微信小程序部署机器学习模型全流程（1、模型的训练与导出）

前言

本文记录了如何在服务器后端部署机器学习模型（分类，目标检测，语义分割，自然语言处理等），然后使用微信小程序作为前端，实现模型的部署的全流程。

全文目录

1、模型的训练与导出
2、服务器的租用与域名的申请

1 模型的选择

这里我以tensorflow架构为例，选择最简单的手写数字识别模型（其他模型的部署是类似的）

关于tensorflow的安装和环境配置与机器学习模型的原理，我这里就不过多赘述，因为网上有很多可供学习的资料。

2 数据集准备

这里我使用的是Jupyter NoteBook来编写代码。

import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model

# 准备数据集
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()

# 对数据进行预处理
x_train, x_test = x_train / 255.0, x_test / 255.0

# 在样本维度上添加一个维度，以适应卷积网络的输入
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]

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

运行结果：

3 构建模型

# 创建模型
class MyModel(Model):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = Conv2D(32, 3, activation='relu')
        self.flatten = Flatten()
        self.d1 = Dense(64, activation='relu')
        self.d2 = Dense(10)

    def call(self, x):
        x = self.conv1(x)
        x = self.flatten(x)
        x = self.d1(x)
        return self.d2(x)

model = MyModel()

4 训练模型前的准备

# 定义损失函数和优化器
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
optimizer = tf.keras.optimizers.Adam()

# 定义评估指标
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')

# 定义训练步骤
def train_step(images, labels):
    with tf.GradientTape() as tape:
        predictions = model(images, training=True)
        loss = loss_object(labels, predictions)
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))

    train_loss(loss)
    train_accuracy(labels, predictions)

# 定义测试步骤
def test_step(images, labels):
    predictions = model(images, training=False)
    t_loss = loss_object(labels, predictions)

    test_loss(t_loss)
    test_accuracy(labels, predictions)

    
# 超参数 & 分batch
EPOCHS = 5
BATCH_SIZE = 16

train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(BATCH_SIZE)
test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(BATCH_SIZE)

5 训练模型

# 训练模型
for epoch in range(EPOCHS):
    train_loss.reset_states()
    train_accuracy.reset_states()
    test_loss.reset_states()
    test_accuracy.reset_states()

    for images, labels in train_dataset:
        train_step(images, labels)

    for images, labels in test_dataset:
        test_step(images, labels)

    template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
    print(template.format(epoch + 1,
                          train_loss.result(),
                          train_accuracy.result() * 100,
                          test_loss.result(),
                          test_accuracy.result() * 100))

运行结果：

6 模型导出

# 导出模型
tf.saved_model.save(model, 'saved_model')

运行结果：

导出的文件如下：