Classic convolutional neural network Python, TensorFlow full code implementation

LeNet

class LeNet5(Model):
    def __init__(self):
        super(LeNet5, self).__init__()
        self.c1 = Conv2D(filters=6, kernel_size=(5, 5),
                         activation='sigmoid')
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2)

        self.c2 = Conv2D(filters=16, kernel_size=(5, 5),
                         activation='sigmoid')
        self.p2 = MaxPool2D(pool_size=(2, 2), strides=2)

        self.flatten = Flatten()
        self.f1 = Dense(120, activation='sigmoid')
        self.f2 = Dense(84, activation='sigmoid')
        self.f3 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.c1(x)
        x = self.p1(x)

        x = self.c2(x)
        x = self.p2(x)

        x = self.flatten(x)
        x = self.f1(x)
        x = self.f2(x)
        y = self.f3(x)
        return y

#model = LeNet5()
#model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])
#model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
#model.summary()

AlexNet

class AlexNet8(Model):
    def __init__(self):
        super(AlexNet8, self).__init__()
        self.c1 = Conv2D(filters=96, kernel_size=(3, 3))
        self.b1 = BatchNormalization()
        self.a1 = Activation('relu')
        self.p1 = MaxPool2D(pool_size=(3, 3), strides=2)

        self.c2 = Conv2D(filters=256, kernel_size=(3, 3))
        self.b2 = BatchNormalization()
        self.a2 = Activation('relu')
        self.p2 = MaxPool2D(pool_size=(3, 3), strides=2)

        self.c3 = Conv2D(filters=384, kernel_size=(3, 3), padding='same',
                         activation='relu')
                         
        self.c4 = Conv2D(filters=384, kernel_size=(3, 3), padding='same',
                         activation='relu')
                         
        self.c5 = Conv2D(filters=256, kernel_size=(3, 3), padding='same',
                         activation='relu')
        self.p3 = MaxPool2D(pool_size=(3, 3), strides=2)

        self.flatten = Flatten()
        self.f1 = Dense(2048, activation='relu')
        self.d1 = Dropout(0.5)
        self.f2 = Dense(2048, activation='relu')
        self.d2 = Dropout(0.5)
        self.f3 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.c1(x)
        x = self.b1(x)
        x = self.a1(x)
        x = self.p1(x)

        x = self.c2(x)
        x = self.b2(x)
        x = self.a2(x)
        x = self.p2(x)

        x = self.c3(x)

        x = self.c4(x)

        x = self.c5(x)
        x = self.p3(x)

        x = self.flatten(x)
        x = self.f1(x)
        x = self.d1(x)
        x = self.f2(x)
        x = self.d2(x)
        y = self.f3(x)
        return y


#model = AlexNet8()
#model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])
#model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
#model.summary()

VGGNet

class VGG16(Model):
    def __init__(self):
        super(VGG16, self).__init__()
        self.c1 = Conv2D(filters=64, kernel_size=(3, 3), padding='same')  # 卷积层1
        self.b1 = BatchNormalization()  # BN层1
        self.a1 = Activation('relu')  # 激活层1
        self.c2 = Conv2D(filters=64, kernel_size=(3, 3), padding='same', )
        self.b2 = BatchNormalization()  # BN层1
        self.a2 = Activation('relu')  # 激活层1
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d1 = Dropout(0.2)  # dropout层

        self.c3 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
        self.b3 = BatchNormalization()  # BN层1
        self.a3 = Activation('relu')  # 激活层1
        self.c4 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
        self.b4 = BatchNormalization()  # BN层1
        self.a4 = Activation('relu')  # 激活层1
        self.p2 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d2 = Dropout(0.2)  # dropout层

        self.c5 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b5 = BatchNormalization()  # BN层1
        self.a5 = Activation('relu')  # 激活层1
        self.c6 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b6 = BatchNormalization()  # BN层1
        self.a6 = Activation('relu')  # 激活层1
        self.c7 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b7 = BatchNormalization()
        self.a7 = Activation('relu')
        self.p3 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d3 = Dropout(0.2)

        self.c8 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b8 = BatchNormalization()  # BN层1
        self.a8 = Activation('relu')  # 激活层1
        self.c9 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b9 = BatchNormalization()  # BN层1
        self.a9 = Activation('relu')  # 激活层1
        self.c10 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b10 = BatchNormalization()
        self.a10 = Activation('relu')
        self.p4 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d4 = Dropout(0.2)

        self.c11 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b11 = BatchNormalization()  # BN层1
        self.a11 = Activation('relu')  # 激活层1
        self.c12 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b12 = BatchNormalization()  # BN层1
        self.a12 = Activation('relu')  # 激活层1
        self.c13 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b13 = BatchNormalization()
        self.a13 = Activation('relu')
        self.p5 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d5 = Dropout(0.2)

        self.flatten = Flatten()
        self.f1 = Dense(512, activation='relu')
        self.d6 = Dropout(0.2)
        self.f2 = Dense(512, activation='relu')
        self.d7 = Dropout(0.2)
        self.f3 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.c1(x)
        x = self.b1(x)
        x = self.a1(x)
        x = self.c2(x)
        x = self.b2(x)
        x = self.a2(x)
        x = self.p1(x)
        x = self.d1(x)

        x = self.c3(x)
        x = self.b3(x)
        x = self.a3(x)
        x = self.c4(x)
        x = self.b4(x)
        x = self.a4(x)
        x = self.p2(x)
        x = self.d2(x)

        x = self.c5(x)
        x = self.b5(x)
        x = self.a5(x)
        x = self.c6(x)
        x = self.b6(x)
        x = self.a6(x)
        x = self.c7(x)
        x = self.b7(x)
        x = self.a7(x)
        x = self.p3(x)
        x = self.d3(x)

        x = self.c8(x)
        x = self.b8(x)
        x = self.a8(x)
        x = self.c9(x)
        x = self.b9(x)
        x = self.a9(x)
        x = self.c10(x)
        x = self.b10(x)
        x = self.a10(x)
        x = self.p4(x)
        x = self.d4(x)

        x = self.c11(x)
        x = self.b11(x)
        x = self.a11(x)
        x = self.c12(x)
        x = self.b12(x)
        x = self.a12(x)
        x = self.c13(x)
        x = self.b13(x)
        x = self.a13(x)
        x = self.p5(x)
        x = self.d5(x)

        x = self.flatten(x)
        x = self.f1(x)
        x = self.d6(x)
        x = self.f2(x)
        x = self.d7(x)
        y = self.f3(x)
        return y


#model = VGG16()
#model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])
#model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
#model.summary()

InceptionNet (GoogleNet)

class ConvBNRelu(Model):
    def __init__(self, ch, kernelsz=3, strides=1, padding='same'):
        super(ConvBNRelu, self).__init__()
        self.model = tf.keras.models.Sequential([
            Conv2D(ch, kernelsz, strides=strides, padding=padding),
            BatchNormalization(),
            Activation('relu')
        ])

    def call(self, x):
        x = self.model(x, training=False) #在training=False时，BN通过整个训练集计算均值、方差去做批归一化，training=True时，通过当前batch的均值、方差去做批归一化。推理时 training=False效果好
        return x


class InceptionBlk(Model):
    def __init__(self, ch, strides=1):
        super(InceptionBlk, self).__init__()
        self.ch = ch
        self.strides = strides
        self.c1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
        self.c2_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
        self.c2_2 = ConvBNRelu(ch, kernelsz=3, strides=1)
        self.c3_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
        self.c3_2 = ConvBNRelu(ch, kernelsz=5, strides=1)
        self.p4_1 = MaxPool2D(3, strides=1, padding='same')
        self.c4_2 = ConvBNRelu(ch, kernelsz=1, strides=strides)

    def call(self, x):
        x1 = self.c1(x)
        x2_1 = self.c2_1(x)
        x2_2 = self.c2_2(x2_1)
        x3_1 = self.c3_1(x)
        x3_2 = self.c3_2(x3_1)
        x4_1 = self.p4_1(x)
        x4_2 = self.c4_2(x4_1)
        # concat along axis=channel
        x = tf.concat([x1, x2_2, x3_2, x4_2], axis=3)
        return x


class Inception10(Model):
    def __init__(self, num_blocks, num_classes, init_ch=16, **kwargs):
        super(Inception10, self).__init__(**kwargs)
        self.in_channels = init_ch
        self.out_channels = init_ch
        self.num_blocks = num_blocks
        self.init_ch = init_ch
        self.c1 = ConvBNRelu(init_ch)
        self.blocks = tf.keras.models.Sequential()
        for block_id in range(num_blocks):
            for layer_id in range(2):
                if layer_id == 0:
                    block = InceptionBlk(self.out_channels, strides=2)
                else:
                    block = InceptionBlk(self.out_channels, strides=1)
                self.blocks.add(block)
            # enlarger out_channels per block
            self.out_channels *= 2
        self.p1 = GlobalAveragePooling2D()
        self.f1 = Dense(num_classes, activation='softmax')

    def call(self, x):
        x = self.c1(x)
        x = self.blocks(x)
        x = self.p1(x)
        y = self.f1(x)
        return y


#model = Inception10(num_blocks=2, num_classes=10)
#model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])
#model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
#model.summary()

ResNet

class ResnetBlock(Model):

    def __init__(self, filters, strides=1, residual_path=False):
        super(ResnetBlock, self).__init__()
        self.filters = filters
        self.strides = strides
        self.residual_path = residual_path

        self.c1 = Conv2D(filters, (3, 3), strides=strides, padding='same', use_bias=False)
        self.b1 = BatchNormalization()
        self.a1 = Activation('relu')

        self.c2 = Conv2D(filters, (3, 3), strides=1, padding='same', use_bias=False)
        self.b2 = BatchNormalization()

        # residual_path为True时，对输入进行下采样，即用1x1的卷积核做卷积操作，保证x能和F(x)维度相同，顺利相加
        if residual_path:
            self.down_c1 = Conv2D(filters, (1, 1), strides=strides, padding='same', use_bias=False)
            self.down_b1 = BatchNormalization()
        
        self.a2 = Activation('relu')

    def call(self, inputs):
        residual = inputs  # residual等于输入值本身，即residual=x
        # 将输入通过卷积、BN层、激活层，计算F(x)
        x = self.c1(inputs)
        x = self.b1(x)
        x = self.a1(x)

        x = self.c2(x)
        y = self.b2(x)

        if self.residual_path:
            residual = self.down_c1(inputs)
            residual = self.down_b1(residual)

        out = self.a2(y + residual)  # 最后输出的是两部分的和，即F(x)+x或F(x)+Wx,再过激活函数
        return out


class ResNet18(Model):

    def __init__(self, block_list, initial_filters=64):  # block_list表示每个block有几个卷积层
        super(ResNet18, self).__init__()
        self.num_blocks = len(block_list)  # 共有几个block
        self.block_list = block_list
        self.out_filters = initial_filters
        self.c1 = Conv2D(self.out_filters, (3, 3), strides=1, padding='same', use_bias=False)
        self.b1 = BatchNormalization()
        self.a1 = Activation('relu')
        self.blocks = tf.keras.models.Sequential()
        # 构建ResNet网络结构
        for block_id in range(len(block_list)):  # 第几个resnet block
            for layer_id in range(block_list[block_id]):  # 第几个卷积层

                if block_id != 0 and layer_id == 0:  # 对除第一个block以外的每个block的输入进行下采样
                    block = ResnetBlock(self.out_filters, strides=2, residual_path=True)
                else:
                    block = ResnetBlock(self.out_filters, residual_path=False)
                self.blocks.add(block)  # 将构建好的block加入resnet
            self.out_filters *= 2  # 下一个block的卷积核数是上一个block的2倍
        self.p1 = tf.keras.layers.GlobalAveragePooling2D()
        self.f1 = tf.keras.layers.Dense(10, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())

    def call(self, inputs):
        x = self.c1(inputs)
        x = self.b1(x)
        x = self.a1(x)
        x = self.blocks(x)
        x = self.p1(x)
        y = self.f1(x)
        return y


#model = ResNet18([2, 2, 2, 2])
#model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])
#model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
#model.summary()

 

Summarize

LeNet (1998)
The beginning of the convolutional network, through the sharing of spatial convolution kernels, reduces the parameters to be trained.

AlexNet (2012)
The relu activation function is used to improve the training speed; Dropout is used to alleviate overfitting.

VGGNet (2014)
The use of small-sized convolution kernels reduces the parameters to be trained and the amount of calculation. Its network structure is very regular and suitable for hardware parallel acceleration.

InceptionNet (2014)
Convolution kernels of different sizes are used in the same layer to improve the perception of the model; batch normalization is used to alleviate the gradient disappearance.

ResNet (2015)
Through inter-layer residual jumping, the front information is introduced, the model degradation is alleviated, and it is possible to deepen the number of neural network layers.