케라스를 사용해 Resnet-34 CNN직접 구현하기

 핸즈온 머신러닝을 참고하여 Resnet-34를 직접 구현해보았다.

class ResidualUnit(keras.layers.Layer):
    def __init__(self, filters, strides=1, activation="relu", **kwargs):
        super().__init__(**kwargs)
        self.activation = keras.activations.get(activation)
        self.main_layers = [
            keras.layers.Conv2D(filters, 3, strides=strides, padding="same", use_bias=False),
            keras.layers.BatchNormalization(),
            self.activation,
            keras.layers.Conv2D(filters, 3, strides =1, padding="same", use_bias = False),
            keras.layers.BatchNormalization()]
        self.skip_layers = []
        if strides > 1:
            self.skip_layers = [
                keras.layers.Conv2D(filters, 1, strides = strides, padding="same", use_bias = False),
                keras.layers.BatchNormalization()]
    def call(self, inputs):
        Z = inputs
        for layer in self.main_layers:
            Z = layer(Z)
        skip_Z = inputs
        for layer in self.skip_layers:
            skip_Z = layer(skip_Z)
        return self.activation(Z + skip_Z)

model = keras.models.Sequential()
model.add(keras.layers.Conv2D(64,7, strides=2, input_shape=[32,32,3], padding="same", use_bias = False))
model.add(keras.layers.BatchNormalization())
model.add(keras.layers.Activation("relu"))
model.add(keras.layers.MaxPool2D(pool_size=3, strides=2, padding="same"))
prev_filters = 64
for filters in [64]*3+[128]*4 + [256]*6 + [512]*3:
    strides = 1 if filters == prev_filters else 2
    model.add(ResidualUnit(filters, strides=strides))
    prev_filters = filters

model.add(keras.layers.GlobalAvgPool2D())
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(10, activation="softmax"))

model.summary()

 

(x_train, y_train), (x_test, y_test) = tk.datasets.mnist.load_data()

x_train = tf.pad(x_train, [[0, 0], [2,2], [2,2]])/255
x_test = tf.pad(x_test, [[0, 0], [2,2], [2,2]])/255

x_train = tf.expand_dims(x_train, axis=3, name=None)
x_test = tf.expand_dims(x_test, axis=3, name=None)
x_train = tf.repeat(x_train, 3, axis=3)
x_test = tf.repeat(x_test, 3, axis=3)

print(x_train.shape, y_train.shape, x_test.shape, y_test.shape)

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
         
model.summary()

print(model.fit(x_train, y_train, epochs=100, batch_size = 20))

print(model.evaluate(x_test, y_test))

 

 

학습 중 GPU사용하는지 여부 확인 코드

https://rfriend.tistory.com/425