def __init__(
self,
architecture: CompiledArchitecture,
data: DataSetSplit,
epochs: int,
patience: int,
) -> None:
"""
# Arguments
epochs:
- 0 for automatically stopping when training yields no improvements for a specified number of epochs
- any positive integer for a set number of epochs
"""
self._architecture: CompiledArchitecture = architecture
self._data: DataSetSplit = data
self._names: ModelSplitName = ModelSplitName(
architecture.name(),
data.name(),
epochs,
patience,
)
self._kmodel: keras.models.Model = None
self._total_epochs: int = epochs
self._patience: int = patience
self._is_best: bool = False
self._status: TrainingStatusData = None
self._res = Resolution(190)
self._batch = 10
def create(self, res: Resolution, classes: Optional[int]) -> Model:
"""
Creates a keras.models.Model object.
"""
if type(classes) is not int:
raise ValueError(classes)
return VGG16(
include_top=True,
weights=None,
input_tensor=Input(res.hwc()),
classes=classes,
)
def create(self, res: Resolution, classes: Optional[int]) -> Model:
"""
Creates a keras.models.Model object.
"""
img_input = Input(res.hwc())
x = ResNet101(
include_top=True,
weights=None,
input_tensor=img_input,
)
x = Dense(1, activation='relu', name='predictions')(x.output)
model = Model(img_input, x, name='resnet101a')
return model
def create(self, res: Resolution, classes: Optional[int]) -> Model:
"""
Creates a keras.models.Model object.
"""
if type(classes) is not int:
raise ValueError(classes)
base = VGG16(
include_top=False,
weights='imagenet',
input_shape=res.hwc(),
)
base.trainable = False
x = Flatten(name='flatten')(base.output)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
model = Model(base.input, x, name='vgg16pt')
return model
def create(self, res: Resolution, classes: Optional[int]) -> Model:
"""
Creates a keras.models.Model object.
"""
if type(classes) is not int:
raise ValueError(classes)
img_input = Input(res.hwc())
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
model = Model(img_input, x, name='vgg16')
return model
def create(self, res: Resolution, classes: Optional[int]) -> Model:
"""
Returns a Keras Model object.
"""
img_input = Input(res.hwc())
# Block 1
x = Conv2D(filters=96,
kernel_size=(11, 11),
strides=4,
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = BatchNormalization()(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(
filters=256,
kernel_size=(5, 5),
# strides=4,
activation='relu',
padding='same',
name='block2_conv1')(x)
x = BatchNormalization()(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(
filters=384,
kernel_size=(3, 3),
# strides=4,
activation='relu',
padding='same',
name='block3_conv1')(x)
# Block 4
x = Conv2D(
filters=384,
kernel_size=(3, 3),
# strides=4,
activation='relu',
padding='same',
name='block4_conv1')(x)
# Block 5
x = Conv2D(
filters=256,
kernel_size=(3, 3),
# strides=4,
activation='relu',
padding='same',
name='block5_conv1')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='block5_pool')(x)
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
model = Model(img_input, x, name='smi13a')
return model