CIFAR10实战合集

Tips:

人工智能难题不仅是计算机科学问题，更是数学、认知科学和哲学问题。− François Chollet

代码

CIFAR10自定义网络实战

点击查看代码

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras


def preprocess(x, y):
    # [0, 255] --> [-1,1]
    x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1.
    y = tf.cast(y, dtype=tf.int32)

    return x, y


batch_size = 128
# x --> [32,32,3], y --> [10k, 1]
(x, y), (x_val, y_val) = datasets.cifar10.load_data()
y = tf.squeeze(y)  # [10k, 1] --> [10k]
y_val = tf.squeeze(y_val)
y = tf.one_hot(y, depth=10)  # [50k, 10]
y_val = tf.one_hot(y_val, depth=10)  # [10k, 10]
print('datasets:', x.shape, y.shape, x_val.shape, y_val.shape, x.min(),
      x.max())

# 构建数据集
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.map(preprocess).shuffle(10000).batch(batch_size)
test_db = tf.data.Dataset.from_tensor_slices((x_val, y_val))
test_db = test_db.map(preprocess).batch(batch_size)

sample = next(iter(train_db))
print('batch:', sample[0].shape, sample[1].shape)


# 新建网络对象
class MyDense(layers.Layer):
    # to replace standard layers.Dense()
    def __init__(self, inp_dim, outp_dim):
        super(MyDense, self).__init__()

        self.kernel = self.add_weight('w', [inp_dim, outp_dim])
        # self.bias = self.add_weight('b', [outp_dim])

    def call(self, inputs, training=None):
        x = inputs @ self.kernel
        return x


# 自定义网络层
class MyNetwork(keras.Model):
    def __init__(self):
        super(MyNetwork, self).__init__()
        self.fc1 = MyDense(32 * 32 * 3, 256)
        self.fc2 = MyDense(256, 128)
        self.fc3 = MyDense(128, 64)
        self.fc4 = MyDense(64, 32)
        self.fc5 = MyDense(32, 10)

    def call(self, inputs, training=None):
        """inputs: [b,32,32,3]"""
        x = tf.reshape(inputs, [-1, 32 * 32 * 3])
        # [b,32*32*3] --> [b, 256]
        x = self.fc1(x)
        x = tf.nn.relu(x)
        # [b, 256] --> [b,128]
        x = self.fc2(x)
        x = tf.nn.relu(x)
        # [b, 128] --> [b,64]
        x = self.fc3(x)
        x = tf.nn.relu(x)
        # [b, 64] --> [b,32]
        x = self.fc4(x)
        x = tf.nn.relu(x)
        # [b, 32] --> [b,10]
        x = self.fc5(x)

        return x


network = MyNetwork()
# 装配
network.compile(optimizer=optimizers.Adam(lr=1e-3),
                loss=tf.losses.CategoricalCrossentropy(from_logits=True),
                metrics=['accuracy'])
# 训练
network.fit(train_db, epochs=5, validation_data=test_db, validation_freq=1)

network.evaluate(test_db)
network.save_weights('ckpt/weights.ckpt')  # 模型的保存
del network
print('saved to ckpt/weights.ckpt')

# 模型的加载
network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),
                loss=tf.losses.CategoricalCrossentropy(from_logits=True),
                metrics=['accuracy'])
network.load_weights('ckpt/weights.ckpt')
print('loaded weights from file.')

network.evaluate(test_db)

CIFAR10与VGG13实战

点击查看代码

import os
import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential


os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
tf.random.set_seed(2345)

conv_layers = [  # 5 units of conv + max pooling
    # unit 1
    layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.Conv2D(64, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),

    # unit 2
    layers.Conv2D(128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.Conv2D(128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),

    # unit 3
    layers.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),

    # unit 4
    layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),

    # unit 5
    layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same')

]


def preprocess(x, y):
    # [0~1]
    x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1
    y = tf.cast(y, dtype=tf.int32)
    return x, y


(x, y), (x_test, y_test) = datasets.cifar10.load_data()
y = tf.squeeze(y, axis=1)
y_test = tf.squeeze(y_test, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)

train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(preprocess).batch(128)

test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(preprocess).batch(64)

sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
      tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))


def main():
    # [b, 32, 32, 3] => [b, 1, 1, 512]
    conv_net = Sequential(conv_layers)

    fc_net = Sequential([
        layers.Dense(256, activation=tf.nn.relu),
        layers.Dense(128, activation=tf.nn.relu),
        layers.Dense(10, activation=None),
    ])

    conv_net.build(input_shape=[None, 32, 32, 3])
    fc_net.build(input_shape=[None, 512])
    conv_net.summary()
    fc_net.summary()
    optimizer = optimizers.Adam(learning_rate=1e-4)

    # [1, 2] + [3, 4] => [1, 2, 3, 4]
    variables = conv_net.trainable_variables + fc_net.trainable_variables

    for epoch in range(5):

        for step, (x, y) in enumerate(train_db):

            with tf.GradientTape() as tape:
                # [b, 32, 32, 3] => [b, 1, 1, 512]
                out = conv_net(x)
                # flatten, => [b, 512]
                out = tf.reshape(out, [-1, 512])
                # [b, 512] => [b, 10]
                logits = fc_net(out)
                # [b] => [b, 10]
                y_onehot = tf.one_hot(y, depth=10)
                # compute loss
                loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
                loss = tf.reduce_mean(loss)

            grads = tape.gradient(loss, variables)
            optimizer.apply_gradients(zip(grads, variables))

            if step % 100 == 0:
                print(epoch, step, 'loss:', float(loss))

        total_num = 0
        total_correct = 0
        for x, y in test_db:
            out = conv_net(x)
            out = tf.reshape(out, [-1, 512])
            logits = fc_net(out)
            prob = tf.nn.softmax(logits, axis=1)
            pred = tf.argmax(prob, axis=1)
            pred = tf.cast(pred, dtype=tf.int32)

            correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
            correct = tf.reduce_sum(correct)

            total_num += x.shape[0]
            total_correct += int(correct)

        acc = total_correct / total_num
        print(epoch, 'acc:', acc)


if __name__ == '__main__':
    main()

CIFAR10与ResNet18实战

点击查看resnet代码

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, Sequential


class BasicBlock(layers.Layer):
    # 残差模块
    def __init__(self, filter_num, stride=1):
        super(BasicBlock, self).__init__()
        # 第一个卷积单元
        self.conv1 = layers.Conv2D(filter_num, (3, 3), strides=stride, padding='same')
        self.bn1 = layers.BatchNormalization()
        self.relu = layers.Activation('relu')
        # 第二个卷积单元
        self.conv2 = layers.Conv2D(filter_num, (3, 3), strides=1, padding='same')
        self.bn2 = layers.BatchNormalization()

        if stride != 1:  # 通过1x1卷积完成shape匹配
            self.downsample = Sequential()
            self.downsample.add(layers.Conv2D(filter_num, (1, 1), strides=stride))
        else:  # shape匹配，直接短接
            self.downsample = lambda x: x

    def call(self, inputs, training=None):

        # [b, h, w, c]，通过第一个卷积单元
        out = self.conv1(inputs)
        out = self.bn1(out)
        out = self.relu(out)
        # 通过第二个卷积单元
        out = self.conv2(out)
        out = self.bn2(out)
        # 通过identity模块
        identity = self.downsample(inputs)
        # 2条路径输出直接相加
        output = layers.add([out, identity])
        output = tf.nn.relu(output)  # 激活函数

        return output


class ResNet(keras.Model):
    # 通用的ResNet实现类
    def __init__(self, layer_dims, num_classes=10):  # [2, 2, 2, 2]
        super(ResNet, self).__init__()
        # 根网络，预处理
        self.stem = Sequential([layers.Conv2D(64, (3, 3), strides=(1, 1)),
                                layers.BatchNormalization(),
                                layers.Activation('relu'),
                                layers.MaxPool2D(pool_size=(2, 2), strides=(1, 1), padding='same')
                                ])
        # 堆叠4个Block，每个block包含了多个BasicBlock,设置步长不一样
        self.layer1 = self.build_resblock(64, layer_dims[0])
        self.layer2 = self.build_resblock(128, layer_dims[1], stride=2)
        self.layer3 = self.build_resblock(256, layer_dims[2], stride=2)
        self.layer4 = self.build_resblock(512, layer_dims[3], stride=2)

        # 通过Pooling层将高宽降低为1x1
        self.avgpool = layers.GlobalAveragePooling2D()
        # 最后连接一个全连接层分类
        self.fc = layers.Dense(num_classes)

    def call(self, inputs, training=None):
        # 通过根网络
        x = self.stem(inputs)
        # 一次通过4个模块
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        # 通过池化层
        x = self.avgpool(x)
        # 通过全连接层
        x = self.fc(x)

        return x

    def build_resblock(self, filter_num, blocks, stride=1):
        # 辅助函数，堆叠filter_num个BasicBlock
        res_blocks = Sequential()
        # 只有第一个BasicBlock的步长可能不为1，实现下采样
        res_blocks.add(BasicBlock(filter_num, stride))

        for _ in range(1, blocks):  # 其他BasicBlock步长都为1
            res_blocks.add(BasicBlock(filter_num, stride=1))

        return res_blocks


def resnet18():
    # 通过调整模块内部BasicBlock的数量和配置实现不同的ResNet
    return ResNet([2, 2, 2, 2])


def resnet34():
    # 通过调整模块内部BasicBlock的数量和配置实现不同的ResNet
    return ResNet([3, 4, 6, 3])

点击查看"CIFAR10与ResNet18实战"代码

import os
import tensorflow as tf
from tensorflow.keras import optimizers, datasets
from resnet import resnet18

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
tf.random.set_seed(2345)


def preprocess(x, y):
    # 将数据映射到-1~1
    x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1
    y = tf.cast(y, dtype=tf.int32)  # 类型转换
    return x, y


(x, y), (x_test, y_test) = datasets.cifar10.load_data()  # 加载数据集
y = tf.squeeze(y, axis=1)  # 删除不必要的维度
y_test = tf.squeeze(y_test, axis=1)  # 删除不必要的维度
print(x.shape, y.shape, x_test.shape, y_test.shape)

train_db = tf.data.Dataset.from_tensor_slices((x, y))  # 构建训练集
# 随机打散，预处理，批量化
train_db = train_db.shuffle(1000).map(preprocess).batch(512)

test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))  # 构建测试集
# 随机打散，预处理，批量化
test_db = test_db.map(preprocess).batch(512)
# 采样一个样本
sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
      tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))


def main():
    # [b, 32, 32, 3] => [b, 1, 1, 512]
    model = resnet18()  # ResNet18网络
    model.build(input_shape=(None, 32, 32, 3))
    model.summary()  # 统计网络参数
    optimizer = optimizers.Adam(learning_rate=1e-4)  # 构建优化器

    for epoch in range(5):  # 训练epoch

        for step, (x, y) in enumerate(train_db):

            with tf.GradientTape() as tape:
                # [b, 32, 32, 3] => [b, 10],前向传播
                logits = model(x)
                # [b] => [b, 10],one-hot编码
                y_onehot = tf.one_hot(y, depth=10)
                # 计算交叉熵
                loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
                loss = tf.reduce_mean(loss)
            # 计算梯度信息
            grads = tape.gradient(loss, model.trainable_variables)
            # 更新网络参数
            optimizer.apply_gradients(zip(grads, model.trainable_variables))

            if step % 50 == 0:
                print(epoch, step, 'loss:', float(loss))

        total_num = 0
        total_correct = 0
        for x, y in test_db:
            logits = model(x)
            prob = tf.nn.softmax(logits, axis=1)
            pred = tf.argmax(prob, axis=1)
            pred = tf.cast(pred, dtype=tf.int32)

            correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
            correct = tf.reduce_sum(correct)

            total_num += x.shape[0]
            total_correct += int(correct)

        acc = total_correct / total_num
        print(epoch, 'acc:', acc)


if __name__ == '__main__':
    main()