TensorFlow2.0之CIFAR10与ResNet18实战

TensorFlow2.0之CIFAR10与ResNet18实战

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, Sequential
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession

config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)


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

    def call(self, inputs, training=None):
        # 前向计算函数
        # [b, h, w, c]通过第一个卷积单元
        out = self.conv1(inputs)
        out = self.bn1(out)
        out = self.bn2(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条路输出直接相加
        output = layers.add([out, identity])
        output = tf.nn.relu(output)
        return output


class ResNet(keras.Model):
    # 通用的Resnet实现类
    def __init__(self, layer_dims, num_classes=10):
        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1*1,
        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):
        # 前向计算函数：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fiter_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):
            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])

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


# 预处理，把数据映射在(-1~1)，保证梯度
def preprocess(x, y):
    x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1
    y = tf.cast(y, dtype=tf.int32)
    return x, y


# 加载数据集
(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()
    model.build(input_shape=(None, 32, 32, 3))
    # 统计网络参数
    model.summary()
    # 构建优化器
    optimizer = optimizers.Adam(lr=1e-4)

    for epoch in range(100):
        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.traiables))

            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()