def model(dataset, l2_reg=5e-4, init='he_normal'):
if dataset in ['cifar10', 'cifar100', 'svhn']:
x = Input((32, 32, 3))
else:
raise ValueError('Model is not defined for dataset: %s' % dataset)
# Input size is 32x32
o = conv_bn_relu(x, 64, l2_reg, init=init, name='block1_conv1')
o = Dropout(0.3)(o)
o = conv_bn_relu(o, 64, l2_reg, init=init, name='block1_conv2')
o = MaxPooling2D()(o)
# Input size is 16x16
o = conv_bn_relu(o, 128, l2_reg, init=init, name='block2_conv1')
o = Dropout(0.4)(o)
o = conv_bn_relu(o, 128, l2_reg, init=init, name='block2_conv2')
o = MaxPooling2D()(o)
# Input size is 8x8
o = conv_bn_relu(o, 256, l2_reg, init=init, name='block3_conv1')
o = Dropout(0.4)(o)
o = conv_bn_relu(o, 256, l2_reg, init=init, name='block3_conv2')
o = Dropout(0.4)(o)
o = conv_bn_relu(o, 256, l2_reg, init=init, name='block3_conv3')
o = MaxPooling2D()(o)
# Input size is 4x4
o = conv_bn_relu(o, 512, l2_reg, init=init, name='block4_conv1')
o = Dropout(0.4)(o)
o = conv_bn_relu(o, 512, l2_reg, init=init, name='block4_conv2')
o = Dropout(0.4)(o)
o = conv_bn_relu(o, 512, l2_reg, init=init, name='block4_conv3')
o = MaxPooling2D()(o)
# Input size is 2x2
# Manually pad the image to 4x4 and use VALID padding to get it back to 2x2
o = ZeroPadding2D(padding=(1, 1))(o)
o = conv_bn_relu(o,
512,
l2_reg,
init=init,
name='block5_conv1',
border_mode='valid')
o = Dropout(0.4)(o)
o = ZeroPadding2D(padding=(1, 1))(o)
o = conv_bn_relu(o,
512,
l2_reg,
init=init,
name='block5_conv2',
border_mode='valid')
o = Dropout(0.4)(o)
o = ZeroPadding2D(padding=(1, 1))(o)
o = conv_bn_relu(o,
512,
l2_reg,
init=init,
name='block5_conv3',
border_mode='valid')
o = MaxPooling2D()(o)
# Input size is 1x1
o = Flatten()(o)
# Classifier
o = Dropout(0.5)(o)
o = Dense(512)(o)
o = BatchNormalization()(o)
o = Activation('relu')(o)
o = Dropout(0.5)(o)
if dataset in ['cifar10', 'svhn']:
output_size = 10
elif dataset == 'cifar100':
output_size = 100
o = Dense(output_size)(o)
o = Activation('softmax')(o)
return Model(input=x, output=o)
def __init__(self, load_encodings=1):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(224,224, 3)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Conv2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Conv2D(4096, (7, 7), activation='relu'))
model.add(Dropout(0.5))
model.add(Conv2D(4096, (1, 1), activation='relu'))
model.add(Dropout(0.5))
model.add(Conv2D(2622, (1, 1)))
model.add(Flatten())
model.add(Activation('softmax'))
model.load_weights("vgg_face_weights.h5")
"""Here we load all the encodings from the file where the created encodings are kept.
But if the load_encodings parameter is manually kept 0 the program doesn't load the encodings.
This can be done if you simply want to compare two images using the get_values and get_sim functions.
We load this now on the creation of object so less time is consumed when recognizing"""
self.__vggNet = Model(inputs = model.layers[0].input, outputs = model.layers[-2].output)
self.load_encodings = load_encodings
if load_encodings == 1:
if os.path.exists("encodings.pk"):
file = open("encodings.pk", "rb")
self.encodings_from_file = pickle.load(file)
file.close
self.scores = {}
for x in self.encodings_from_file:
self.scores[x] = 0
else:
print("Couldn't find encodings please create using the create_encodings function.")
def vgg_face(weights_path=None):
img = Input(shape=(3, 224, 224))
pad1_1 = ZeroPadding2D(padding=(1, 1))(img)
conv1_1 = Convolution2D(64, 3, 3, activation='relu',
name='conv1_1')(pad1_1)
pad1_2 = ZeroPadding2D(padding=(1, 1))(conv1_1)
conv1_2 = Convolution2D(64, 3, 3, activation='relu',
name='conv1_2')(pad1_2)
pool1 = MaxPooling2D((2, 2), strides=(2, 2))(conv1_2)
pad2_1 = ZeroPadding2D((1, 1))(pool1)
conv2_1 = Convolution2D(128, 3, 3, activation='relu',
name='conv2_1')(pad2_1)
pad2_2 = ZeroPadding2D((1, 1))(conv2_1)
conv2_2 = Convolution2D(128, 3, 3, activation='relu',
name='conv2_2')(pad2_2)
pool2 = MaxPooling2D((2, 2), strides=(2, 2))(conv2_2)
pad3_1 = ZeroPadding2D((1, 1))(pool2)
conv3_1 = Convolution2D(256, 3, 3, activation='relu',
name='conv3_1')(pad3_1)
pad3_2 = ZeroPadding2D((1, 1))(conv3_1)
conv3_2 = Convolution2D(256, 3, 3, activation='relu',
name='conv3_2')(pad3_2)
pad3_3 = ZeroPadding2D((1, 1))(conv3_2)
conv3_3 = Convolution2D(256, 3, 3, activation='relu',
name='conv3_3')(pad3_3)
pool3 = MaxPooling2D((2, 2), strides=(2, 2))(conv3_3)
pad4_1 = ZeroPadding2D((1, 1))(pool3)
conv4_1 = Convolution2D(512, 3, 3, activation='relu',
name='conv4_1')(pad4_1)
pad4_2 = ZeroPadding2D((1, 1))(conv4_1)
conv4_2 = Convolution2D(512, 3, 3, activation='relu',
name='conv4_2')(pad4_2)
pad4_3 = ZeroPadding2D((1, 1))(conv4_2)
conv4_3 = Convolution2D(512, 3, 3, activation='relu',
name='conv4_3')(pad4_3)
pool4 = MaxPooling2D((2, 2), strides=(2, 2))(conv4_3)
pad5_1 = ZeroPadding2D((1, 1))(pool4)
conv5_1 = Convolution2D(512, 3, 3, activation='relu',
name='conv5_1')(pad5_1)
pad5_2 = ZeroPadding2D((1, 1))(conv5_1)
conv5_2 = Convolution2D(512, 3, 3, activation='relu',
name='conv5_2')(pad5_2)
pad5_3 = ZeroPadding2D((1, 1))(conv5_2)
conv5_3 = Convolution2D(512, 3, 3, activation='relu',
name='conv5_3')(pad5_3)
pool5 = MaxPooling2D((2, 2), strides=(2, 2))(conv5_3)
flat = Flatten()(pool5)
fc6 = Dense(4096, activation='relu', name='fc6')(flat)
fc6_drop = Dropout(0.5)(fc6)
fc7 = Dense(4096, activation='relu', name='fc7')(fc6_drop)
fc7_drop = Dropout(0.5)(fc7)
out = Dense(2622, activation='softmax', name='fc8')(fc7_drop)
model = Model(input=img, output=out)
if weights_path:
model.load_weights(weights_path)
return model
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained on ImageNet. Note that when using
Tensorflow, for best performance you should set
'image_data_format='channels_last'' in your Keras config at
~/.keras/keras.json
The model and the weights are compatible with both TensorFlow an Theano.
The data format convention used by the model is the one specified in
your Keras config file.
# Arguments
include_top: whether to include the fully-connected layer
at the top of the network
weights: one of 'None' (random initialization) or 'imagenet'
(pre-training on ImageNet)
input_tensor: optional Keras tensor (i.e. output of 'layers.Input()')
to use as image input for the model
input_shape: optional shape tuple, only to be specified if
'include_top' is false (otherwise the input shape has to be
'(224,224, 3)' (with 'channels_last' data format)
or (3, 224, 224) ( with 'channels_first' data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197
E.g. (200, 200, 3) would be one valid value
pooling: Optional pooling mode for feature extraction when
'include_top' is 'False'.
- 'None' means that the output of the model will be the
4D tensor output of the last convolutional layer
- 'avg' means that global average pooling will be applied
to the output of the last convolutional layer, and thus
the output of the model will be a 2D tensor
- 'max' means that global max pooling will be applied
classes: optional number of classes to classify images into,
only to be specified if 'include_top' is True, and if no
'weights' argument is specified.
# Returns
A Keras model instance
# Raises
ValueError: in case of invalid argument for 'weights',
or invalid input shape
"""
if weights not in {'imagenet', None}:
raise ValueError(
'The weights argument should be either '
'None (random initilization) or imagenet (pre-training on ImageNet).'
)
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using weights as imagenet with include_top as true, '
'classes should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=False)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of 'input_tensor'
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='resnet50')
def MobileNetV2(input_shape=None,
alpha=1.0,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
num_classes=1000,
**kwargs):
# Instantiate the MobileNetV2 architecture.
"""
# Arguments
input_shape: optional tuple such as (224, 224, 3) or infer input_shape from
an input_tensor; If selecting include both input_tensor and input_shape,
input_shape will be used if matching or throwing an error.
alpha: controls the width of the network.
- If `alpha` < 1.0, proportionally decreases filters # in each layer.
- If `alpha` > 1.0, proportionally increases filters # in each layer.
- If `alpha` = 1, default filters # from the paper used at each layer.
include_top: whether to include the FC layer at the top of the network.
weights: `None` (random initialization)or 'imagenet'.
input_tensor: optional Keras tensor (output of `layers.Input()`)
pooling: Optional mode for feature extraction when `include_top` is `False`.
- `None`: the output of model is the 4D tensor of the last conv layer
- `avg` means global average pooling and the output as a 2D tensor.
- `max` means global max pooling will be applied.
num_classes: specified if `include_top` is True
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights` or invalid input shape.
RuntimeError: run the model with a backend without support separable conv.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either `None` '
'(random initialization) or `imagenet` or the'
'path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and num_classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top` '
'as true, `num_classes` should be 1000')
# Determine the proper input shape/default size if both input_shape and input_tensor
# are used while being matched.
if input_shape is not None and input_tensor is not None:
try:
is_input_t_tensor = K.is_keras_tensor(input_tensor)
except ValueError:
try:
is_input_t_tensor = K.is_keras_tensor(
get_source_inputs(input_tensor))
except ValueError:
raise ValueError('input_tensor: ', input_tensor,
'is not type input_tensor')
if is_input_t_tensor:
if K.image_data_format == 'channels_last':
if K.int_shape(input_tensor)[2] != input_shape[1]:
raise ValueError(
'input_shape: ', input_shape, 'and input_tensor: ',
input_tensor,
'do not meet the same shape requirements')
else:
if K.int_shape(input_tensor)[1] != input_shape[1]:
raise ValueError(
'input_shape: ', input_shape, 'and input_tensor: ',
input_tensor,
'do not meet the same shape requirements')
else:
raise ValueError('input_tensor specified: ', input_tensor,
'is not a keras tensor')
# Infer the shape from input_tensor if input_shape as None
if input_shape is None and input_tensor is not None:
try:
K.is_keras_tensor(input_tensor)
except ValueError:
raise ValueError('input_tensor: ', input_tensor, 'is type: ',
type(input_tensor), 'which is not a valid type')
if input_shape is None and not K.is_keras_tensor(input_tensor):
default_size = 224
elif input_shape is None and K.is_keras_tensor(input_tensor):
if K.image_data_format() == 'channels_last':
rows = K.int_shape(input_tensor)[1]
cols = K.int_shape(input_tensor)[2]
else:
rows = K.int_shape(input_tensor)[2]
cols = K.int_shape(input_tensor)[3]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
# If input_shape is None and no input_tensor
elif input_shape is None:
default_size = 224
# Assume the default size if input_shape as not None
else:
if K.image_data_format() == 'channels_last':
rows = input_shape[0]
cols = input_shape[1]
else:
rows = input_shape[1]
cols = input_shape[2]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = _obtain_input_shape(input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if K.image_data_format() == 'channels_last':
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if weights == 'imagenet':
if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of `0.35`, `0.50`, `0.75`, '
'`1.0`, `1.3` or `1.4` only.')
if rows != cols or rows not in [96, 128, 160, 192, 224]:
rows = 224
warnings.warn('`input_shape` is undefined or non-square, '
'or `rows` is not in [96, 128, 160, 192, 224].'
' Weights for input shape (224, 224) will be'
' loaded as the default.')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
channel_axis = -1 if K.image_data_format() == 'channels_last' else 1
first_block_filters = _make_divisible(32 * alpha, 8)
# Call the function of correct_pad()
x = ZeroPadding2D(padding=correct_pad(K, img_input, 3),
name='Conv1_pad')(img_input)
x = Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='valid',
use_bias=False,
name='Conv1')(x)
x = BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='bn_Conv1')(x)
x = ReLU(6., name='Conv1_relu')(x)
x = _inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=2,
expansion=6,
block_id=1)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=1,
expansion=6,
block_id=2)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=2,
expansion=6,
block_id=3)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=4)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=5)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=2,
expansion=6,
block_id=6)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=7)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=8)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=9)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=10)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=11)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=12)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=2,
expansion=6,
block_id=13)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=14)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=15)
x = _inverted_res_block(x,
filters=320,
alpha=alpha,
stride=1,
expansion=6,
block_id=16)
# Increase the output channels # if the width multiplier > 1.0
if alpha > 1.0: # No alpha applied to last conv as stated in the paper:
last_block_filters = _make_divisible(1280 * alpha, 8)
else:
last_block_filters = 1280
x = Conv2D(last_block_filters,
kernel_size=1,
use_bias=False,
name='Conv_1')(x)
x = BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='Conv_1_bn')(x)
x = ReLU(6., name='out_relu')(x)
if include_top:
x = GlobalAveragePooling2D()(x)
x = Dense(num_classes,
activation='softmax',
use_bias=True,
name='Logits')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure the model considers any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Build the model.
model = Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows))
# Load the weights.
if weights == 'imagenet':
if include_top:
model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '.h5')
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weight_path,
cache_subdir='models')
else:
model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
str(alpha) + '_' + str(rows) + '_no_top' + '.h5')
weight_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weight_path,
cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
VGG16_weights_path = '/home/pablo/Documents/VGG16/vgg16_weights.h5' top_model_weights_path = 'bottleneck_top_model.h5' # dimensions of our images. img_width, img_height = 150, 150 # train_data_dir = 'data/train' # validation_data_dir = 'data/validation' test_data_dir = '/home/pablo/Documents/Git_repositories/data_examples/DogsVsCats/data/test_small' # nb_train_samples = 2000 # nb_validation_samples = 800 nb_predict_samples = len(os.listdir(os.path.join(test_data_dir, 'test'))) # nb_epoch = 50 # build the VGG16 network model = Sequential() model.add(ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height))) model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1')) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2')) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1')) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2')) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1')) model.add(ZeroPadding2D((1, 1)))
def faceRecoModel(input_shape):
"""
Implementation of the Inception model used for FaceNet
Arguments:
input_shape -- shape of the images of the dataset
Returns:
model -- a Model() instance in Keras
"""
# Define the input as a tensor with shape input_shape
X_input = Input(input_shape)
# Zero-Padding
X = ZeroPadding2D((3, 3))(X_input)
# First Block
X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(X)
X = BatchNormalization(axis=1, name='bn1')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
X = MaxPooling2D((3, 3), strides=2)(X)
# Second Block
X = Conv2D(64, (1, 1), strides=(1, 1), name='conv2')(X)
X = BatchNormalization(axis=1, epsilon=0.00001, name='bn2')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
# Second Block
X = Conv2D(192, (3, 3), strides=(1, 1), name='conv3')(X)
X = BatchNormalization(axis=1, epsilon=0.00001, name='bn3')(X)
X = Activation('relu')(X)
# Zero-Padding + MAXPOOL
X = ZeroPadding2D((1, 1))(X)
X = MaxPooling2D(pool_size=3, strides=2)(X)
# Inception 1: a/b/c
X = inception_block_1a(X)
X = inception_block_1b(X)
X = inception_block_1c(X)
# Inception 2: a/b
X = inception_block_2a(X)
X = inception_block_2b(X)
# Inception 3: a/b
X = inception_block_3a(X)
X = inception_block_3b(X)
# Top layer
X = AveragePooling2D(pool_size=(3, 3),
strides=(1, 1),
data_format='channels_first')(X)
X = Flatten()(X)
X = Dense(128, name='dense_layer')(X)
# L2 normalization
X = Lambda(lambda x: K.l2_normalize(x, axis=1))(X)
# Create model instance
model = Model(inputs=X_input, outputs=X, name='FaceRecoModel')
return model
def ssd_300(image_size,
n_classes,
min_scale=None,
max_scale=None,
scales=None,
aspect_ratios_global=None,
aspect_ratios_per_layer=[[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],
[0.5, 1.0, 2.0], [0.5, 1.0, 2.0]],
two_boxes_for_ar1=True,
steps=None,
offsets=None,
limit_boxes=False,
variances=[0.1, 0.1, 0.2, 0.2],
coords='centroids',
normalize_coords=False,
subtract_mean=None,
divide_by_stddev=None,
swap_channels=False,
return_predictor_sizes=False):
'''
Build a Keras model with SSD_300 architecture, see references.
The base network is a reduced atrous VGG-16, extended by the SSD architecture,
as described in the paper.
In case you're wondering why this function has so many arguments: All arguments except
the first two (`image_size` and `n_classes`) are only needed so that the anchor box
layers can produce the correct anchor boxes. In case you're training the network, the
parameters passed here must be the same as the ones used to set up `SSDBoxEncoder`.
In case you're loading trained weights, the parameters passed here must be the same
as the ones used to produce the trained weights.
Some of these arguments are explained in more detail in the documentation of the
`SSDBoxEncoder` class.
Note: Requires Keras v2.0 or later. Currently works only with the
TensorFlow backend (v1.0 or later).
Arguments:
image_size (tuple): The input image size in the format `(height, width, channels)`.
n_classes (int): The number of categories for classification including
the background class (i.e. the number of positive classes +1 for
the background calss).
min_scale (float, optional): The smallest scaling factor for the size of the anchor boxes as a fraction
of the shorter side of the input images. Defaults to 0.1.
max_scale (float, optional): The largest scaling factor for the size of the anchor boxes as a fraction
of the shorter side of the input images. All scaling factors between the smallest and the
largest will be linearly interpolated. Note that the second to last of the linearly interpolated
scaling factors will actually be the scaling factor for the last predictor layer, while the last
scaling factor is used for the second box for aspect ratio 1 in the last predictor layer
if `two_boxes_for_ar1` is `True`. Defaults to 0.9.
scales (list, optional): A list of floats containing scaling factors per convolutional predictor layer.
This list must be one element longer than the number of predictor layers. The first `k` elements are the
scaling factors for the `k` predictor layers, while the last element is used for the second box
for aspect ratio 1 in the last predictor layer if `two_boxes_for_ar1` is `True`. This additional
last scaling factor must be passed either way, even if it is not being used.
Defaults to `None`. If a list is passed, this argument overrides `min_scale` and
`max_scale`. All scaling factors must be greater than zero.
aspect_ratios_global (list, optional): The list of aspect ratios for which anchor boxes are to be
generated. This list is valid for all prediction layers. Defaults to None.
aspect_ratios_per_layer (list, optional): A list containing one aspect ratio list for each prediction layer.
This allows you to set the aspect ratios for each predictor layer individually, which is the case for the
original SSD300 implementation. If a list is passed, it overrides `aspect_ratios_global`.
Defaults to the aspect ratios used in the original SSD300 architecture, i.e.:
[[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],
[0.5, 1.0, 2.0],
[0.5, 1.0, 2.0]]
two_boxes_for_ar1 (bool, optional): Only relevant for aspect ratio lists that contain 1. Will be ignored otherwise.
If `True`, two anchor boxes will be generated for aspect ratio 1. The first will be generated
using the scaling factor for the respective layer, the second one will be generated using
geometric mean of said scaling factor and next bigger scaling factor. Defaults to `True`, following the original
implementation.
steps (list, optional): `None` or a list with as many elements as there are predictor layers. The elements can be
either ints/floats or tuples of two ints/floats. These numbers represent for each predictor layer how many
pixels apart the anchor box center points should be vertically and horizontally along the spatial grid over
the image. If the list contains ints/floats, then that value will be used for both spatial dimensions.
If the list contains tuples of two ints/floats, then they represent `(step_height, step_width)`.
If no steps are provided, then they will be computed such that the anchor box center points will form an
equidistant grid within the image dimensions. Defaults to `None`.
offsets (list, optional): `None` or a list with as many elements as there are predictor layers. The elements can be
either floats or tuples of two floats. These numbers represent for each predictor layer how many
pixels from the top and left boarders of the image the top-most and left-most anchor box center points should be
as a fraction of `steps`. The last bit is important: The offsets are not absolute pixel values, but fractions
of the step size specified in the `steps` argument. If the list contains floats, then that value will
be used for both spatial dimensions. If the list contains tuples of two floats, then they represent
`(vertical_offset, horizontal_offset)`. If no offsets are provided, then they will default to 0.5 of the step size.
Defaults to `None`.
limit_boxes (bool, optional): If `True`, limits box coordinates to stay within image boundaries.
This would normally be set to `True`, but here it defaults to `False`, following the original
implementation.
variances (list, optional): A list of 4 floats >0 with scaling factors (actually it's not factors but divisors
to be precise) for the encoded predicted box coordinates. A variance value of 1.0 would apply
no scaling at all to the predictions, while values in (0,1) upscale the encoded predictions and values greater
than 1.0 downscale the encoded predictions. Defaults to `[0.1, 0.1, 0.2, 0.2]`, following the original implementation.
The coordinate format must be 'centroids'.
coords (str, optional): The box coordinate format to be used. Can be either 'centroids' for the format
`(cx, cy, w, h)` (box center coordinates, width, and height) or 'minmax' for the format
`(xmin, xmax, ymin, ymax)`. Defaults to 'centroids', following the original implementation.
normalize_coords (bool, optional): Set to `True` if the model is supposed to use relative instead of absolute coordinates,
i.e. if the model predicts box coordinates within [0,1] instead of absolute coordinates. Defaults to `False`.
subtract_mean (array-like, optional): `None` or an array-like object of integers or floating point values
of any shape that is broadcast-compatible with the image shape. The elements of this array will be
subtracted from the image pixel intensity values. For example, pass a list of three integers
to perform per-channel mean normalization for color images. Defaults to `None`.
divide_by_stddev (array-like, optional): `None` or an array-like object of non-zero integers or
floating point values of any shape that is broadcast-compatible with the image shape. The image pixel
intensity values will be divided by the elements of this array. For example, pass a list
of three integers to perform per-channel standard deviation normalization for color images.
Defaults to `None`.
swap_channels (bool, optional): If `True` the color channel order of the input images will be reversed,
i.e. if the input color channel order is RGB, the color channels will be swapped to BGR. Note that the
original Caffe implementation assumes BGR input. Defaults to `True`.
return_predictor_sizes (bool, optional): If `True`, this function not only returns the model, but also
a list containing the spatial dimensions of the predictor layers. This isn't strictly necessary since
you can always get their sizes easily via the Keras API, but it's convenient and less error-prone
to get them this way. THey are only relevant for training anyway (SSDBoxEncoder needs to know the
spatial dimensions of the predictor layers), for inference you don't need them.
Returns:
model: The Keras SSD model.
predictor_sizes: A Numpy array containing the `(height, width)` portion
of the output tensor shape for each convolutional predictor layer. During
training, the generator function needs this in order to transform
the ground truth labels into tensors of identical structure as the
output tensors of the model, which is in turn needed for the cost
function.
References:
https://arxiv.org/abs/1512.02325v5
'''
n_predictor_layers = 6 # The number of predictor conv layers in the network is 6 for the original SSD300
# Get a few exceptions out of the way first
if aspect_ratios_global is None and aspect_ratios_per_layer is None:
raise ValueError(
"`aspect_ratios_global` and `aspect_ratios_per_layer` cannot both be None. At least one needs to be specified."
)
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))
if (not (steps is None)) and (len(steps) != n_predictor_layers):
raise ValueError(
"You must provide at least one step value per predictor layer.")
if (not (offsets is None)) and (len(offsets) != n_predictor_layers):
raise ValueError(
"You must provide at least one offset value per predictor layer.")
# Set the aspect ratios for each predictor layer. These are only needed for the anchor box layers.
if aspect_ratios_per_layer:
aspect_ratios = aspect_ratios_per_layer
else:
aspect_ratios = [aspect_ratios_global] * n_predictor_layers
# 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_per_layer:
n_boxes = []
for ar in aspect_ratios_per_layer:
if (1 in ar) & two_boxes_for_ar1:
n_boxes.append(len(ar) +
1) # +1 for the second box for aspect ratio 1
else:
n_boxes.append(len(ar))
else: # If only a global aspect ratio list was passed, then the number of boxes is the same for each predictor layer
if (1 in aspect_ratios_global) & two_boxes_for_ar1:
n_boxes = len(aspect_ratios_global) + 1
else:
n_boxes = len(aspect_ratios_global)
n_boxes = [n_boxes] * n_predictor_layers
if steps is None:
steps = [None] * n_predictor_layers
if offsets is None:
offsets = [None] * n_predictor_layers
# Input image format
img_height, img_width, img_channels = image_size[0], image_size[
1], image_size[2]
### Build the actual network.
x = Input(shape=(img_height, img_width, img_channels))
# The following identity layer is only needed so that subsequent two lambda layers can be optional.
x1 = Lambda(lambda z: z,
output_shape=(img_height, img_width, img_channels),
name='idendity_layer')(x)
if not (subtract_mean is None):
x1 = Lambda(lambda z: z - np.array(subtract_mean),
output_shape=(img_height, img_width, img_channels),
name='input_mean_normalization')(x1)
if not (divide_by_stddev is None):
x1 = Lambda(lambda z: z / np.array(divide_by_stddev),
output_shape=(img_height, img_width, img_channels),
name='input_stddev_normalization')(x1)
if swap_channels and (img_channels == 3):
x1 = Lambda(lambda z: z[..., ::-1],
output_shape=(img_height, img_width, img_channels),
name='input_channel_swap')(x1)
conv1_1 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv1_1')(x1)
conv1_2 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv1_2')(conv1_1)
pool1 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool1')(conv1_2)
conv2_1 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv2_1')(pool1)
conv2_2 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv2_2')(conv2_1)
pool2 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool2')(conv2_2)
conv3_1 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv3_1')(pool2)
conv3_2 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv3_2')(conv3_1)
conv3_3 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv3_3')(conv3_2)
pool3 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool3')(conv3_3)
conv4_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv4_1')(pool3)
conv4_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv4_3')(conv4_2)
pool4 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool4')(conv4_3)
conv5_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv5_1')(pool4)
conv5_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv5_2')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv5_3')(conv5_2)
pool5 = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='pool5')(conv5_3)
fc6 = Conv2D(1024, (3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='fc6')(pool5)
fc7 = Conv2D(1024, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='fc7')(fc6)
conv6_1 = Conv2D(256, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv6_1')(fc7)
conv6_1 = ZeroPadding2D(padding=((1, 1), (1, 1)),
name='conv6_padding')(conv6_1)
conv6_2 = Conv2D(512, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
name='conv6_2')(conv6_1)
conv7_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv7_1')(conv6_2)
conv7_1 = ZeroPadding2D(padding=((1, 1), (1, 1)),
name='conv7_padding')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
name='conv7_2')(conv7_1)
conv8_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv8_1')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
strides=(1, 1),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
name='conv8_2')(conv8_1)
conv9_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
name='conv9_1')(conv8_2)
conv9_2 = Conv2D(256, (3, 3),
strides=(1, 1),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
name='conv9_2')(conv9_1)
# Feed conv4_3 into the L2 normalization layer
conv4_3_norm = L2Normalization(gamma_init=20, name='conv4_3_norm')(conv4_3)
### Build the convolutional predictor layers on top of the base network
# 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)`
conv4_3_norm_mbox_conf = Conv2D(
n_boxes[0] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv4_3_norm_mbox_conf')(conv4_3_norm)
fc7_mbox_conf = Conv2D(n_boxes[1] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='fc7_mbox_conf')(fc7)
conv6_2_mbox_conf = Conv2D(n_boxes[2] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv6_2_mbox_conf')(conv6_2)
conv7_2_mbox_conf = Conv2D(n_boxes[3] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv7_2_mbox_conf')(conv7_2)
conv8_2_mbox_conf = Conv2D(n_boxes[4] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv8_2_mbox_conf')(conv8_2)
conv9_2_mbox_conf = Conv2D(n_boxes[5] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv9_2_mbox_conf')(conv9_2)
# 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)`
conv4_3_norm_mbox_loc = Conv2D(n_boxes[0] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv4_3_norm_mbox_loc')(conv4_3_norm)
fc7_mbox_loc = Conv2D(n_boxes[1] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='fc7_mbox_loc')(fc7)
conv6_2_mbox_loc = Conv2D(n_boxes[2] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv6_2_mbox_loc')(conv6_2)
conv7_2_mbox_loc = Conv2D(n_boxes[3] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv7_2_mbox_loc')(conv7_2)
conv8_2_mbox_loc = Conv2D(n_boxes[4] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv8_2_mbox_loc')(conv8_2)
conv9_2_mbox_loc = Conv2D(n_boxes[5] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
name='conv9_2_mbox_loc')(conv9_2)
### Generate the anchor boxes (called "priors" in the original Caffe/C++ implementation, so I'll keep their layer names)
# Output shape of anchors: `(batch, height, width, n_boxes, 8)`
conv4_3_norm_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[0],
next_scale=scales[1],
aspect_ratios=aspect_ratios[0],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[0],
this_offsets=offsets[0],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv4_3_norm_mbox_priorbox')(conv4_3_norm_mbox_loc)
fc7_mbox_priorbox = AnchorBoxes(img_height,
img_width,
this_scale=scales[1],
next_scale=scales[2],
aspect_ratios=aspect_ratios[1],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[1],
this_offsets=offsets[1],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='fc7_mbox_priorbox')(fc7_mbox_loc)
conv6_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[2],
next_scale=scales[3],
aspect_ratios=aspect_ratios[2],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[2],
this_offsets=offsets[2],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv6_2_mbox_priorbox')(conv6_2_mbox_loc)
conv7_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[3],
next_scale=scales[4],
aspect_ratios=aspect_ratios[3],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[3],
this_offsets=offsets[3],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv7_2_mbox_priorbox')(conv7_2_mbox_loc)
conv8_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[4],
next_scale=scales[5],
aspect_ratios=aspect_ratios[4],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[4],
this_offsets=offsets[4],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv8_2_mbox_priorbox')(conv8_2_mbox_loc)
conv9_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[5],
next_scale=scales[6],
aspect_ratios=aspect_ratios[5],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[5],
this_offsets=offsets[5],
limit_boxes=limit_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv9_2_mbox_priorbox')(conv9_2_mbox_loc)
### Reshape
# Reshape the class predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, n_classes)`
# We want the classes isolated in the last axis to perform softmax on them
conv4_3_norm_mbox_conf_reshape = Reshape(
(-1, n_classes),
name='conv4_3_norm_mbox_conf_reshape')(conv4_3_norm_mbox_conf)
fc7_mbox_conf_reshape = Reshape(
(-1, n_classes), name='fc7_mbox_conf_reshape')(fc7_mbox_conf)
conv6_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv6_2_mbox_conf_reshape')(conv6_2_mbox_conf)
conv7_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv7_2_mbox_conf_reshape')(conv7_2_mbox_conf)
conv8_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv8_2_mbox_conf_reshape')(conv8_2_mbox_conf)
conv9_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv9_2_mbox_conf_reshape')(conv9_2_mbox_conf)
# Reshape the box predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, 4)`
# We want the four box coordinates isolated in the last axis to compute the smooth L1 loss
conv4_3_norm_mbox_loc_reshape = Reshape(
(-1, 4), name='conv4_3_norm_mbox_loc_reshape')(conv4_3_norm_mbox_loc)
fc7_mbox_loc_reshape = Reshape((-1, 4),
name='fc7_mbox_loc_reshape')(fc7_mbox_loc)
conv6_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv6_2_mbox_loc_reshape')(conv6_2_mbox_loc)
conv7_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv7_2_mbox_loc_reshape')(conv7_2_mbox_loc)
conv8_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv8_2_mbox_loc_reshape')(conv8_2_mbox_loc)
conv9_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv9_2_mbox_loc_reshape')(conv9_2_mbox_loc)
# 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)
### Concatenate the predictions from the 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_conf`: (batch, n_boxes_total, n_classes)
mbox_conf = Concatenate(axis=1, name='mbox_conf')([
conv4_3_norm_mbox_conf_reshape, fc7_mbox_conf_reshape,
conv6_2_mbox_conf_reshape, conv7_2_mbox_conf_reshape,
conv8_2_mbox_conf_reshape, conv9_2_mbox_conf_reshape
])
# Output shape of `mbox_loc`: (batch, n_boxes_total, 4)
mbox_loc = Concatenate(axis=1, name='mbox_loc')([
conv4_3_norm_mbox_loc_reshape, fc7_mbox_loc_reshape,
conv6_2_mbox_loc_reshape, conv7_2_mbox_loc_reshape,
conv8_2_mbox_loc_reshape, conv9_2_mbox_loc_reshape
])
# Output shape of `mbox_priorbox`: (batch, n_boxes_total, 8)
mbox_priorbox = Concatenate(axis=1, name='mbox_priorbox')([
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
])
# The box coordinate predictions will go into the loss function just the way they are,
# but for the class predictions, we'll apply a softmax activation layer first
mbox_conf_softmax = Activation('softmax',
name='mbox_conf_softmax')(mbox_conf)
# Concatenate the class and box predictions and the anchors to one large predictions vector
# Output shape of `predictions`: (batch, n_boxes_total, n_classes + 4 + 8)
predictions = Concatenate(axis=2, name='predictions')(
[mbox_conf_softmax, mbox_loc, mbox_priorbox])
model = Model(inputs=x, outputs=predictions)
if return_predictor_sizes:
# Get the spatial dimensions (height, width) of the predictor conv layers, we need them to
# be able to generate the default boxes for the matching process outside of the model during training.
# Note that the original implementation performs anchor box matching inside the loss function. We don't do that.
# Instead, we'll do it in the batch generator function.
# The spatial dimensions are the same for the confidence and localization predictors, so we just take those of the conf layers.
predictor_sizes = np.array([
conv4_3_norm_mbox_conf._keras_shape[1:3],
fc7_mbox_conf._keras_shape[1:3],
conv6_2_mbox_conf._keras_shape[1:3],
conv7_2_mbox_conf._keras_shape[1:3],
conv8_2_mbox_conf._keras_shape[1:3],
conv9_2_mbox_conf._keras_shape[1:3]
])
return model, predictor_sizes
else:
return model
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with
TensorFlow, Theano, and CNTK. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
blocks: numbers of building blocks for the four dense layers.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=221,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
x = ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = Activation('relu', name='conv1/relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = Model(inputs, x, name='densenet201')
else:
model = Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='50662582284e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def inception_block_1a(X):
"""
Implementation of an inception block
"""
X_3x3 = Conv2D(96, (1, 1),
data_format='channels_first',
name='inception_3a_3x3_conv1')(X)
X_3x3 = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_3x3_bn1')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
X_3x3 = Conv2D(128, (3, 3),
data_format='channels_first',
name='inception_3a_3x3_conv2')(X_3x3)
X_3x3 = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_3x3_bn2')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_5x5 = Conv2D(16, (1, 1),
data_format='channels_first',
name='inception_3a_5x5_conv1')(X)
X_5x5 = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_5x5_bn1')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
X_5x5 = Conv2D(32, (5, 5),
data_format='channels_first',
name='inception_3a_5x5_conv2')(X_5x5)
X_5x5 = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_5x5_bn2')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_pool = MaxPooling2D(pool_size=3, strides=2,
data_format='channels_first')(X)
X_pool = Conv2D(32, (1, 1),
data_format='channels_first',
name='inception_3a_pool_conv')(X_pool)
X_pool = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_pool_bn')(X_pool)
X_pool = Activation('relu')(X_pool)
X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)),
data_format='channels_first')(X_pool)
X_1x1 = Conv2D(64, (1, 1),
data_format='channels_first',
name='inception_3a_1x1_conv')(X)
X_1x1 = BatchNormalization(axis=1,
epsilon=0.00001,
name='inception_3a_1x1_bn')(X_1x1)
X_1x1 = Activation('relu')(X_1x1)
# CONCAT
inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)
return inception
else:
val_generator = None
if use_keras_fit:
val = None
#%% Compile the model structure with some generator data information
# Up-sampling convolutional network with LSTM layer
cs = generator.convolution_shape
cso = generator.output_convolution_shape
# Convolutional NN
input_0 = Input(shape=cs, name='input_0')
periodic_padding_2 = PeriodicPadding2D(padding=(0, 2),
data_format='channels_first')
zero_padding_2 = ZeroPadding2D(padding=(2, 0), data_format='channels_first')
periodic_padding_1 = PeriodicPadding2D(padding=(0, 1),
data_format='channels_first')
zero_padding_1 = ZeroPadding2D(padding=(1, 0), data_format='channels_first')
max_pooling_2 = MaxPooling2D(2, data_format='channels_first')
up_sampling_2 = UpSampling2D(2, data_format='channels_first')
conv_2d_1 = Conv2D(
32, 3, **{
'dilation_rate': 2,
'padding': 'valid',
'activation': 'tanh',
'data_format': 'channels_first'
})
conv_2d_2 = Conv2D(
64, 3, **{
'dilation_rate': 1,
def ssd_300(image_size,
n_classes,
mode='training',
l2_regularization=0.0005,
min_scale=None,
max_scale=None,
scales=None,
aspect_ratios_global=None,
aspect_ratios_per_layer=[[1.0, 2.0, 0.5],
[1.0, 2.0, 0.5, 3.0, 1.0 / 3.0],
[1.0, 2.0, 0.5, 3.0, 1.0 / 3.0],
[1.0, 2.0, 0.5, 3.0, 1.0 / 3.0],
[1.0, 2.0, 0.5], [1.0, 2.0, 0.5]],
two_boxes_for_ar1=True,
steps=[8, 16, 32, 64, 100, 300],
offsets=None,
clip_boxes=False,
variances=[0.1, 0.1, 0.2, 0.2],
coords='centroids',
normalize_coords=True,
subtract_mean=[123, 117, 104],
divide_by_stddev=None,
swap_channels=[2, 1, 0],
confidence_thresh=0.01,
iou_threshold=0.45,
top_k=200,
nms_max_output_size=400,
return_predictor_sizes=False):
'''
Build a Keras model with SSD300 architecture, see references.
The base network is a reduced atrous VGG-16, extended by the SSD architecture,
as described in the paper.
Most of the arguments that this function takes are only needed for the anchor
box layers. In case you're training the network, the parameters passed here must
be the same as the ones used to set up `SSDBoxEncoder`. In case you're loading
trained weights, the parameters passed here must be the same as the ones used
to produce the trained weights.
Some of these arguments are explained in more detail in the documentation of the
`SSDBoxEncoder` class.
Note: Requires Keras v2.0 or later. Currently works only with the
TensorFlow backend (v1.0 or later).
Arguments:
image_size (tuple): The input image size in the format `(height, width, channels)`.
n_classes (int): The number of positive classes, e.g. 20 for Pascal VOC, 80 for MS COCO.
mode (str, optional): One of 'training', 'inference' and 'inference_fast'. In 'training' mode,
the model outputs the raw prediction tensor, while in 'inference' and 'inference_fast' modes,
the raw predictions are decoded into absolute coordinates and filtered via confidence thresholding,
non-maximum suppression, and top-k filtering. The difference between latter two modes is that
'inference' follows the exact procedure of the original Caffe implementation, while
'inference_fast' uses a faster prediction decoding procedure.
l2_regularization (float, optional): The L2-regularization rate. Applies to all convolutional layers.
Set to zero to deactivate L2-regularization.
min_scale (float, optional): The smallest scaling factor for the size of the anchor boxes as a fraction
of the shorter side of the input images.
max_scale (float, optional): The largest scaling factor for the size of the anchor boxes as a fraction
of the shorter side of the input images. All scaling factors between the smallest and the
largest will be linearly interpolated. Note that the second to last of the linearly interpolated
scaling factors will actually be the scaling factor for the last predictor layer, while the last
scaling factor is used for the second box for aspect ratio 1 in the last predictor layer
if `two_boxes_for_ar1` is `True`.
scales (list, optional): A list of floats containing scaling factors per convolutional predictor layer.
This list must be one element longer than the number of predictor layers. The first `k` elements are the
scaling factors for the `k` predictor layers, while the last element is used for the second box
for aspect ratio 1 in the last predictor layer if `two_boxes_for_ar1` is `True`. This additional
last scaling factor must be passed either way, even if it is not being used. If a list is passed,
this argument overrides `min_scale` and `max_scale`. All scaling factors must be greater than zero.
aspect_ratios_global (list, optional): The list of aspect ratios for which anchor boxes are to be
generated. This list is valid for all prediction layers.
aspect_ratios_per_layer (list, optional): A list containing one aspect ratio list for each prediction layer.
This allows you to set the aspect ratios for each predictor layer individually, which is the case for the
original SSD300 implementation. If a list is passed, it overrides `aspect_ratios_global`.
two_boxes_for_ar1 (bool, optional): Only relevant for aspect ratio lists that contain 1. Will be ignored otherwise.
If `True`, two anchor boxes will be generated for aspect ratio 1. The first will be generated
using the scaling factor for the respective layer, the second one will be generated using
geometric mean of said scaling factor and next bigger scaling factor.
steps (list, optional): `None` or a list with as many elements as there are predictor layers. The elements can be
either ints/floats or tuples of two ints/floats. These numbers represent for each predictor layer how many
pixels apart the anchor box center points should be vertically and horizontally along the spatial grid over
the image. If the list contains ints/floats, then that value will be used for both spatial dimensions.
If the list contains tuples of two ints/floats, then they represent `(step_height, step_width)`.
If no steps are provided, then they will be computed such that the anchor box center points will form an
equidistant grid within the image dimensions.
offsets (list, optional): `None` or a list with as many elements as there are predictor layers. The elements can be
either floats or tuples of two floats. These numbers represent for each predictor layer how many
pixels from the top and left boarders of the image the top-most and left-most anchor box center points should be
as a fraction of `steps`. The last bit is important: The offsets are not absolute pixel values, but fractions
of the step size specified in the `steps` argument. If the list contains floats, then that value will
be used for both spatial dimensions. If the list contains tuples of two floats, then they represent
`(vertical_offset, horizontal_offset)`. If no offsets are provided, then they will default to 0.5 of the step size.
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.
coords (str, optional): The box coordinate format to be used internally by the model (i.e. this is not the input format
of the ground truth labels). Can be either 'centroids' for the format `(cx, cy, w, h)` (box center coordinates, width,
and height), 'minmax' for the format `(xmin, xmax, ymin, ymax)`, or 'corners' for the format `(xmin, ymin, xmax, ymax)`.
normalize_coords (bool, optional): Set to `True` if the model is supposed to use relative instead of absolute coordinates,
i.e. if the model predicts box coordinates within [0,1] instead of absolute coordinates.
subtract_mean (array-like, optional): `None` or an array-like object of integers or floating point values
of any shape that is broadcast-compatible with the image shape. The elements of this array will be
subtracted from the image pixel intensity values. For example, pass a list of three integers
to perform per-channel mean normalization for color images.
divide_by_stddev (array-like, optional): `None` or an array-like object of non-zero integers or
floating point values of any shape that is broadcast-compatible with the image shape. The image pixel
intensity values will be divided by the elements of this array. For example, pass a list
of three integers to perform per-channel standard deviation normalization for color images.
swap_channels (list, optional): Either `False` or a list of integers representing the desired order in which the input
image channels should be swapped.
confidence_thresh (float, optional): A float in [0,1), the minimum classification confidence in a specific
positive class in order to be considered for the non-maximum suppression stage for the respective class.
A lower value will result in a larger part of the selection process being done by the non-maximum suppression
stage, while a larger value will result in a larger part of the selection process happening in the confidence
thresholding stage.
iou_threshold (float, optional): A float in [0,1]. All boxes that have a Jaccard similarity of greater than `iou_threshold`
with a locally maximal box will be removed from the set of predictions for a given class, where 'maximal' refers
to the box's confidence score.
top_k (int, optional): The number of highest scoring predictions to be kept for each batch item after the
non-maximum suppression stage.
nms_max_output_size (int, optional): The maximal number of predictions that will be left over after the NMS stage.
return_predictor_sizes (bool, optional): If `True`, this function not only returns the model, but also
a list containing the spatial dimensions of the predictor layers. This isn't strictly necessary since
you can always get their sizes easily via the Keras API, but it's convenient and less error-prone
to get them this way. They are only relevant for training anyway (SSDBoxEncoder needs to know the
spatial dimensions of the predictor layers), for inference you don't need them.
Returns:
model: The Keras SSD300 model.
predictor_sizes (optional): A Numpy array containing the `(height, width)` portion
of the output tensor shape for each convolutional predictor layer. During
training, the generator function needs this in order to transform
the ground truth labels into tensors of identical structure as the
output tensors of the model, which is in turn needed for the cost
function.
References:
https://arxiv.org/abs/1512.02325v5
'''
n_predictor_layers = 6 # The number of predictor conv layers in the network is 6 for the original SSD300.
n_classes += 1 # Account for the background class.
l2_reg = l2_regularization # Make the internal name shorter.
img_height, img_width, img_channels = image_size[0], image_size[
1], image_size[2]
############################################################################
# Get a few exceptions out of the way.
############################################################################
if aspect_ratios_global is None and aspect_ratios_per_layer is None:
raise ValueError(
"`aspect_ratios_global` and `aspect_ratios_per_layer` cannot both be None. At least one needs to be specified."
)
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))
if (not (steps is None)) and (len(steps) != n_predictor_layers):
raise ValueError(
"You must provide at least one step value per predictor layer.")
if (not (offsets is None)) and (len(offsets) != n_predictor_layers):
raise ValueError(
"You must provide at least one offset value per predictor layer.")
############################################################################
# Compute the anchor box parameters.
############################################################################
# Set the aspect ratios for each predictor layer. These are only needed for the anchor box layers.
if aspect_ratios_per_layer:
aspect_ratios = aspect_ratios_per_layer
else:
aspect_ratios = [aspect_ratios_global] * n_predictor_layers
# 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_per_layer:
n_boxes = []
for ar in aspect_ratios_per_layer:
if (1 in ar) & two_boxes_for_ar1:
n_boxes.append(len(ar) +
1) # +1 for the second box for aspect ratio 1
else:
n_boxes.append(len(ar))
else: # If only a global aspect ratio list was passed, then the number of boxes is the same for each predictor layer
if (1 in aspect_ratios_global) & two_boxes_for_ar1:
n_boxes = len(aspect_ratios_global) + 1
else:
n_boxes = len(aspect_ratios_global)
n_boxes = [n_boxes] * n_predictor_layers
if steps is None:
steps = [None] * n_predictor_layers
if offsets is None:
offsets = [None] * n_predictor_layers
############################################################################
# Define functions for the Lambda layers below.
############################################################################
def identity_layer(tensor):
return tensor
def input_mean_normalization(tensor):
return tensor - np.array(subtract_mean)
def input_stddev_normalization(tensor):
return tensor / np.array(divide_by_stddev)
def input_channel_swap(tensor):
if len(swap_channels) == 3:
return K.stack([
tensor[..., swap_channels[0]], tensor[..., swap_channels[1]],
tensor[..., swap_channels[2]]
],
axis=-1)
elif len(swap_channels) == 4:
return K.stack([
tensor[..., swap_channels[0]], tensor[..., swap_channels[1]],
tensor[..., swap_channels[2]], tensor[..., swap_channels[3]]
],
axis=-1)
############################################################################
# Build the network.
############################################################################
x = Input(shape=(img_height, img_width, img_channels))
# The following identity layer is only needed so that the subsequent lambda layers can be optional.
x1 = Lambda(identity_layer,
output_shape=(img_height, img_width, img_channels),
name='identity_layer')(x)
if not (subtract_mean is None):
x1 = Lambda(input_mean_normalization,
output_shape=(img_height, img_width, img_channels),
name='input_mean_normalization')(x1)
if not (divide_by_stddev is None):
x1 = Lambda(input_stddev_normalization,
output_shape=(img_height, img_width, img_channels),
name='input_stddev_normalization')(x1)
if swap_channels:
x1 = Lambda(input_channel_swap,
output_shape=(img_height, img_width, img_channels),
name='input_channel_swap')(x1)
conv1_1 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv1_1')(x1)
conv1_2 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv1_2')(conv1_1)
pool1 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool1')(conv1_2)
conv2_1 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv2_1')(pool1)
conv2_2 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv2_2')(conv2_1)
pool2 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool2')(conv2_2)
conv3_1 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv3_1')(pool2)
conv3_2 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv3_2')(conv3_1)
conv3_3 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv3_3')(conv3_2)
pool3 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool3')(conv3_3)
conv4_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv4_1')(pool3)
conv4_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv4_3')(conv4_2)
pool4 = MaxPooling2D(pool_size=(2, 2),
strides=(2, 2),
padding='same',
name='pool4')(conv4_3)
conv5_1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv5_1')(pool4)
conv5_2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv5_2')(conv5_1)
conv5_3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv5_3')(conv5_2)
pool5 = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='pool5')(conv5_3)
fc6 = Conv2D(1024, (3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='fc6')(pool5)
fc7 = Conv2D(1024, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='fc7')(fc6)
conv6_1 = Conv2D(256, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv6_1')(fc7)
conv6_1 = ZeroPadding2D(padding=((1, 1), (1, 1)),
name='conv6_padding')(conv6_1)
conv6_2 = Conv2D(512, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv6_2')(conv6_1)
conv7_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv7_1')(conv6_2)
conv7_1 = ZeroPadding2D(padding=((1, 1), (1, 1)),
name='conv7_padding')(conv7_1)
conv7_2 = Conv2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv7_2')(conv7_1)
conv8_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv8_1')(conv7_2)
conv8_2 = Conv2D(256, (3, 3),
strides=(1, 1),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv8_2')(conv8_1)
conv9_1 = Conv2D(128, (1, 1),
activation='relu',
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv9_1')(conv8_2)
conv9_2 = Conv2D(256, (3, 3),
strides=(1, 1),
activation='relu',
padding='valid',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv9_2')(conv9_1)
# Feed conv4_3 into the L2 normalization layer
conv4_3_norm = L2Normalization(gamma_init=20, name='conv4_3_norm')(conv4_3)
### Build the convolutional predictor layers on top of the base network
# 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)`
conv4_3_norm_mbox_conf = Conv2D(
n_boxes[0] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv4_3_norm_mbox_conf')(conv4_3_norm)
fc7_mbox_conf = Conv2D(n_boxes[1] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='fc7_mbox_conf')(fc7)
conv6_2_mbox_conf = Conv2D(n_boxes[2] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv6_2_mbox_conf')(conv6_2)
conv7_2_mbox_conf = Conv2D(n_boxes[3] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv7_2_mbox_conf')(conv7_2)
conv8_2_mbox_conf = Conv2D(n_boxes[4] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv8_2_mbox_conf')(conv8_2)
conv9_2_mbox_conf = Conv2D(n_boxes[5] * n_classes, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv9_2_mbox_conf')(conv9_2)
# 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)`
conv4_3_norm_mbox_loc = Conv2D(n_boxes[0] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv4_3_norm_mbox_loc')(conv4_3_norm)
fc7_mbox_loc = Conv2D(n_boxes[1] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='fc7_mbox_loc')(fc7)
conv6_2_mbox_loc = Conv2D(n_boxes[2] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv6_2_mbox_loc')(conv6_2)
conv7_2_mbox_loc = Conv2D(n_boxes[3] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv7_2_mbox_loc')(conv7_2)
conv8_2_mbox_loc = Conv2D(n_boxes[4] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv8_2_mbox_loc')(conv8_2)
conv9_2_mbox_loc = Conv2D(n_boxes[5] * 4, (3, 3),
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(l2_reg),
name='conv9_2_mbox_loc')(conv9_2)
### Generate the anchor boxes (called "priors" in the original Caffe/C++ implementation, so I'll keep their layer names)
# Output shape of anchors: `(batch, height, width, n_boxes, 8)`
conv4_3_norm_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[0],
next_scale=scales[1],
aspect_ratios=aspect_ratios[0],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[0],
this_offsets=offsets[0],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv4_3_norm_mbox_priorbox')(conv4_3_norm_mbox_loc)
fc7_mbox_priorbox = AnchorBoxes(img_height,
img_width,
this_scale=scales[1],
next_scale=scales[2],
aspect_ratios=aspect_ratios[1],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[1],
this_offsets=offsets[1],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='fc7_mbox_priorbox')(fc7_mbox_loc)
conv6_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[2],
next_scale=scales[3],
aspect_ratios=aspect_ratios[2],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[2],
this_offsets=offsets[2],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv6_2_mbox_priorbox')(conv6_2_mbox_loc)
conv7_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[3],
next_scale=scales[4],
aspect_ratios=aspect_ratios[3],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[3],
this_offsets=offsets[3],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv7_2_mbox_priorbox')(conv7_2_mbox_loc)
conv8_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[4],
next_scale=scales[5],
aspect_ratios=aspect_ratios[4],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[4],
this_offsets=offsets[4],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv8_2_mbox_priorbox')(conv8_2_mbox_loc)
conv9_2_mbox_priorbox = AnchorBoxes(
img_height,
img_width,
this_scale=scales[5],
next_scale=scales[6],
aspect_ratios=aspect_ratios[5],
two_boxes_for_ar1=two_boxes_for_ar1,
this_steps=steps[5],
this_offsets=offsets[5],
clip_boxes=clip_boxes,
variances=variances,
coords=coords,
normalize_coords=normalize_coords,
name='conv9_2_mbox_priorbox')(conv9_2_mbox_loc)
### Reshape
# Reshape the class predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, n_classes)`
# We want the classes isolated in the last axis to perform softmax on them
conv4_3_norm_mbox_conf_reshape = Reshape(
(-1, n_classes),
name='conv4_3_norm_mbox_conf_reshape')(conv4_3_norm_mbox_conf)
fc7_mbox_conf_reshape = Reshape(
(-1, n_classes), name='fc7_mbox_conf_reshape')(fc7_mbox_conf)
conv6_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv6_2_mbox_conf_reshape')(conv6_2_mbox_conf)
conv7_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv7_2_mbox_conf_reshape')(conv7_2_mbox_conf)
conv8_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv8_2_mbox_conf_reshape')(conv8_2_mbox_conf)
conv9_2_mbox_conf_reshape = Reshape(
(-1, n_classes), name='conv9_2_mbox_conf_reshape')(conv9_2_mbox_conf)
# Reshape the box predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, 4)`
# We want the four box coordinates isolated in the last axis to compute the smooth L1 loss
conv4_3_norm_mbox_loc_reshape = Reshape(
(-1, 4), name='conv4_3_norm_mbox_loc_reshape')(conv4_3_norm_mbox_loc)
fc7_mbox_loc_reshape = Reshape((-1, 4),
name='fc7_mbox_loc_reshape')(fc7_mbox_loc)
conv6_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv6_2_mbox_loc_reshape')(conv6_2_mbox_loc)
conv7_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv7_2_mbox_loc_reshape')(conv7_2_mbox_loc)
conv8_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv8_2_mbox_loc_reshape')(conv8_2_mbox_loc)
conv9_2_mbox_loc_reshape = Reshape(
(-1, 4), name='conv9_2_mbox_loc_reshape')(conv9_2_mbox_loc)
# 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)
### Concatenate the predictions from the 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_conf`: (batch, n_boxes_total, n_classes)
mbox_conf = Concatenate(axis=1, name='mbox_conf')([
conv4_3_norm_mbox_conf_reshape, fc7_mbox_conf_reshape,
conv6_2_mbox_conf_reshape, conv7_2_mbox_conf_reshape,
conv8_2_mbox_conf_reshape, conv9_2_mbox_conf_reshape
])
# Output shape of `mbox_loc`: (batch, n_boxes_total, 4)
mbox_loc = Concatenate(axis=1, name='mbox_loc')([
conv4_3_norm_mbox_loc_reshape, fc7_mbox_loc_reshape,
conv6_2_mbox_loc_reshape, conv7_2_mbox_loc_reshape,
conv8_2_mbox_loc_reshape, conv9_2_mbox_loc_reshape
])
# Output shape of `mbox_priorbox`: (batch, n_boxes_total, 8)
mbox_priorbox = Concatenate(axis=1, name='mbox_priorbox')([
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
])
# The box coordinate predictions will go into the loss function just the way they are,
# but for the class predictions, we'll apply a softmax activation layer first
mbox_conf_softmax = Activation('softmax',
name='mbox_conf_softmax')(mbox_conf)
# Concatenate the class and box predictions and the anchors to one large predictions vector
# Output shape of `predictions`: (batch, n_boxes_total, n_classes + 4 + 8)
predictions = Concatenate(axis=2, name='predictions')(
[mbox_conf_softmax, mbox_loc, mbox_priorbox])
if mode == 'training':
model = Model(inputs=x, outputs=predictions)
elif mode == 'inference':
decoded_predictions = DecodeDetections(
confidence_thresh=confidence_thresh,
iou_threshold=iou_threshold,
top_k=top_k,
nms_max_output_size=nms_max_output_size,
coords=coords,
normalize_coords=normalize_coords,
img_height=img_height,
img_width=img_width,
name='decoded_predictions')(predictions)
model = Model(inputs=x, outputs=decoded_predictions)
elif mode == 'inference_fast':
decoded_predictions = DecodeDetectionsFast(
confidence_thresh=confidence_thresh,
iou_threshold=iou_threshold,
top_k=top_k,
nms_max_output_size=nms_max_output_size,
coords=coords,
normalize_coords=normalize_coords,
img_height=img_height,
img_width=img_width,
name='decoded_predictions')(predictions)
model = Model(inputs=x, outputs=decoded_predictions)
else:
raise ValueError(
"`mode` must be one of 'training', 'inference' or 'inference_fast', but received '{}'."
.format(mode))
if return_predictor_sizes:
predictor_sizes = np.array([
conv4_3_norm_mbox_conf._keras_shape[1:3],
fc7_mbox_conf._keras_shape[1:3],
conv6_2_mbox_conf._keras_shape[1:3],
conv7_2_mbox_conf._keras_shape[1:3],
conv8_2_mbox_conf._keras_shape[1:3],
conv9_2_mbox_conf._keras_shape[1:3]
])
return model, predictor_sizes
else:
return model
def custom_model_hand():
'''
USER CODE STARTS HERE
'''
image_model = Sequential()
image_model.add(ZeroPadding2D((2, 2), input_shape=(50, 50, 1)))
#54x54 fed in due to zero padding
image_model.add(Conv2D(8, (5, 5), activation='relu', name='conv1_1'))
image_model.add(ZeroPadding2D((2, 2)))
image_model.add(Conv2D(8, (5, 5), activation='relu', name='conv1_2'))
image_model.add(MaxPooling2D((2, 2),
strides=(2, 2))) #convert 50x50 to 25x25
#25x25 fed in
image_model.add(ZeroPadding2D((2, 2)))
image_model.add(Conv2D(16, (5, 5), activation='relu', name='conv2_1'))
image_model.add(ZeroPadding2D((2, 2)))
image_model.add(Conv2D(16, (5, 5), activation='relu', name='conv2_2'))
image_model.add(MaxPooling2D((5, 5),
strides=(5, 5))) #convert 25x25 to 5x5
#5x5 fed in
image_model.add(ZeroPadding2D((2, 2)))
image_model.add(Conv2D(40, (5, 5), activation='relu', name='conv3_1'))
image_model.add(ZeroPadding2D((2, 2)))
image_model.add(Conv2D(32, (5, 5), activation='relu', name='conv3_2'))
image_model.add(Dropout(0.2))
image_model.add(Flatten())
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dropout(0.2))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dropout(0.15))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dropout(0.1))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dense(512))
image_model.add(Activation('tanh'))
image_model.add(Dense(5))
image_model.add(Activation('sigmoid'))
return image_model
'''
def create_model_descriptor():
""" Create model descriptor of VGG-Face classificator """
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(224, 224, 3)))
model.add(Convolution2D(64, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(Convolution2D(4096, (7, 7), activation='relu'))
model.add(Dropout(0.5))
model.add(Convolution2D(4096, (1, 1), activation='relu'))
model.add(Dropout(0.5))
model.add(Convolution2D(2622, (1, 1)))
model.add(Flatten())
model.add(Activation('softmax'))
model.load_weights('vgg_face_weights.h5')
# create VGG-Face descriptor without the last layer
vgg_descriptor = Model(inputs=model.layers[0].input,
outputs=model.layers[-2].output)
return vgg_descriptor
def ResNet50(input_shape = (64, 64, 3), classes = 6):
"""
Implementation of the popular ResNet50 the following architecture:
CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
-> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER
Arguments:
input_shape -- shape of the images of the dataset
classes -- integer, number of classes
Returns:
model -- a Model() instance in Keras
"""
# Define the input as a tensor with shape input_shape
X_input = Input(input_shape)
# Zero-Padding
X = ZeroPadding2D((3, 3))(X_input)
# Stage 1
X = Conv2D(64, (7, 7), strides = (2, 2), name = 'conv1', kernel_initializer = glorot_uniform(seed=0))(X)
X = BatchNormalization(axis = 3, name = 'bn_conv1')(X)
X = Activation('relu')(X)
X = MaxPooling2D((3, 3), strides=(2, 2))(X)
# Stage 2
X = convolutional_block(X, f = 3, filters = [64, 64, 256], stage = 2, block='a', s = 1)
X = identity_block(X, 3, [64, 64, 256], stage=2, block='b')
X = identity_block(X, 3, [64, 64, 256], stage=2, block='c')
### START CODE HERE ###
# Stage 3 (≈4 lines)
X = convolutional_block(X, f=3, filters=[128, 128, 512], stage=3, block='a', s=2)
X = identity_block(X, 3, [128, 128, 512], stage=3, block='b')
X = identity_block(X, 3, [128, 128, 512], stage=3, block='c')
X = identity_block(X, 3, [128, 128, 512], stage=3, block='d')
# Stage 4 (≈6 lines)
X = convolutional_block(X, f=3, filters=[256, 256, 1024], stage=4, block='a', s=2)
X = identity_block(X, 3, [256, 256, 1024], stage=4, block='b')
X = identity_block(X, 3, [256, 256, 1024], stage=4, block='c')
X = identity_block(X, 3, [256, 256, 1024], stage=4, block='d')
X = identity_block(X, 3, [256, 256, 1024], stage=4, block='e')
X = identity_block(X, 3, [256, 256, 1024], stage=4, block='f')
# Stage 5 (≈3 lines)
X = X = convolutional_block(X, f=3, filters=[512, 512, 2048], stage=5, block='a', s=2)
X = identity_block(X, 3, [512, 512, 2048], stage=5, block='b')
X = identity_block(X, 3, [512, 512, 2048], stage=5, block='c')
# AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
X = AveragePooling2D(pool_size=(2, 2), padding='same')(X)
### END CODE HERE ###
# output layer
X = Flatten()(X)
X = Dense(classes, activation='softmax', name='fc' + str(classes), kernel_initializer = glorot_uniform(seed=0))(X)
# Create model
model = Model(inputs = X_input, outputs = X, name='ResNet50')
return model
def save_bottleneck_features():
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(3, img_width, img_height)))
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(256, 3, 3, activation='relu', name='conv3_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv4_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Convolution2D(512, 3, 3, activation='relu', name='conv5_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
assert os.path.exists(weight_path), 'Model weights not found (see "weights_path" variable in script).'
f = h5py.File(weight_path)
for k in range(f.attrs['nb_layers']):
if k >= len(model.layers):
break
g = f['layer_{}'.format(k)]
weights = [g['param_{}'.format(p)] for p in range(g.attrs['nb_params'])]
model.layers[k].set_weights(weights)
f.close()
print('Model loaded.')
X, y = load2d()
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
X_flipped, y_flipped = flip_image(X_train, y_train)
X_train = np.vstack((X_train, X_flipped))
y_train = np.vstack((y_train, y_flipped))
X_train = gray_to_rgb(X_train)
X_val = gray_to_rgb(X_val)
bottleneck_features_train = model.predict(X_train)
np.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)
np.save(open('label_train.npy', 'w'), y_train)
bottleneck_features_validation = model.predict(X_val)
np.save(open('bottleneck_features_validation.npy', 'w'), bottleneck_features_validation)
np.save(open('label_validation.npy', 'w'), y_val)
#This generator function takes in a generator and catches
# exceptions that come up from it.
def generatorChecker(imageGenerator):
while True:
try:
x, y = next(imageGenerator)
yield x, y
except:
pass
#I'm making my own VGGNet now
myVGGNet = Sequential()
myVGGNet.add(ZeroPadding2D((1, 1), input_shape=(128, 128, 3)))
myVGGNet.add(Conv2D(64, kernel_size=(3, 3)))
myVGGNet.add(LeakyReLU())
myVGGNet.add(ZeroPadding2D((1, 1)))
myVGGNet.add(Conv2D(64, kernel_size=(3, 3)))
myVGGNet.add(LeakyReLU())
myVGGNet.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
myVGGNet.add(ZeroPadding2D((1, 1)))
myVGGNet.add(Conv2D(128, kernel_size=(3, 3)))
myVGGNet.add(LeakyReLU())
myVGGNet.add(ZeroPadding2D((1, 1)))
myVGGNet.add(Conv2D(128, kernel_size=(3, 3)))
myVGGNet.add(LeakyReLU())
myVGGNet.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
def create_model():
# input_img = Input(shape=(720, 576, 1)) # adapt this if using `channels_first` image data format
input_img = Input(shape=(120, 120, 1))
# 256: 120
x = Conv2D(256, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(input_img)
x = BatchNormalization(momentum=0.1)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
x = Conv2D(256, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
x = MaxPooling2D((2, 2), padding='same')(x)
# 128:60
x = Conv2D(128, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2D(128, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
# 64 : 30 == 32
x = Conv2D(64, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2D(64, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = ZeroPadding2D(padding=(1, 1), dim_ordering='default')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
# 32: 15 == 16
x = Conv2D(32, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2D(32, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# at this point the representation is (4, 4, 8) i.e. 128-dimensional
# 32
x = Conv2DTranspose(32, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(encoded)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2DTranspose(32, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(encoded)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = UpSampling2D((2, 2))(x)
# 64
x = Conv2DTranspose(64, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2DTranspose(64, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = UpSampling2D((2, 2))(x)
# 128
x = Conv2DTranspose(128, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Conv2DTranspose(128, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Dropout(0.5)(x)
x = Activation('relu')(x)
x = Cropping2D(cropping=((1, 1), (1, 1)))(x)
x = UpSampling2D((2, 2))(x)
# 256
x = Conv2DTranspose(256, (3, 3),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
x = Conv2DTranspose(256, (1, 1),
padding='same',
kernel_regularizer=l2(0.0001),
kernel_constraint=maxnorm(3))(x)
x = BatchNormalization(momentum=0.1)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3),
activation='sigmoid',
padding='same',
kernel_regularizer=l2(0.01),
bias_regularizer=l2(0.01))(x)
autoencoder = Model(input_img, decoded)
encoder = Model(input_img, encoded)
autoencoder.summary()
return autoencoder, encoder
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
if input_tensor is None:
img_input = Input(shape=(224, 224, 3))
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
#print bn_axis
#print K.image_data_format()
x = ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = Activation('relu', name='conv1/relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
# 确保模型考虑到任何潜在的前缀“input_tensor”。
'''
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
'''
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = Model(inputs, x, name='densenet201')
else:
model = Model(inputs, x, name='densenet')
#x = Dense(1024, activation='relu')(x)
x = model.output
#x = Flatten()(x)
predictions = Dense(
classes,
activation='softmax',
use_bias=False,
kernel_initializer=initializers.RandomNormal(mean=0.0,
stddev=0.05,
seed=None),
#bias_initializer=initializers.Zeros(),
kernel_constraint=max_norm(5.),
#bias_constraints=max_norm(5.),
#kernel_regularizer=regularizers.l2(0.01),
activity_regularizer=regularizers.l2(0.01))(x)
denseNet_model = Model(inputs=model.input, outputs=predictions)
return denseNet_model
