[Tensorflow]making your own model

from keras.models import Sequential

Keras provides a lot API and the prototype of model for developing model.

class sampleVGGNet:
	@staticmethod
	def build(width, height, depth, classes):
		# initialize the model along with the input shape to be
		# "channels last" and the channels dimension itself
		model = Sequential()
		inputShape = (height, width, depth)

customizing the model by the processing flow

There is an example.

class LeNet:
	@staticmethod
	def build(width, height, depth, classes):
		# initialize the model
		model = Sequential()
		inputShape = (height, width, depth)

		# if we are using "channels first", update the input shape
		if K.image_data_format() == "channels_first":
			inputShape = (depth, height, width)

		# first set of CONV => RELU => POOL layers
		model.add(Conv2D(20, (5, 5), padding="same",
			input_shape=inputShape))
		model.add(Activation("relu"))
		model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))

		# second set of CONV => RELU => POOL layers
		model.add(Conv2D(50, (5, 5), padding="same"))
		model.add(Activation("relu"))
		model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))

		# first (and only) set of FC => RELU layers
		model.add(Flatten())
		model.add(Dense(500))
		model.add(Activation("relu"))

		# softmax classifier
		model.add(Dense(classes))
		model.add(Activation("softmax"))

		# return the constructed network architecture
		return model

Almost changing exist model to be a new one.

# import the necessary packages
from keras.applications import VGG16
from keras.layers.core import Dropout
from keras.layers.core import Flatten
from keras.layers.core import Dense
from keras.layers import Input
from keras.models import Model

class VGG2:
	@staticmethod
	def build(size_width, classes, D):
		# initialize the head model that will be placed on top of
		# the base, then add a FC layer
		baseModel = VGG16(weights="imagenet", include_top=False,
			input_tensor=Input(shape=(size_width, size_width, 3)))
		headModel = baseModel.output
		headModel = Flatten(name="flatten")(headModel)
		headModel = Dense(D, activation="relu")(headModel)
		headModel = Dropout(0.5)(headModel)

		# add a softmax layer
		headModel = Dense(classes, activation="softmax")(headModel)

		# return the model
		return Model(inputs=baseModel.input, outputs=headModel)