_loc'] = Concatenate(axis=1, name='mbox_loc')([
net['conv3_4_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']])
net['mbox_conf'] = Concatenate(axis=1, name='mbox_conf')([
net['conv3_4_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']])
net['mbox_priorbox'] = Concatenate(axis=1, name='mbox_priorbox')([
net['conv3_4_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'],
net['pool6_mbox_priorbox']])
if segmentation_head:
psp = Concatenate(axis=-1, name='psp')([
net['psp1'],
net['psp2'],
net['psp3'],
net['psp4'],
net['psp5'],
net['psp6'],
])
psp.trainable = False
x = Conv2D(256, (3, 3), strides=(1, 1), padding="same", name="seg_conv1_1")(psp)
x = Activation('relu')(x)
x = Conv2D(256, (3, 3), strides=(1, 1), padding="same", name="seg_conv1_2")(x)
x = BatchNormalization(momentum=0.95, epsilon=1e-5, name="seg_conv1_2_bn")(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
x = Conv2D(num_classes, (1, 1), strides=(1, 1), name="seg_conv_last")(x)
x = Lambda(Interp, arguments={'shape': (input_shape[0], input_shape[1])})(x)
segmentation = Activation('sigmoid', name='segmentation')(x)
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4), name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes), name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax', name='mbox_conf_final')(net['mbox_conf'])
ssd_out = Concatenate(axis=2, name='ssd_out')([
net['mbox_loc'],
net['mbox_conf'],
net['mbox_priorbox']])
if not segmentation_head and not depth_head:
model = Model(input_tensor, ssd_out)
else:
out = [ssd_out]
if segmentation_head:
out.append(segmentation)
if depth_head:
out.append(depth_map)
model = Model(input_tensor, out)
return model
def ssd512(input_shape=(512, 512, 3),
num_classes=21,
min_scale=0.1,
max_scale=0.9,
scales=None,
aspect_ratios_global=None,
aspect_ratios_per_layer=None,
two_boxes_for_ar1=True,
limit_boxes=True,
variances=[0.1, 0.1, 0.2, 0.2],
weights_path=None,
frozen_layers=None,
summary=False,
plot=False):
n_predictor_layers = 7 # The number of predictor conv layers in the network is 6 for the original SSD300
default_aspect_ratios = [[0.5, 1.0, 2.0],
[1.0/3.0, 0.5, 1.0, 2.0, 3.0],
[1.0/3.0, 0.5, 1.0, 2.0, 3.0],
[1.0/3.0, 0.5, 1.0, 2.0, 3.0],
[1.0/3.0, 0.5, 1.0, 2.0, 3.0],
[0.5, 1.0, 2.0],
[0.5, 1.0, 2.0]]
# Get a few exceptions out of the way first
if aspect_ratios_global is None and aspect_ratios_per_layer is None:
print(
"`aspect_ratios_global` and `aspect_ratios_per_layer` both are None. Default aspect ratios of the paper implementation are used.")
if aspect_ratios_per_layer:
if len(aspect_ratios_per_layer) != n_predictor_layers:
raise ValueError(
"It must be either aspect_ratios_per_layer is None or len(aspect_ratios_per_layer) == {}, but len(aspect_ratios_per_layer) == {}.".format(
n_predictor_layers, len(aspect_ratios_per_layer)))
if (min_scale is None or max_scale is None) and scales is None:
raise ValueError("Either `min_scale` and `max_scale` or `scales` need to be specified.")
if scales:
if len(scales) != n_predictor_layers + 1:
raise ValueError("It must be either scales is None or len(scales) == {}, but len(scales) == {}.".format(
n_predictor_layers + 1, len(scales)))
else: # If no explicit list of scaling factors was passed, compute the list of scaling factors from `min_scale` and `max_scale`
scales = np.linspace(min_scale, max_scale, n_predictor_layers + 1)
if len(variances) != 4:
raise ValueError("4 variance values must be pased, but {} values were received.".format(len(variances)))
variances = np.array(variances)
if np.any(variances <= 0):
raise ValueError("All variances must be >0, but the variances given are {}".format(variances))
# Set the aspect ratios for each predictor layer. These are only needed for the anchor box layers.
if aspect_ratios_global is None and aspect_ratios_per_layer is None:
aspect_ratios = default_aspect_ratios
elif aspect_ratios_per_layer and aspect_ratios_global is None:
aspect_ratios = aspect_ratios_per_layer
elif aspect_ratios_per_layer is None and aspect_ratios_global:
aspect_ratios = [aspect_ratios_global] * n_predictor_layers
aspect_ratios_conv4_3 = aspect_ratios[0]
aspect_ratios_fc7 = aspect_ratios[1]
aspect_ratios_conv6_2 = aspect_ratios[2]
aspect_ratios_conv7_2 = aspect_ratios[3]
aspect_ratios_conv8_2 = aspect_ratios[4]
aspect_ratios_conv9_2 = aspect_ratios[5]
aspect_ratios_conv10_2 = aspect_ratios[6]
# Compute the number of boxes to be predicted per cell for each predictor layer.
# We need this so that we know how many channels the predictor layers need to have.
if aspect_ratios:
n_boxes = []
for aspect_ratio in aspect_ratios:
if (1 in aspect_ratio) & two_boxes_for_ar1:
n_boxes.append(len(aspect_ratio) + 1) # +1 for the second box for aspect ratio 1
else:
n_boxes.append(len(aspect_ratio))
n_boxes_conv4_3 = n_boxes[0]
n_boxes_fc7 = n_boxes[1]
n_boxes_conv6_2 = n_boxes[2]
n_boxes_conv7_2 = n_boxes[3]
n_boxes_conv8_2 = n_boxes[4]
n_boxes_conv9_2 = n_boxes[5]
n_boxes_conv10_2 = n_boxes[6]
input_layer = Input(shape=input_shape)
img_height, img_width, img_channels = input_shape[0], input_shape[1], input_shape[2]
# Block 1 -----------------------------------------------
conv1_1 = Conv2D(64, (3, 3),
name='conv1_1',
padding='same',
activation='relu')(input_layer)
conv1_2 = Conv2D(64, (3, 3),
name='conv1_2',
padding='same',
activation='relu')(conv1_1)
pool1 = MaxPooling2D(name='pool1',
pool_size=(2, 2),
strides=(2, 2),
padding='same', )(conv1_2)
# Block 2 ----------------------------------------------
conv2_1 = Conv2D(128, (3, 3),
name='conv2_1',
padding='same',
activation='relu')(pool1)
conv2_2 = Conv2D(128, (3, 3),
name='conv2_2',
padding='same',
activation='relu')(conv2_1)
pool2 = MaxPooling2D(name='pool2',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv2_2)
# Block 3 ----------------------------------------------
conv3_1 = Conv2D(256, (3, 3),
name='conv3_1',
padding='same',
activation='relu')(pool2)
conv3_2 = Conv2D(256, (3, 3),
name='conv3_2',
padding='same',
activation='relu')(conv3_1)
conv3_3 = Conv2D(256, (3, 3),
name='conv3_3',
padding='same',
activation='relu')(conv3_2)
pool3 = MaxPooling2D(name='pool3',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv3_3)
# Block 4 ---------------------------------------------
conv4_1 = Conv2D(512, (3, 3),
name='conv4_1',
padding='same',
activation='relu')(pool3)
conv4_2 = Conv2D(512, (3, 3),
name='conv4_2',
padding='same',
activation='relu')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),
name='conv4_3',
padding='same',
activation='relu')(conv4_2)
pool4 = MaxPooling2D(name='pool4',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv4_3)
# Block 5 --------------------------------------------
conv5_1 = Conv2D(512, (3, 3),
name='conv5_1',
padding='same',
activation='relu')(pool4)
conv5_2 = Conv2D(512, (3, 3),
name='conv5_2',
padding='same',
activation='relu')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
name='conv5_3',
padding='same',
activation='relu')(conv5_2)
pool5 = MaxPooling2D(name='pool5',
pool_size=(3, 3),
strides=(1, 1),
padding='same')(conv5_3)
# Block 6 --------------------------------------------
fc6 = Conv2D(1024, (3, 3),
name='fc6',
dilation_rate=(6, 6),
padding='same',
activation='relu'
)(pool5)
# Block 7 --------------------------------------------
fc7 = Conv2D(1024, (1, 1),
name='fc7',
padding='same',
activation='relu'
)(fc6)
# EXTRAS
# Block 8 --------------------------------------------
conv6_1 = Conv2D(256, (1, 1),
name='conv6_1',
padding='same',
activation='relu')(fc7)
conv6_1z = ZeroPadding2D(name='conv6_1z')(conv6_1)
conv6_2 = Conv2D(512, (3, 3),
name='conv6_2',
strides=(2, 2),
padding='valid',
activation='relu')(conv6_1z)
# Block 9 --------------------------------------------
conv7_1 = Conv2D(128, (1, 1),
name='conv7_1',
padding='same',
activation='relu')(conv6_2)
conv7_1z = ZeroPadding2D(name='conv7_1z')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
name='conv7_2',
padding='valid',
strides=(2, 2),
activation='relu')(conv7_1z)
# Block 10 -------------------------------------------
conv8_1 = Conv2D(128, (1, 1),
name='conv8_1',
padding='same',
activation='relu')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
name='conv8_2',
padding='valid',
strides=(1, 1),
activation='relu')(conv8_1)
# Block 11 -------------------------------------------
conv9_1 = Conv2D(128, (1, 1),
name='conv9_1',
padding='same',
activation='relu')(conv8_2)
conv9_2 = Conv2D(256, (3, 3),
name='conv9_2',
padding='valid',
strides=(1, 1),
activation='relu')(conv9_1)
# Block 12 -------------------------------------------
conv10_1 = Conv2D(128, (1, 1),
name='conv10_1',
padding='same',
activation='relu')(conv9_2)
conv10_2 = Conv2D(256, (4, 4),
name='conv10_2',
padding='valid',
strides=(1, 1),
activation='relu')(conv10_1)
# Last Pool ------------------------------------------
# pool6 = GlobalAveragePooling2D(name='pool6')(conv8_2)
# Prediction from conv4_3 ----------------------------
conv4_3_norm = Normalize(20, name='conv4_3_norm')(conv4_3)
conv4_3_norm_mbox_loc = Conv2D(n_boxes_conv4_3 * 4, (3, 3),
name='conv4_3_norm_mbox_loc',
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_loc_flat = Flatten(name='conv4_3_norm_mbox_loc_flat')(conv4_3_norm_mbox_loc)
conv4_3_norm_mbox_conf = Conv2D(n_boxes_conv4_3 * num_classes, (3, 3),
name='conv4_3_norm_mbox_conf',
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_conf_flat = Flatten(name='conv4_3_norm_mbox_conf_flat')(conv4_3_norm_mbox_conf)
conv4_3_norm_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[0], next_scale=scales[1],
aspect_ratios=aspect_ratios_conv4_3,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv4_3_norm_mbox_priorbox')(conv4_3_norm)
# Prediction from fc7 ---------------------------------
fc7_mbox_conf = Conv2D(n_boxes_fc7 * num_classes, (3, 3),
padding='same',
name='fc7_mbox_conf')(fc7)
fc7_mbox_conf_flat = Flatten(name='fc7_mbox_conf_flat')(fc7_mbox_conf)
fc7_mbox_loc = Conv2D(n_boxes_fc7 * 4, (3, 3),
name='fc7_mbox_loc',
padding='same')(fc7)
fc7_mbox_loc_flat = Flatten(name='fc7_mbox_loc_flat')(fc7_mbox_loc)
fc7_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[1], next_scale=scales[2],
aspect_ratios=aspect_ratios_fc7,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='fc7_mbox_priorbox')(fc7)
# Prediction from conv6_2 ------------------------------
conv6_2_mbox_conf = Conv2D(n_boxes_conv6_2 * num_classes, (3, 3),
padding='same',
name='conv6_2_mbox_conf')(conv6_2)
conv6_2_mbox_conf_flat = Flatten(name='conv6_2_mbox_conf_flat')(conv6_2_mbox_conf)
conv6_2_mbox_loc = Conv2D(n_boxes_conv6_2 * 4, (3, 3,),
name='conv6_2_mbox_loc',
padding='same')(conv6_2)
conv6_2_mbox_loc_flat = Flatten(name='conv6_2_mbox_loc_flat')(conv6_2_mbox_loc)
conv6_2_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[2], next_scale=scales[3],
aspect_ratios=aspect_ratios_conv6_2,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv6_2_mbox_priorbox')(conv6_2)
# Prediction from conv7_2 --------------------------------
conv7_2_mbox_conf = Conv2D(n_boxes_conv7_2 * num_classes, (3, 3),
padding='same',
name='conv7_2_mbox_conf')(conv7_2)
conv7_2_mbox_conf_flat = Flatten(name='conv7_2_mbox_conf_flat')(conv7_2_mbox_conf)
conv7_2_mbox_loc = Conv2D(n_boxes_conv7_2 * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(conv7_2)
conv7_2_mbox_loc_flat = Flatten(name='conv7_2_mbox_loc_flat')(conv7_2_mbox_loc)
conv7_2_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[3], next_scale=scales[4],
aspect_ratios=aspect_ratios_conv7_2,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv7_2_mbox_priorbox')(conv7_2)
# Prediction from conv8_2 -------------------------------
conv8_2_mbox_conf = Conv2D(n_boxes_conv8_2 * num_classes, (3, 3),
padding='same',
name='conv8_2_mbox_conf')(conv8_2)
conv8_2_mbox_conf_flat = Flatten(name='conv8_2_mbox_conf_flat')(conv8_2_mbox_conf)
conv8_2_mbox_loc = Conv2D(n_boxes_conv8_2 * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(conv8_2)
conv8_2_mbox_loc_flat = Flatten(name='conv8_2_mbox_loc_flat')(conv8_2_mbox_loc)
conv8_2_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[4], next_scale=scales[5],
aspect_ratios=aspect_ratios_conv8_2,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv8_2_mbox_priorbox')(conv8_2)
# Prediction from conv9_2 -------------------------------
conv9_2_mbox_conf = Conv2D(n_boxes_conv9_2 * num_classes, (3, 3),
padding='same',
name='conv9_2_mbox_conf')(conv9_2)
conv9_2_mbox_conf_flat = Flatten(name='conv9_2_mbox_conf_flat')(conv9_2_mbox_conf)
conv9_2_mbox_loc = Conv2D(n_boxes_conv9_2 * 4, (3, 3),
padding='same',
name='conv9_2_mbox_loc')(conv9_2)
conv9_2_mbox_loc_flat = Flatten(name='conv9_2_mbox_loc_flat')(conv9_2_mbox_loc)
conv9_2_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[5], next_scale=scales[6],
aspect_ratios=aspect_ratios_conv9_2,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv9_2_mbox_priorbox')(conv9_2)
# Prediction from conv10_2 --------------------------------------------
conv10_2_mbox_conf = Conv2D(n_boxes_conv10_2 * num_classes, (3, 3),
padding='same',
name='conv10_2_mbox_conf')(conv10_2)
conv10_2_mbox_conf_flat = Flatten(name='conv10_2_mbox_conf_flat')(conv10_2_mbox_conf)
conv10_2_mbox_loc = Conv2D(n_boxes_conv10_2 * 4, (3, 3),
padding='same',
name='conv10_2_mbox_loc')(conv10_2)
conv10_2_mbox_loc_flat = Flatten(name='conv10_2_mbox_loc_flat')(conv10_2_mbox_loc)
conv10_2_mbox_priorbox = PriorBox(img_height, img_width,
this_scale=scales[6], next_scale=scales[7],
aspect_ratios=aspect_ratios_conv10_2,
two_boxes_for_ar1=two_boxes_for_ar1,
limit_boxes=limit_boxes,
variances=variances,
name='conv10_2_mbox_priorbox')(conv10_2)
# Gather all predictions -------------------------------------------
mbox_loc = concatenate([conv4_3_norm_mbox_loc_flat,
fc7_mbox_loc_flat,
conv6_2_mbox_loc_flat,
conv7_2_mbox_loc_flat,
conv8_2_mbox_loc_flat,
conv9_2_mbox_loc_flat,
conv10_2_mbox_loc_flat],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([conv4_3_norm_mbox_conf_flat,
fc7_mbox_conf_flat,
conv6_2_mbox_conf_flat,
conv7_2_mbox_conf_flat,
conv8_2_mbox_conf_flat,
conv9_2_mbox_conf_flat,
conv10_2_mbox_conf_flat],
axis=1,
name='mbox_conf')
# Reshape the anchor box tensors, yielding 3D tensors of shape `(batch, height * width * n_boxes, 8)`
conv4_3_norm_mbox_priorbox_reshape = Reshape((-1, 8), name='conv4_3_norm_mbox_priorbox_reshape')(conv4_3_norm_mbox_priorbox)
fc7_mbox_priorbox_reshape = Reshape((-1, 8), name='fc7_mbox_priorbox_reshape')(fc7_mbox_priorbox)
conv6_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv6_2_mbox_priorbox_reshape')(conv6_2_mbox_priorbox)
conv7_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv7_2_mbox_priorbox_reshape')(conv7_2_mbox_priorbox)
conv8_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv8_2_mbox_priorbox_reshape')(conv8_2_mbox_priorbox)
conv9_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv9_2_mbox_priorbox_reshape')(conv9_2_mbox_priorbox)
conv10_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv10_2_mbox_priorbox_reshape')(conv10_2_mbox_priorbox)
mbox_priorbox = concatenate([conv4_3_norm_mbox_priorbox_reshape,
fc7_mbox_priorbox_reshape,
conv6_2_mbox_priorbox_reshape,
conv7_2_mbox_priorbox_reshape,
conv8_2_mbox_priorbox_reshape,
conv9_2_mbox_priorbox_reshape,
conv10_2_mbox_priorbox_reshape],
axis=1, name='mbox_priorbox')
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
mbox_loc = Reshape((num_boxes, 4),
name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax',
name='mbox_conf_final')(mbox_conf)
predictions = concatenate([mbox_loc,
mbox_conf,
mbox_priorbox],
axis=2,
name='predictions')
model = Model(inputs=input_layer, outputs=predictions)
if weights_path is not None:
model.load_weights(weights_path, by_name=True)
if frozen_layers is not None:
for layer in model.layers:
if layer.name in frozen_layers:
layer.trainable = False
if summary:
model.summary()
if plot:
plot_model(model, to_file='SSD512.png')
SVG(model_to_dot(model).create(prog='dot', format='svg'))
return model
def SSD300(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
# SSD网路（以键值对方式存储每个网络层张量）
net = {}
# <editor-fold defaultstate = "collapsed" desc = "block1" >
# Block 1
# 输入源
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
# 卷积
net['conv1_1'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_1')(net['input'])
# 卷积
net['conv1_2'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
# 池化
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool1')(net['conv1_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block2" >
# Block 2
# 卷积
net['conv2_1'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
# 卷积
net['conv2_2'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
# 池化
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool2')(net['conv2_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block3" >
# Block 3
# 卷积
net['conv3_1'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
# 卷积
net['conv3_2'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
# 卷积
net['conv3_3'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
# 池化
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool3')(net['conv3_3'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block4" >
# Block 4
# 卷积
net['conv4_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
# 卷积
net['conv4_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
# 卷积
net['conv4_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
# 池化
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool4')(net['conv4_3'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block5" >
# Block 5
# 卷积
net['conv5_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
# 卷积
net['conv5_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
# 卷积
net['conv5_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
# 池化
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
border_mode='same',
name='pool5')(net['conv5_3'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "fc6" >
# FC6
# 带孔卷积
net['fc6'] = AtrousConvolution2D(1024,
3,
3,
atrous_rate=(6, 6),
activation='relu',
border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "fc7" >
# FC7
# 卷积
net['fc7'] = Convolution2D(1024,
1,
1,
activation='relu',
border_mode='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block6" >
# Block 6
# 卷积
net['conv6_1'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
# 卷积
net['conv6_2'] = Convolution2D(512,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv6_2')(net['conv6_1'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block7" >
# Block 7
# 卷积
net['conv7_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
# ZeroPadding
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
# 卷积
net['conv7_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv7_2')(net['conv7_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "block8" >
# Block 8
# 卷积
net['conv8_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
# 卷积
net['conv8_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv8_2')(net['conv8_1'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "AveragePooling" >
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from conv4_3" >
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from fc7" >
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from conv6_2" >
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from conv7_2" >
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from conv8_2" >
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Prediction from pool6" >
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Gather all predictions" >
# Gather all predictions
net['mbox_loc'] = merge([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
mode='concat',
concat_axis=1,
name='mbox_loc')
net['mbox_conf'] = merge([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
mode='concat',
concat_axis=1,
name='mbox_conf')
net['mbox_priorbox'] = merge([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
mode='concat',
concat_axis=1,
name='mbox_priorbox')
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Reshape And Merge" >
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
mode='concat',
concat_axis=2,
name='predictions')
# </editor-fold>
# <editor-fold defaultstate = "collapsed" desc = "Build Model" >
model = Model(net['input'], net['predictions'])
return model
def SSD300(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net2 = MarkNet(input_shape=(64, 64, 3))
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
# prior layerに引数として渡す際利用する
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
border_mode='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = AtrousConvolution2D(1024,
3,
3,
atrous_rate=(6, 6),
activation='relu',
border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024,
1,
1,
activation='relu',
border_mode='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv8_2')(net['conv8_1'])
# Last Pool 最終出力
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
from keras.layers import Lambda
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
# Marknetとのmarge
# merge = Add()([x, net2['dense2m']])
net['pool6_mbox_conf_flat'] = x # merge#x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = concatenate([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
# 最終出力
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
# モデルの構造プロット
keras.utils.plot_model(model, "./ssdmodel.png", show_shapes=True)
return model
def SSD300(input_shape=(300, 300, 3), num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
####################################################################################
# ResNet50 architecture
# (adapted from https://github.com/fchollet/deep-learning-models/resnet50.py)
if not K.is_keras_tensor(input_tensor):
net['input'] = Input(tensor=input_tensor)
else:
net['input'] = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
# Block 1
x = ZeroPadding2D((3, 3))(net['input'])
net['conv1'] = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x)
net['bn_conv1'] = BatchNormalization(axis=bn_axis,
name='bn_conv1')(net['conv1'])
x = Activation('relu')(net['bn_conv1'])
x = ZeroPadding2D((1, 1))(x)
net['pool1'] = MaxPooling2D((3, 3), strides=(2, 2))(x)
# Block 2
net['conv2_1'] = conv_block(net['pool1'],
3, [64, 64, 256],
stage=2,
block='a',
strides=(1, 1))
net['conv2_2'] = identity_block(net['conv2_1'],
3, [64, 64, 256],
stage=2,
block='b')
net['conv2_3'] = identity_block(net['conv2_2'],
3, [64, 64, 256],
stage=2,
block='c')
# Block 3
net['conv3_1'] = conv_block(net['conv2_3'],
3, [128, 128, 512],
stage=3,
block='a')
net['conv3_2'] = identity_block(net['conv3_1'],
3, [128, 128, 512],
stage=3,
block='b')
net['conv3_3'] = identity_block(net['conv3_2'],
3, [128, 128, 512],
stage=3,
block='c')
net['conv3_4'] = identity_block(net['conv3_3'],
3, [128, 128, 512],
stage=3,
block='d')
# Block 4
net['conv4_1'] = conv_block(net['conv3_4'],
3, [256, 256, 1024],
stage=4,
block='a')
net['conv4_2'] = identity_block(net['conv4_1'],
3, [256, 256, 1024],
stage=4,
block='b')
net['conv4_3'] = identity_block(net['conv4_2'],
3, [256, 256, 1024],
stage=4,
block='c')
net['conv4_4'] = identity_block(net['conv4_3'],
3, [256, 256, 1024],
stage=4,
block='d')
net['conv4_5'] = identity_block(net['conv4_4'],
3, [256, 256, 1024],
stage=4,
block='e')
net['conv4_6'] = identity_block(net['conv4_5'],
3, [256, 256, 1024],
stage=4,
block='f')
# Block 5
net['conv5_1'] = conv_block(net['conv4_6'],
3, [512, 512, 2048],
stage=5,
block='a')
net['conv5_2'] = identity_block(net['conv5_1'],
3, [512, 512, 2048],
stage=5,
block='b')
net['conv5_3'] = identity_block(net['conv5_2'],
3, [512, 512, 2048],
stage=5,
block='c')
# net['pool5'] = AveragePooling2D((7, 7), name='pool5')(net['conv5_3'])
# resnet uses this map directly onto the classification (top layer)
# we will use the VGG pooling instead, which provides an appropriately sized input to fc6
net['pool5v'] = MaxPooling2D((3, 3),
strides=(1, 1),
border_mode='same',
name='pool5v')(net['conv5_3'])
# END ResNet50
#####################################################################################
# FC6
net['fc6'] = AtrousConvolution2D(1024,
3,
3,
atrous_rate=(6, 6),
activation='relu',
border_mode='same',
name='fc6')(net['pool5v'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024,
1,
1,
activation='relu',
border_mode='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = ZeroPadding2D()(net['conv6_1'])
net['conv6_2'] = Convolution2D(512,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv6_2')(net['conv6_2'])
# Block 7
net['conv7_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = ZeroPadding2D()(net['conv8_1'])
net['conv8_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv8_2')(net['conv8_2'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv3_4 (still called conv4_3 in the remainder)
# Will clean this up after training tests
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv3_4'])
num_priors = 3
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from conv4_6 -- again, will replace after train test
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='fc7_mbox_loc')(net['conv4_6'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(
num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv4_6']) # changed from fc7
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
# Another change from fc7
net['fc7_mbox_priorbox'] = priorbox(net['conv4_6'])
# Prediction from this fc7 (it will still be called 6_2)
# project it so that its channels are 512, as bounding box data
net['fc7_mbox_pre'] = Convolution2D(512,
1,
1,
activation='relu',
border_mode='same',
name='fc7_mbox_pre')(net['fc7'])
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv6_2_mbox_loc')(net['fc7_mbox_pre'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['fc7_mbox_pre']) # changed from conv6_2
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(
net['fc7_mbox_pre']) # changed from conv6_2
# Prediction from conv6_2
# Project it down to 256
# (old conv7_2)
net['conv6_2_mbox_pre'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_2_mbox_pre')(
net['conv6_2'])
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv7_2_mbox_loc')(net['conv6_2_mbox_pre'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(
net['conv6_2_mbox_pre']) # changed from conv7_2
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
# old conv7_2
net['conv7_2_mbox_priorbox'] = priorbox(net['conv6_2_mbox_pre'])
# Prediction from conv7_2
# old (conv8_2)
# no projections needed
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv8_2_mbox_loc')(net['conv7_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv7_2']) # changed from conv8_2
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(
net['conv7_2']) # changed from conv8_2
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = merge([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
mode='concat',
concat_axis=1,
name='mbox_loc')
net['mbox_conf'] = merge([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
mode='concat',
concat_axis=1,
name='mbox_conf')
net['mbox_priorbox'] = merge([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
mode='concat',
concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
mode='concat',
concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
return model
def SSD(input_shape, num_classes):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
img_size=(input_shape[1],input_shape[0])
input_shape=(input_shape[1],input_shape[0],3)
mobilenet_input_shape=(224,224,3)
net={}
net['input']=Input(input_shape)
mobilenet=MobileNet(input_shape=mobilenet_input_shape,include_top=False,weights='imagenet')
FeatureExtractor=Model(inputs=mobilenet.input,outputs=mobilenet.get_layer('conv_dw_11_relu').output)
conv11=FeatureExtractor(net['input'])
net['conv11'] = Conv2D(512, (1, 1), padding='same', name='conv11')(conv11)
net['conv11'] = BatchNormalization( momentum=0.99, name='bn11')(net['conv11'])
net['conv11'] = Activation('relu')(net['conv11'])
# Block
#(19,19)
net['conv12dw'] = SeparableConv2D(512, (3, 3),strides=(2, 2), padding='same', name='conv12dw')(net['conv11'])
net['conv12dw'] = BatchNormalization( momentum=0.99, name='bn12dw')(net['conv12dw'])
net['conv12dw'] = Activation('relu')(net['conv12dw'])
net['conv12'] = Conv2D(1024, (1, 1), padding='same',name='conv12')(net['conv12dw'])
net['conv12'] = BatchNormalization( momentum=0.99, name='bn12')(net['conv12'])
net['conv12'] = Activation('relu')(net['conv12'])
net['conv13dw'] = SeparableConv2D(1024, (3, 3), padding='same',name='conv13dw')(net['conv12'])
net['conv13dw'] = BatchNormalization( momentum=0.99, name='bn13dw')(net['conv13dw'])
net['conv13dw'] = Activation('relu')(net['conv13dw'])
net['conv13'] = Conv2D(1024, (1, 1), padding='same',name='conv13')(net['conv13dw'])
net['conv13'] = BatchNormalization( momentum=0.99, name='bn13')(net['conv13'])
net['conv13'] = Activation('relu')(net['conv13'])
net['conv14_1'] = Conv2D(256, (1, 1), padding='same', name='conv14_1')(net['conv13'])
net['conv14_1'] = BatchNormalization( momentum=0.99, name='bn14_1')(net['conv14_1'])
net['conv14_1'] = Activation('relu')(net['conv14_1'])
net['conv14_2'] = Conv2D(512, (3, 3), strides=(2, 2), padding='same', name='conv14_2')(net['conv14_1'])
net['conv14_2'] = BatchNormalization( momentum=0.99, name='bn14_2')(net['conv14_2'])
net['conv14_2'] = Activation('relu')(net['conv14_2'])
net['conv15_1'] = Conv2D(128, (1, 1), padding='same',name='conv15_1')(net['conv14_2'])
net['conv15_1'] = BatchNormalization( momentum=0.99, name='bn15_1')(net['conv15_1'])
net['conv15_1'] = Activation('relu')(net['conv15_1'])
net['conv15_2'] = Conv2D(256, (3, 3), strides=(2, 2), padding='same',name='conv15_2')(net['conv15_1'])
net['conv15_2'] = BatchNormalization( momentum=0.99, name='bn15_2')(net['conv15_2'])
net['conv15_2'] = Activation('relu')(net['conv15_2'])
net['conv16_1'] = Conv2D(128, (1, 1), padding='same', name='conv16_1')(net['conv15_2'])
net['conv16_1'] = BatchNormalization( momentum=0.99, name='bn16_1')(net['conv16_1'])
net['conv16_1'] = Activation('relu')(net['conv16_1'])
net['conv16_2'] = Conv2D(256, (3, 3), strides=(2, 2), padding='same', name='conv16_2')(net['conv16_1'])
net['conv16_2'] = BatchNormalization( momentum=0.99, name='bn16_2')(net['conv16_2'])
net['conv16_2'] = Activation('relu')(net['conv16_2'])
net['conv17_1'] = Conv2D(64, (1, 1), padding='same', name='conv17_1')(net['conv16_2'])
net['conv17_1'] = BatchNormalization( momentum=0.99, name='bn17_1')(net['conv17_1'])
net['conv17_1'] = Activation('relu')(net['conv17_1'])
net['conv17_2'] = Conv2D(128, (3, 3), strides=(2, 2), padding='same', name='conv17_2')(net['conv17_1'])
net['conv17_2'] = BatchNormalization( momentum=0.99, name='bn17_2')(net['conv17_2'])
net['conv17_2'] = Activation('relu')(net['conv17_2'])
#Prediction from conv11
num_priors = 3
x = Conv2D(num_priors * 4, (1,1), padding='same',name='conv11_mbox_loc')(net['conv11'])
net['conv11_mbox_loc'] = x
flatten = Flatten(name='conv11_mbox_loc_flat')
net['conv11_mbox_loc_flat'] = flatten(net['conv11_mbox_loc'])
name = 'conv11_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (1,1), padding='same',name=name)(net['conv11'])
net['conv11_mbox_conf'] = x
flatten = Flatten(name='conv11_mbox_conf_flat')
net['conv11_mbox_conf_flat'] = flatten(net['conv11_mbox_conf'])
priorbox = PriorBox(img_size,60,max_size=None, aspect_ratios=[2],variances=[0.1, 0.1, 0.2, 0.2],name='conv11_mbox_priorbox')
net['conv11_mbox_priorbox'] = priorbox(net['conv11'])
# Prediction from conv13
num_priors = 6
net['conv13_mbox_loc'] = Conv2D(num_priors * 4, (1,1),padding='same',name='conv13_mbox_loc')(net['conv13'])
flatten = Flatten(name='conv13_mbox_loc_flat')
net['conv13_mbox_loc_flat'] = flatten(net['conv13_mbox_loc'])
name = 'conv13_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['conv13_mbox_conf'] = Conv2D(num_priors * num_classes, (1,1),padding='same',name=name)(net['conv13'])
flatten = Flatten(name='conv13_mbox_conf_flat')
net['conv13_mbox_conf_flat'] = flatten(net['conv13_mbox_conf'])
priorbox = PriorBox(img_size, 105.0, max_size=150.0, aspect_ratios=[2, 3],variances=[0.1, 0.1, 0.2, 0.2],name='conv13_mbox_priorbox')
net['conv13_mbox_priorbox'] = priorbox(net['conv13'])
# Prediction from conv12
num_priors = 6
x = Conv2D(num_priors * 4, (1,1), padding='same',name='conv14_2_mbox_loc')(net['conv14_2'])
net['conv14_2_mbox_loc'] = x
flatten = Flatten(name='conv14_2_mbox_loc_flat')
net['conv14_2_mbox_loc_flat'] = flatten(net['conv14_2_mbox_loc'])
name = 'conv14_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (1,1), padding='same',name=name)(net['conv14_2'])
net['conv14_2_mbox_conf'] = x
flatten = Flatten(name='conv14_2_mbox_conf_flat')
net['conv14_2_mbox_conf_flat'] = flatten(net['conv14_2_mbox_conf'])
priorbox = PriorBox(img_size, 150, max_size=195.0, aspect_ratios=[2, 3],variances=[0.1, 0.1, 0.2, 0.2],name='conv14_2_mbox_priorbox')
net['conv14_2_mbox_priorbox'] = priorbox(net['conv14_2'])
# Prediction from conv15_2_mbox
num_priors = 6
x = Conv2D(num_priors * 4, (1,1), padding='same',name='conv15_2_mbox_loc')(net['conv15_2'])
net['conv15_2_mbox_loc'] = x
flatten = Flatten(name='conv15_2_mbox_loc_flat')
net['conv15_2_mbox_loc_flat'] = flatten(net['conv15_2_mbox_loc'])
name = 'conv15_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (1,1), padding='same',name=name)(net['conv15_2'])
net['conv15_2_mbox_conf'] = x
flatten = Flatten(name='conv15_2_mbox_conf_flat')
net['conv15_2_mbox_conf_flat'] = flatten(net['conv15_2_mbox_conf'])
priorbox = PriorBox(img_size, 195.0, max_size=240.0, aspect_ratios=[2, 3],variances=[0.1, 0.1, 0.2, 0.2],name='conv15_2_mbox_priorbox')
net['conv15_2_mbox_priorbox'] = priorbox(net['conv15_2'])
# Prediction from conv16_2
num_priors = 6
x = Conv2D(num_priors * 4, (1,1), padding='same',name='conv16_2_mbox_loc')(net['conv16_2'])
net['conv16_2_mbox_loc'] = x
flatten = Flatten(name='conv16_2_mbox_loc_flat')
net['conv16_2_mbox_loc_flat'] = flatten(net['conv16_2_mbox_loc'])
name = 'conv16_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (1,1), padding='same',name=name)(net['conv16_2'])
net['conv16_2_mbox_conf'] = x
flatten = Flatten(name='conv16_2_mbox_conf_flat')
net['conv16_2_mbox_conf_flat'] = flatten(net['conv16_2_mbox_conf'])
priorbox = PriorBox(img_size, 240.0, max_size=285.0, aspect_ratios=[2, 3],variances=[0.1, 0.1, 0.2, 0.2],name='conv16_2_mbox_priorbox')
net['conv16_2_mbox_priorbox'] = priorbox(net['conv16_2'])
# Prediction from conv17_2
num_priors = 6
x = Conv2D(num_priors * 4,(1, 1), padding='same', name='conv17_2_mbox_loc')(net['conv17_2'])
net['conv17_2_mbox_loc'] = x
flatten = Flatten(name='conv17_2_mbox_loc_flat')
net['conv17_2_mbox_loc_flat'] = flatten(net['conv17_2_mbox_loc'])
name = 'conv17_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes, (1,1), padding='same', name=name)(net['conv17_2'])
net['conv17_2_mbox_conf'] = x
flatten = Flatten(name='conv17_2_mbox_conf_flat')
net['conv17_2_mbox_conf_flat'] = flatten(net['conv17_2_mbox_conf'])
priorbox = PriorBox(img_size, 285.0, max_size=300.0, aspect_ratios=[2, 3], variances=[0.1, 0.1, 0.2, 0.2],name='conv17_2_mbox_priorbox')
net['conv17_2_mbox_priorbox'] = priorbox(net['conv17_2'])
# Gather all predictions
net['mbox_loc'] = concatenate([net['conv11_mbox_loc_flat'],net['conv13_mbox_loc_flat'],net['conv14_2_mbox_loc_flat'],net['conv15_2_mbox_loc_flat'],net['conv16_2_mbox_loc_flat'],net['conv17_2_mbox_loc_flat']],axis=1, name='mbox_loc')
net['mbox_conf'] = concatenate([net['conv11_mbox_conf_flat'],net['conv13_mbox_conf_flat'],net['conv14_2_mbox_conf_flat'],net['conv15_2_mbox_conf_flat'],net['conv16_2_mbox_conf_flat'],net['conv17_2_mbox_conf_flat']],axis=1, name='mbox_conf')
net['mbox_priorbox'] = concatenate([net['conv11_mbox_priorbox'],net['conv13_mbox_priorbox'],net['conv14_2_mbox_priorbox'],net['conv15_2_mbox_priorbox'],net['conv16_2_mbox_priorbox'],net['conv17_2_mbox_priorbox']],axis=1,name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate([net['mbox_loc'],net['mbox_conf'],net['mbox_priorbox']],axis=2,name='predictions')
model = Model(net['input'], net['predictions'])
return model
def SSD300v2(input_shape, num_classes=21, featurte_map=None):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
input_layer = Input(shape=input_shape)
# Block 1
with tf.name_scope("Block1"):
conv1_1 = Conv2D(64, (3, 3),
name='conv1_1',
padding='same',
activation='relu')(input_layer)
conv1_2 = Conv2D(64, (3, 3),
name='conv1_2',
padding='same',
activation='relu')(conv1_1)
pool1 = MaxPooling2D(
name='pool1',
pool_size=(2, 2),
strides=(2, 2),
padding='same',
)(conv1_2)
# Block 2
with tf.name_scope("Block2"):
conv2_1 = Conv2D(128, (3, 3),
name='conv2_1',
padding='same',
activation='relu')(pool1)
conv2_2 = Conv2D(128, (3, 3),
name='conv2_2',
padding='same',
activation='relu')(conv2_1)
pool2 = MaxPooling2D(name='pool2',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv2_2)
# Block 3
with tf.name_scope("Block3"):
conv3_1 = Conv2D(256, (3, 3),
name='conv3_1',
padding='same',
activation='relu')(pool2)
conv3_2 = Conv2D(256, (3, 3),
name='conv3_2',
padding='same',
activation='relu')(conv3_1)
conv3_3 = Conv2D(256, (3, 3),
name='conv3_3',
padding='same',
activation='relu')(conv3_2)
pool3 = MaxPooling2D(name='pool3',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv3_3)
# Block 4
with tf.name_scope("Block4"):
conv4_1 = Conv2D(512, (3, 3),
name='conv4_1',
padding='same',
activation='relu')(pool3)
conv4_2 = Conv2D(512, (3, 3),
name='conv4_2',
padding='same',
activation='relu')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),
name='conv4_3',
padding='same',
activation='relu')(conv4_2)
pool4 = MaxPooling2D(name='pool4',
pool_size=(2, 2),
strides=(2, 2),
padding='same')(conv4_3)
# Block 5
with tf.name_scope("Block5"):
conv5_1 = Conv2D(512, (3, 3),
name='conv5_1',
padding='same',
activation='relu')(pool4)
conv5_2 = Conv2D(512, (3, 3),
name='conv5_2',
padding='same',
activation='relu')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
name='conv5_3',
padding='same',
activation='relu')(conv5_2)
pool5 = MaxPooling2D(name='pool5',
pool_size=(2, 2),
strides=(1, 1),
padding='same')(conv5_3)
# FC6
with tf.name_scope("fc6"):
fc6 = Conv2D(1024, (3, 3),
name='fc6',
dilation_rate=(6, 6),
padding='same',
activation='relu')(pool5)
# x = Dropout(0.5, name='drop6')(x)
# FC7
with tf.name_scope("fc7"):
fc7 = Conv2D(1024, (1, 1),
name='fc7',
padding='same',
activation='relu')(fc6)
# x = Dropout(0.5, name='drop7')(x)
# Block 6
with tf.name_scope("Block6"):
conv6_1 = Conv2D(256, (1, 1),
name='conv6_1',
padding='same',
activation='relu')(fc7)
conv6_2 = Conv2D(512, (3, 3),
name='conv6_2',
strides=(2, 2),
padding='same',
activation='relu')(conv6_1)
# Block 7
with tf.name_scope("Block7"):
conv7_1 = Conv2D(128, (1, 1),
name='conv7_1',
padding='same',
activation='relu')(conv6_2)
conv7_1z = ZeroPadding2D(name='conv7_1z')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
name='conv7_2',
padding='valid',
strides=(2, 2),
activation='relu')(conv7_1z)
# Block 8
with tf.name_scope("Block8"):
conv8_1 = Conv2D(128, (1, 1),
name='conv8_1',
padding='same',
activation='relu')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
name='conv8_2',
padding='same',
strides=(2, 2),
activation='relu')(conv8_1)
# Last Pool
with tf.name_scope("LastPool"):
pool6 = GlobalAveragePooling2D(name='pool6')(conv8_2)
# Prediction from conv4_3
num_priors = 3
img_size = (input_shape[1], input_shape[0])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
with tf.name_scope("conv4_3"):
conv4_3_norm = Normalize(20, name='conv4_3_norm')(conv4_3)
conv4_3_norm_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='conv4_3_norm_mbox_loc',
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_loc_flat = Flatten(
name='conv4_3_norm_mbox_loc_flat')(conv4_3_norm_mbox_loc)
conv4_3_norm_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
name=name,
padding='same')(conv4_3_norm)
conv4_3_norm_mbox_conf_flat = Flatten(
name='conv4_3_norm_mbox_conf_flat')(conv4_3_norm_mbox_conf)
conv4_3_norm_mbox_priorbox = PriorBox(
img_size,
30.0,
name='conv4_3_norm_mbox_priorbox',
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2])(conv4_3_norm)
# Prediction from fc7
num_priors = 6
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
with tf.name_scope("fc7"):
fc7_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(fc7)
fc7_mbox_conf_flat = Flatten(name='fc7_mbox_conf_flat')(fc7_mbox_conf)
fc7_mbox_loc = Conv2D(num_priors * 4, (3, 3),
name='fc7_mbox_loc',
padding='same')(fc7)
fc7_mbox_loc_flat = Flatten(name='fc7_mbox_loc_flat')(fc7_mbox_loc)
fc7_mbox_priorbox = PriorBox(img_size,
60.0,
name='fc7_mbox_priorbox',
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2])(fc7)
# Prediction from conv6_2
num_priors = 6
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
with tf.name_scope("conv6_2"):
conv6_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv6_2)
conv6_2_mbox_conf_flat = Flatten(
name='conv6_2_mbox_conf_flat')(conv6_2_mbox_conf)
conv6_2_mbox_loc = Conv2D(num_priors * 4, (
3,
3,
),
name='conv6_2_mbox_loc',
padding='same')(conv6_2)
conv6_2_mbox_loc_flat = Flatten(
name='conv6_2_mbox_loc_flat')(conv6_2_mbox_loc)
conv6_2_mbox_priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(conv6_2)
# Prediction from conv7_2
num_priors = 6
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
with tf.name_scope("conv7_2"):
conv7_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv7_2)
conv7_2_mbox_conf_flat = Flatten(
name='conv7_2_mbox_conf_flat')(conv7_2_mbox_conf)
conv7_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(conv7_2)
conv7_2_mbox_loc_flat = Flatten(
name='conv7_2_mbox_loc_flat')(conv7_2_mbox_loc)
conv7_2_mbox_priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(conv7_2)
# Prediction from conv8_2
num_priors = 6
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
with tf.name_scope("conv8_2"):
conv8_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv8_2)
conv8_2_mbox_conf_flat = Flatten(
name='conv8_2_mbox_conf_flat')(conv8_2_mbox_conf)
conv8_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(conv8_2)
conv8_2_mbox_loc_flat = Flatten(
name='conv8_2_mbox_loc_flat')(conv8_2_mbox_loc)
conv8_2_mbox_priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(conv8_2)
# Prediction from pool6
num_priors = 6
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
with tf.name_scope("pool6"):
pool6_mbox_loc_flat = Dense(num_priors * 4,
name='pool6_mbox_loc_flat')(pool6)
pool6_mbox_conf_flat = Dense(num_priors * num_classes,
name=name)(pool6)
pool6_reshaped = Reshape(target_shape, name='pool6_reshaped')(pool6)
pool6_mbox_priorbox = PriorBox(
img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(pool6_reshaped)
# Gather all predictions
with tf.name_scope("mbox"):
mbox_loc = concatenate([
conv4_3_norm_mbox_loc_flat, fc7_mbox_loc_flat,
conv6_2_mbox_loc_flat, conv7_2_mbox_loc_flat,
conv8_2_mbox_loc_flat, pool6_mbox_loc_flat
],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([
conv4_3_norm_mbox_conf_flat, fc7_mbox_conf_flat,
conv6_2_mbox_conf_flat, conv7_2_mbox_conf_flat,
conv8_2_mbox_conf_flat, pool6_mbox_conf_flat
],
axis=1,
name='mbox_conf')
mbox_priorbox = concatenate([
conv4_3_norm_mbox_priorbox, fc7_mbox_priorbox,
conv6_2_mbox_priorbox, conv7_2_mbox_priorbox,
conv8_2_mbox_priorbox, pool6_mbox_priorbox
],
axis=1,
name='mbox_priorbox')
print('{} conv4_3_norm_mbox_loc_flat'.format(
conv4_3_norm_mbox_loc_flat._keras_shape))
print('{} conv4_3_norm_mbox_conf_flat'.format(
conv4_3_norm_mbox_conf_flat._keras_shape))
print(
'{} conv4_3_norm_mbox_priorbox'.format(conv4_3_norm_mbox_priorbox))
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
print('{} num_boxes'.format(num_boxes))
print('{} mbox_loc'.format(mbox_loc._keras_shape))
print('{} mbox_conf'.format(mbox_conf._keras_shape))
mbox_loc = Reshape((num_boxes, 4), name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax', name='mbox_conf_final')(mbox_conf)
print('{} locatation'.format(mbox_loc))
print('{} conf'.format(mbox_conf))
print('{} priorbox'.format(mbox_priorbox))
if featurte_map == 'conv4_3_norm_mbox_loc_flat':
return set_return_model(input_layer=input_layer,
output_layer=conv4_3_norm_mbox_loc_flat)
elif featurte_map == 'fc7_mbox_loc_flat':
return set_return_model(input_layer=input_layer,
output_layer=fc7_mbox_loc_flat)
elif featurte_map == 'conv4_3_norm_mbox_conf_flat':
return set_return_model(input_layer=input_layer,
output_layer=conv4_3_norm_mbox_conf_flat)
elif featurte_map == 'fc7_mbox_conf_flat':
return set_return_model(input_layer=input_layer,
output_layer=fc7_mbox_conf_flat)
predictions = concatenate([mbox_loc, mbox_conf, mbox_priorbox],
axis=2,
name='predictions')
print('{} predictions'.format(predictions.shape))
print('{} predictions'.format(predictions))
model = Model(inputs=input_layer, outputs=predictions)
return model
def SSD512(input_shape, num_classes=21):
"""SSD512 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (512, 512, 3) or (3, 512, 512)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
border_mode='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
border_mode='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = AtrousConvolution2D(1024,
3,
3,
atrous_rate=(6, 6),
activation='relu',
border_mode='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024,
1,
1,
activation='relu',
border_mode='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256,
1,
1,
activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv8_2')(net['conv8_1'])
# Block 9
net['conv9_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv9_1')(net['conv8_2'])
net['conv9_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv9_2')(net['conv9_1'])
# Block 10
net['conv10_1'] = Convolution2D(128,
1,
1,
activation='relu',
border_mode='same',
name='conv10_1')(net['conv9_2'])
net['conv10_2'] = Convolution2D(256,
3,
3,
subsample=(2, 2),
activation='relu',
border_mode='same',
name='conv10_2')(net['conv10_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv10_2'])
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 4
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
35.84,
max_size=76.8,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
76.8,
max_size=153.6,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
153.6,
max_size=230.4,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
230.4,
max_size=307.2,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
307.2,
max_size=384.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from conv9_2
num_priors = 4
x = Convolution2D(num_priors * 4,
3,
3,
border_mode='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
flatten = Flatten(name='conv9_2_mbox_loc_flat')
net['conv9_2_mbox_loc_flat'] = flatten(net['conv9_2_mbox_loc'])
name = 'conv9_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes,
3,
3,
border_mode='same',
name=name)(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
flatten = Flatten(name='conv9_2_mbox_conf_flat')
net['conv9_2_mbox_conf_flat'] = flatten(net['conv9_2_mbox_conf'])
priorbox = PriorBox(img_size,
384.0,
max_size=460.8,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# Prediction from pool6
num_priors = 4
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
460.8,
max_size=537.6,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = merge([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']
],
mode='concat',
concat_axis=1,
name='mbox_loc')
net['mbox_conf'] = merge([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']
],
mode='concat',
concat_axis=1,
name='mbox_conf')
net['mbox_priorbox'] = merge([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox'],
net['pool6_mbox_priorbox']
],
mode='concat',
concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
mode='concat',
concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
return model
def SSD(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
input0 = input_tensor
conv1_1 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_1')(input0)
conv1_2 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_2')(conv1_1)
pool1 = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(conv1_2)
# Block 2
conv2_1 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_1')(pool1)
conv2_2 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_2')(conv2_1)
pool2 = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(conv2_2)
# Block 3
conv3_1 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_1')(pool2)
conv3_2 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_2')(conv3_1)
conv3_3 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_3')(conv3_2)
pool3 = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(conv3_3)
# Block 4
conv4_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_1')(pool3)
conv4_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_3')(conv4_2)
pool4 = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(conv4_3)
# Block 5
conv5_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_1')(pool4)
conv5_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_2')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_3')(conv5_2)
pool5 = MaxPooling2D((3, 3), strides=(1, 1), padding='same',
name='pool5')(conv5_3)
# FC6
fc6 = Conv2D(1024, (3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
name='fc6')(pool5)
#fc6 = Dropout(0.5, name='drop6')(fc6)
# FC7
fc7 = Conv2D(1024, (1, 1), activation='relu', padding='same',
name='fc7')(fc6)
#fc7 = Dropout(0.5, name='drop7')(fc7)
# Block 6
conv6_1 = Conv2D(256, (1, 1),
activation='relu',
padding='same',
name='conv6_1')(fc7)
conv6_2 = Conv2D(512, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv6_2')(conv6_1)
# Block 7
conv7_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='conv7_1')(conv6_2)
conv7_2 = ZeroPadding2D()(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
name='conv7_2')(conv7_2)
# Block 8
conv8_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
name='conv8_1')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv8_2')(conv8_1)
# Last Pool
pool6 = GlobalAveragePooling2D(name='pool6')(conv8_2)
# Prediction from conv4_3
conv4_3_norm = Normalize(num_classes - 1, name='conv4_3_norm')(conv4_3)
num_priors = 3
conv4_3_norm_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(conv4_3_norm)
conv4_3_norm_mbox_loc_flat = Flatten(
name='conv4_3_norm_mbox_loc_flat')(conv4_3_norm_mbox_loc)
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv4_3_norm_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv4_3_norm)
conv4_3_norm_mbox_conf_flat = Flatten(
name='conv4_3_norm_mbox_conf_flat')(conv4_3_norm_mbox_conf)
conv4_3_norm_mbox_priorbox = PriorBox(
img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')(conv4_3_norm)
# Prediction from fc7
num_priors = 6
fc7_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='fc7_mbox_loc')(fc7)
fc7_mbox_loc_flat = Flatten(name='fc7_mbox_loc_flat')(fc7_mbox_loc)
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
fc7_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(fc7)
fc7_mbox_conf_flat = Flatten(name='fc7_mbox_conf_flat')(fc7_mbox_conf)
fc7_mbox_priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')(fc7)
# Prediction from conv6_2
num_priors = 6
conv6_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv6_2_mbox_loc')(conv6_2)
conv6_2_mbox_loc_flat = Flatten(
name='conv6_2_mbox_loc_flat')(conv6_2_mbox_loc)
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv6_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv6_2)
conv6_2_mbox_conf_flat = Flatten(
name='conv6_2_mbox_conf_flat')(conv6_2_mbox_conf)
conv6_2_mbox_priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(conv6_2)
# Prediction from conv7_2
num_priors = 6
conv7_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(conv7_2)
conv7_2_mbox_loc_flat = Flatten(
name='conv7_2_mbox_loc_flat')(conv7_2_mbox_loc)
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv7_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv7_2)
conv7_2_mbox_conf_flat = Flatten(
name='conv7_2_mbox_conf_flat')(conv7_2_mbox_conf)
conv7_2_mbox_priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(conv7_2)
# Prediction from conv8_2
num_priors = 6
conv8_2_mbox_loc = Conv2D(num_priors * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(conv8_2)
conv8_2_mbox_loc_flat = Flatten(
name='conv8_2_mbox_loc_flat')(conv8_2_mbox_loc)
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
conv8_2_mbox_conf = Conv2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(conv8_2)
conv8_2_mbox_conf_flat = Flatten(
name='conv8_2_mbox_conf_flat')(conv8_2_mbox_conf)
conv8_2_mbox_priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(conv8_2)
# Prediction from pool6
num_priors = 6
pool6_mbox_loc_flat = Dense(num_priors * 4,
name='pool6_mbox_loc_flat')(pool6)
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
pool6_mbox_conf_flat = Dense(num_priors * num_classes, name=name)(pool6)
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
pool6_reshaped = Reshape(target_shape, name='pool6_reshaped')(pool6)
pool6_mbox_priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(pool6_reshaped)
# Gather all predictions
mbox_loc = concatenate([
conv4_3_norm_mbox_loc_flat, fc7_mbox_loc_flat, conv6_2_mbox_loc_flat,
conv7_2_mbox_loc_flat, conv8_2_mbox_loc_flat, pool6_mbox_loc_flat
],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([
conv4_3_norm_mbox_conf_flat, fc7_mbox_conf_flat,
conv6_2_mbox_conf_flat, conv7_2_mbox_conf_flat, conv8_2_mbox_conf_flat,
pool6_mbox_conf_flat
],
axis=1,
name='mbox_conf')
mbox_priorbox = concatenate([
conv4_3_norm_mbox_priorbox, fc7_mbox_priorbox, conv6_2_mbox_priorbox,
conv7_2_mbox_priorbox, conv8_2_mbox_priorbox, pool6_mbox_priorbox
],
axis=1,
name='mbox_priorbox')
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
mbox_loc = Reshape((num_boxes, 4), name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax', name='mbox_conf_final')(mbox_conf)
predictions = concatenate([mbox_loc, mbox_conf, mbox_priorbox],
axis=2,
name='predictions')
model = Model(input0, predictions)
return model
def SSD(input_shape, num_classes):
img_size = (input_shape[1], input_shape[0])
input_shape = (input_shape[1], input_shape[0], 3)
alpha = 1.0
depth_multiplier = 1
input0 = Input(input_shape)
x = _conv_block(input0, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(x,
128,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=2)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(x,
256,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(x,
512,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block_f(x,
depth_multiplier,
strides=(1, 1),
block_id=11)
x, conv11 = _conv_blockSSD_f(x,
512,
depth_multiplier,
kernel=(1, 1),
strides=(1, 1),
block_id=11)
x = _depthwise_conv_block(x,
512,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=12)
x = _depthwise_conv_block_f(x,
depth_multiplier,
strides=(1, 1),
block_id=13)
x, conv13 = _conv_blockSSD_f(x,
512,
alpha,
kernel=(1, 1),
strides=(1, 1),
block_id=13)
x, conv14_2 = _conv_blockSSD(x, 256, alpha, block_id=14)
x, conv15_2 = _conv_blockSSD(x, 128, alpha, block_id=15)
x, conv16_2 = _conv_blockSSD(x, 128, alpha, block_id=16)
x, conv17_2 = _conv_blockSSD(x, 64, alpha, block_id=17)
#Prediction from conv11
num_priors = 3
x = Conv2D(num_priors * 4, (1, 1), padding='same',
name='conv11_mbox_loc')(conv11)
conv11_mbox_loc = x
flatten = Flatten(name='conv11_mbox_loc_flat')
conv11_mbox_loc_flat = flatten(conv11_mbox_loc)
name = 'conv11_mbox_conf' # type: str
conv11_mbox_conf = Conv2D(num_priors * num_classes, (1, 1),
padding='same',
name=name)(conv11)
flatten = Flatten(name='conv11_mbox_conf_flat')
conv11_mbox_conf_flat = flatten(conv11_mbox_conf)
priorbox = PriorBox(img_size,
60,
max_size=None,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv11_mbox_priorbox')
conv11_mbox_priorbox = priorbox(conv11)
num_priors = 6
x = Conv2D(num_priors * 4, (1, 1), padding='same',
name='conv13_mbox_loc')(conv13)
conv13_mbox_loc = x
flatten = Flatten(name='conv13_mbox_loc_flat')
conv13_mbox_loc_flat = flatten(conv13_mbox_loc)
name = 'conv13_mbox_conf'
conv13_mbox_conf = Conv2D(num_priors * num_classes, (1, 1),
padding='same',
name=name)(conv13)
flatten = Flatten(name='conv13_mbox_conf_flat')
conv13_mbox_conf_flat = flatten(conv13_mbox_conf)
priorbox = PriorBox(img_size,
105.0,
max_size=150.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv13_mbox_priorbox')
conv13_mbox_priorbox = priorbox(conv13)
num_priors = 6
x = Conv2D(num_priors * 4, (1, 1),
padding='same',
name='conv14_2_mbox_loc')(conv14_2)
conv14_2_mbox_loc = x
flatten = Flatten(name='conv14_2_mbox_loc_flat')
conv14_2_mbox_loc_flat = flatten(conv14_2_mbox_loc)
name = 'conv14_2_mbox_conf'
x = Conv2D(num_priors * num_classes, (1, 1), padding='same',
name=name)(conv14_2)
conv14_2_mbox_conf = x
flatten = Flatten(name='conv14_2_mbox_conf_flat')
conv14_2_mbox_conf_flat = flatten(conv14_2_mbox_conf)
priorbox = PriorBox(img_size,
150,
max_size=195.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv14_2_mbox_priorbox')
conv14_2_mbox_priorbox = priorbox(conv14_2)
num_priors = 6
x = Conv2D(num_priors * 4, (1, 1),
padding='same',
name='conv15_2_mbox_loc')(conv15_2)
conv15_2_mbox_loc = x
flatten = Flatten(name='conv15_2_mbox_loc_flat')
conv15_2_mbox_loc_flat = flatten(conv15_2_mbox_loc)
name = 'conv15_2_mbox_conf'
x = Conv2D(num_priors * num_classes, (1, 1), padding='same',
name=name)(conv15_2)
conv15_2_mbox_conf = x
flatten = Flatten(name='conv15_2_mbox_conf_flat')
conv15_2_mbox_conf_flat = flatten(conv15_2_mbox_conf)
priorbox = PriorBox(img_size,
195.0,
max_size=240.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv15_2_mbox_priorbox')
conv15_2_mbox_priorbox = priorbox(conv15_2)
num_priors = 6
x = Conv2D(num_priors * 4, (1, 1),
padding='same',
name='conv16_2_mbox_loc')(conv16_2)
conv16_2_mbox_loc = x
flatten = Flatten(name='conv16_2_mbox_loc_flat')
conv16_2_mbox_loc_flat = flatten(conv16_2_mbox_loc)
name = 'conv16_2_mbox_conf'
x = Conv2D(num_priors * num_classes, (1, 1), padding='same',
name=name)(conv16_2)
conv16_2_mbox_conf = x
flatten = Flatten(name='conv16_2_mbox_conf_flat')
conv16_2_mbox_conf_flat = flatten(conv16_2_mbox_conf)
priorbox = PriorBox(img_size,
240.0,
max_size=285.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv16_2_mbox_priorbox')
conv16_2_mbox_priorbox = priorbox(conv16_2)
num_priors = 6
x = Conv2D(num_priors * 4, (1, 1),
padding='same',
name='conv17_2_mbox_loc')(conv17_2)
conv17_2_mbox_loc = x
flatten = Flatten(name='conv17_2_mbox_loc_flat')
conv17_2_mbox_loc_flat = flatten(conv17_2_mbox_loc)
name = 'conv17_2_mbox_conf'
x = Conv2D(num_priors * num_classes, (1, 1), padding='same',
name=name)(conv17_2)
conv17_2_mbox_conf = x
flatten = Flatten(name='conv17_2_mbox_conf_flat')
conv17_2_mbox_conf_flat = flatten(conv17_2_mbox_conf)
priorbox = PriorBox(img_size,
285.0,
max_size=300.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv17_2_mbox_priorbox')
conv17_2_mbox_priorbox = priorbox(conv17_2)
mbox_loc = concatenate([
conv11_mbox_loc_flat, conv13_mbox_loc_flat, conv14_2_mbox_loc_flat,
conv15_2_mbox_loc_flat, conv16_2_mbox_loc_flat, conv17_2_mbox_loc_flat
],
axis=1,
name='mbox_loc')
mbox_conf = concatenate([
conv11_mbox_conf_flat, conv13_mbox_conf_flat, conv14_2_mbox_conf_flat,
conv15_2_mbox_conf_flat, conv16_2_mbox_conf_flat,
conv17_2_mbox_conf_flat
],
axis=1,
name='mbox_conf')
mbox_priorbox = concatenate([
conv11_mbox_priorbox, conv13_mbox_priorbox, conv14_2_mbox_priorbox,
conv15_2_mbox_priorbox, conv16_2_mbox_priorbox, conv17_2_mbox_priorbox
],
axis=1,
name='mbox_priorbox')
if hasattr(mbox_loc, '_keras_shape'):
num_boxes = mbox_loc._keras_shape[-1] // 4
elif hasattr(mbox_loc, 'int_shape'):
num_boxes = K.int_shape(mbox_loc)[-1] // 4
mbox_loc = Reshape((num_boxes, 4), name='mbox_loc_final')(mbox_loc)
mbox_conf = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(mbox_conf)
mbox_conf = Activation('softmax', name='mbox_conf_final')(mbox_conf)
predictions = concatenate([mbox_loc, mbox_conf, mbox_priorbox],
axis=2,
name='predictions')
model = Model(inputs=input0, outputs=predictions)
return model
def SSD300(input_shape=(300, 300, 3), num_classes=21):
net = {}
net['inputs'] = Input(shape=input_shape, name='inputs')
net['conv1_1_zp'] = ZeroPadding2D(padding=(1, 1), name='conv1_1_zp')(net['inputs'])
net['conv1_1'] = Conv2D(64, (3, 3), activation='relu', strides=(1, 1), name='conv1_1')(net['conv1_1_zp'])
net['conv1_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv1_2_zp')(net['conv1_1'])
net['conv1_2'] = Conv2D(64, (3, 3), activation='relu', strides=(1, 1), name='conv1_2')(net['conv1_2_zp'])
net['pool1'] = MaxPool2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(net['conv1_2'])
net['conv2_1_zp'] = ZeroPadding2D(padding=(1, 1), name='conv2_1_zp')(net['pool1'])
net['conv2_1'] = Conv2D(128, (3, 3), activation='relu', strides=(1, 1), name='conv2_1')(net['conv2_1_zp'])
net['conv2_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv2_2_zp')(net['conv2_1'])
net['conv2_2'] = Conv2D(128, (3, 3), activation='relu', strides=(1, 1), name='conv2_2')(net['conv2_2_zp'])
net['pool2'] = MaxPool2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(net['conv2_2'])
net['conv3_1_zp'] = ZeroPadding2D(padding=(1, 1), name='conv3_1_zp')(net['pool2'])
net['conv3_1'] = Conv2D(256, (3, 3), activation='relu', strides=(1, 1), name='conv3_1')(net['conv3_1_zp'])
net['conv3_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv3_2_zp')(net['conv3_1'])
net['conv3_2'] = Conv2D(256, (3, 3), activation='relu', strides=(1, 1), name='conv3_2')(net['conv3_2_zp'])
net['conv3_3_zp'] = ZeroPadding2D(padding=(1, 1), name='conv3_3_zp')(net['conv3_2'])
net['conv3_3'] = Conv2D(256, (3, 3), activation='relu', strides=(1, 1), name='conv3_3')(net['conv3_3_zp'])
net['pool3'] = MaxPool2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool3')(net['conv3_3'])
net['conv4_1_zp'] = ZeroPadding2D(padding=(1, 1), name='conv4_1_zp')(net['pool3'])
net['conv4_1'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv4_1')(net['conv4_1_zp'])
net['conv4_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv4_2_zp')(net['conv4_1'])
net['conv4_2'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv4_2')(net['conv4_2_zp'])
net['conv4_3_zp'] = ZeroPadding2D(padding=(1, 1), name='conv4_3_zp')(net['conv4_2'])
net['conv4_3'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv4_3')(net['conv4_3_zp'])
net['pool4'] = MaxPool2D(pool_size=(2, 2), strides=(2, 2), name='pool4')(net['conv4_3'])
net['conv5_1_zp'] = ZeroPadding2D(padding=(1, 1), name='conv5_1_zp')(net['pool4'])
net['conv5_1'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv5_1')(net['conv5_1_zp'])
net['conv5_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv5_2_zp')(net['conv5_1'])
net['conv5_2'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv5_2')(net['conv5_2_zp'])
net['conv5_3_zp'] = ZeroPadding2D(padding=(1, 1), name='conv5_3_zp')(net['conv5_2'])
net['conv5_3'] = Conv2D(512, (3, 3), activation='relu', strides=(1, 1), name='conv5_3')(net['conv5_3_zp'])
net['pool5_zp'] = ZeroPadding2D(padding=(1, 1), name='pool5_zp')(net['conv5_3'])
net['pool5'] = MaxPool2D(pool_size=(3, 3), strides=(1, 1), name='pool5')(net['pool5_zp'])
net['fc6_zp'] = ZeroPadding2D(padding=(6, 6), name='fc6_zp')(net['pool5'])
net['fc6'] = Conv2D(1024, (3, 3), activation='relu', strides=(1, 1), dilation_rate=(6, 6), name='fc6')(net['fc6_zp'])
net['fc7'] = Conv2D(1024, (1, 1), activation='relu', strides=(1, 1), name='fc7')(net['fc6'])
net['conv6_1'] = Conv2D(256, (1, 1), activation='relu', strides=(1, 1), name='conv6_1')(net['fc7'])
net['conv6_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv6_2_zp')(net['conv6_1'])
net['conv6_2'] = Conv2D(512, (3, 3), activation='relu', strides=(2, 2), name='conv6_2')(net['conv6_2_zp'])
net['conv7_1'] = Conv2D(128, (1, 1), activation='relu', strides=(1, 1), name='conv7_1')(net['conv6_2'])
net['conv7_2_zp'] = ZeroPadding2D(padding=(1, 1), name='conv7_2_zp')(net['conv7_1'])
net['conv7_2'] = Conv2D(256, (3, 3), activation='relu', strides=(2, 2), name='conv7_2')(net['conv7_2_zp'])
net['conv8_1'] = Conv2D(128, (1, 1), activation='relu', strides=(1, 1), name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Conv2D(256, (3, 3), activation='relu', strides=(1, 1), name='conv8_2')(net['conv8_1'])
net['conv9_1'] = Conv2D(128, (1, 1), activation='relu', strides=(1, 1), name='conv9_1')(net['conv8_2'])
net['conv9_2'] = Conv2D(256, (3, 3), activation='relu', strides=(1, 1), name='conv9_2')(net['conv9_1'])
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 4
net['conv4_3_norm_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='conv4_3_norm_mbox_loc_zp')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv4_3_norm_mbox_loc')(net['conv4_3_norm_mbox_loc_zp'])
net['conv4_3_norm_mbox_loc_flat'] = Flatten(name='conv4_3_norm_mbox_loc_flat')(net['conv4_3_norm_mbox_loc'])
net['conv4_3_norm_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='conv4_3_norm_mbox_conf_zp')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv4_3_norm_mbox_conf')(net['conv4_3_norm_mbox_conf_zp'])
net['conv4_3_norm_mbox_conf_flat'] = Flatten(name='conv4_3_norm_mbox_conf_flat')(net['conv4_3_norm_mbox_conf'])
net['conv4_3_norm_mbox_priorbox'] = PriorBox((300, 300), min_size=30.0, max_size=60.0,
aspect_ratios=[2.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='conv4_3_norm_mbox_priorbox')(net['conv4_3_norm'])
num_priors = 6
net['fc7_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='fc7_mbox_loc_zp')(net['fc7'])
net['fc7_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='fc7_mbox_loc')(net['fc7_mbox_loc_zp'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(net['fc7_mbox_loc'])
net['fc7_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='fc7_mbox_conf_zp')(net['fc7'])
net['fc7_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='fc7_mbox_conf')(net['fc7_mbox_conf_zp'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(net['fc7_mbox_conf'])
net['fc7_mbox_priorbox'] = PriorBox((300, 300), min_size=60.0, max_size=111.0,
aspect_ratios=[2.0, 3.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='fc7_mbox_priorbox')(net['fc7'])
net['conv6_2_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='conv6_2_mbox_loc_zp')(net['conv6_2'])
net['conv6_2_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv6_2_mbox_loc')(net['conv6_2_mbox_loc_zp'])
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(net['conv6_2_mbox_loc'])
net['conv6_2_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='conv6_2_mbox_conf_zp')(net['conv6_2'])
net['conv6_2_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv6_2_mbox_conf')(net['conv6_2_mbox_conf_zp'])
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(net['conv6_2_mbox_conf'])
net['conv6_2_mbox_priorbox'] = PriorBox((300, 300), min_size=111.0, max_size=162.0,
aspect_ratios=[2.0, 3.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='conv6_2_mbox_priorbox')(net['conv6_2'])
net['conv7_2_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='conv7_2_mbox_loc_zp')(net['conv7_2'])
net['conv7_2_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv7_2_mbox_loc')(net['conv7_2_mbox_loc_zp'])
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(net['conv7_2_mbox_loc'])
net['conv7_2_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='conv7_2_mbox_conf_zp')(net['conv7_2'])
net['conv7_2_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv7_2_mbox_conf')(net['conv7_2_mbox_conf_zp'])
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(net['conv7_2_mbox_conf'])
net['conv7_2_mbox_priorbox'] = PriorBox((300, 300), min_size=162.0, max_size=213.0,
aspect_ratios=[2.0, 3.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='conv7_2_mbox_priorbox')(net['conv7_2'])
num_priors = 4
net['conv8_2_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='conv8_2_mbox_loc_zp')(net['conv8_2'])
net['conv8_2_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv8_2_mbox_loc')(net['conv8_2_mbox_loc_zp'])
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(net['conv8_2_mbox_loc'])
net['conv8_2_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='conv8_2_mbox_conf_zp')(net['conv8_2'])
net['conv8_2_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv8_2_mbox_conf')(net['conv8_2_mbox_conf_zp'])
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(net['conv8_2_mbox_conf'])
net['conv8_2_mbox_priorbox'] = PriorBox((300, 300), min_size=213.0, max_size=264.0,
aspect_ratios=[2.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='conv8_2_mbox_priorbox')(net['conv8_2'])
net['conv9_2_mbox_loc_zp'] = ZeroPadding2D(padding=(1, 1), name='conv9_2_mbox_loc_zp')(net['conv9_2'])
net['conv9_2_mbox_loc'] = Conv2D(4 * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv9_2_mbox_loc')(net['conv9_2_mbox_loc_zp'])
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(net['conv9_2_mbox_loc'])
net['conv9_2_mbox_conf_zp'] = ZeroPadding2D(padding=(1, 1), name='conv9_2_mbox_conf_zp')(net['conv9_2'])
net['conv9_2_mbox_conf'] = Conv2D(num_classes * num_priors, (3, 3), activation='relu', strides=(1, 1), name='conv9_2_mbox_conf')(net['conv9_2_mbox_conf_zp'])
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(net['conv9_2_mbox_conf'])
net['conv9_2_mbox_priorbox'] = PriorBox((300, 300), min_size=264.0, max_size=315.0,
aspect_ratios=[2.0], variances=[0.10, 0.10, 0.20, 0.20],
flip=True, clip=False, name='conv9_2_mbox_priorbox')(net['conv9_2'])
net['mbox_loc'] = concatenate(inputs=[net['conv4_3_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'],
net['conv9_2_mbox_loc_flat']], axis=1, name='mbox_loc')
net['mbox_conf'] = concatenate(inputs=[net['conv4_3_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'],
net['conv9_2_mbox_conf_flat']], axis=1, name='mbox_conf')
net['mbox_priorbox'] = concatenate(inputs=[net['conv4_3_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'],
net['conv9_2_mbox_priorbox']], axis=1, name='mbox_priorbox')
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
net['mbox_conf_reshape'] = Reshape(target_shape=(num_boxes, num_classes), name='mbox_conf_reshape')(net['mbox_conf'])
net['mbox_conf_softmax'] = Activation('softmax', name='mbox_conf_softmax')(net['mbox_conf_reshape'])
net['mbox_loc_reshape'] = Reshape(target_shape=(num_boxes, 4), name='mbox_loc_reshape')(net['mbox_loc'])
net['detection_out'] = concatenate(inputs=[net['mbox_loc_reshape'],
net['mbox_conf_softmax'],
net['mbox_priorbox']], axis=2, name='detection_out')
model = Model(net['inputs'], net['detection_out'])
return model
def SSD300(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Conv2D(64,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Conv2D(64,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Conv2D(128,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Conv2D(128,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Conv2D(256,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Conv2D(256,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Conv2D(256,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Conv2D(512,
kernel_size=(3, 3),
activation='relu',
padding='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = Conv2D(1024,
kernel_size=(3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Conv2D(1024,
kernel_size=(1, 1),
activation='relu',
padding='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Conv2D(256,
kernel_size=(1, 1),
activation='relu',
padding='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Conv2D(512,
kernel_size=(3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Conv2D(128,
kernel_size=(1, 1),
activation='relu',
padding='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Conv2D(256,
kernel_size=(3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Conv2D(128,
kernel_size=(1, 1),
activation='relu',
padding='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Conv2D(256,
kernel_size=(3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
if K.image_data_format() == 'channels_last':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = concatenate([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
model = Model(inputs=(net['input'], ), outputs=(net['predictions'], ))
return model
def ssd_prior_box_layer(img_size, conv4_3_norm, fc7, conv6_2, conv7_2, conv8_2,
pool6):
# conv4_3
conv4_3_norm_mbox_priorbox = PriorBox(img_size,
30.0,
name='conv4_3_norm_mbox_priorbox',
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2,
0.2])(conv4_3_norm)
# fc7
fc7_mbox_priorbox = PriorBox(img_size,
60.0,
name='fc7_mbox_priorbox',
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2])(fc7)
# conv6_2
conv6_2_mbox_priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')(conv6_2)
# conv7_2
conv7_2_mbox_priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')(conv7_2)
# conv8_2
conv8_2_mbox_priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')(conv8_2)
# pool6
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
pool6_reshaped = Reshape(target_shape, name='pool6_reshaped')(pool6)
pool6_mbox_priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')(pool6_reshaped)
return concatenate([
conv4_3_norm_mbox_priorbox, fc7_mbox_priorbox, conv6_2_mbox_priorbox,
conv7_2_mbox_priorbox, conv8_2_mbox_priorbox, pool6_mbox_priorbox
],
axis=1,
name='mbox_priorbox')