手动实现超参数搜索实战

数据集选用加利福尼亚房价预测数据集，是一个房价预测的回归问题

只搜索learning_rate。learning_rate用于参数更新：w = w + grad * learning_rate

关键代码展示：

# learning_rate: [1e-4, 3e-4, 1e-3, 3e-3, 1e-2, 3e-2]
# W = W + grad * learning_rate

learning_rates = [1e-4, 3e-4, 1e-3, 3e-3, 1e-2, 3e-2]
histories = []
for lr in learning_rates:
    model = keras.models.Sequential([
        keras.layers.Dense(30, activation='relu',
                           input_shape=x_train.shape[1:]),
        keras.layers.Dense(1),
    ])
    optimizer = keras.optimizers.SGD(lr)
    model.compile(loss="mean_squared_error", optimizer=optimizer)
    callbacks = [keras.callbacks.EarlyStopping(
        patience=5, min_delta=1e-2)]
    history = model.fit(x_train_scaled, y_train,
                        validation_data = (x_valid_scaled, y_valid),
                        epochs = 100,
                        callbacks = callbacks)
    histories.append(history)

手动训练的缺点：

1、在本简化问题中只调一个学习率参数，但在实际问题中，可能会有很多参数，所以可能需要很多的for循环来实现

2、使用for循环来实现参数搜索，这样模型就只能等上一个模型训练结束后才能开始训练。没有并行化的处理。

所以手动实现很复杂，需要借助现有的库来实现参数搜索，接下来借助sklearn里面实现的参数搜索策略，实现随机化的参数搜索。参考：https://blog.csdn.net/qq_41660119/article/details/105765589

附完整手动搜索代码：

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)

from sklearn.model_selection import train_test_split

x_train_all, x_test, y_train_all, y_test = train_test_split(
    housing.data, housing.target, random_state = 7)
x_train, x_valid, y_train, y_valid = train_test_split(
    x_train_all, y_train_all, random_state = 11)
print(x_train.shape, y_train.shape)
print(x_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

# learning_rate: [1e-4, 3e-4, 1e-3, 3e-3, 1e-2, 3e-2]
# W = W + grad * learning_rate

learning_rates = [1e-4, 3e-4, 1e-3, 3e-3, 1e-2, 3e-2]
histories = []
for lr in learning_rates:
    model = keras.models.Sequential([
        keras.layers.Dense(30, activation='relu',
                           input_shape=x_train.shape[1:]),
        keras.layers.Dense(1),
    ])
    optimizer = keras.optimizers.SGD(lr)
    model.compile(loss="mean_squared_error", optimizer=optimizer)
    callbacks = [keras.callbacks.EarlyStopping(
        patience=5, min_delta=1e-2)]
    history = model.fit(x_train_scaled, y_train,
                        validation_data = (x_valid_scaled, y_valid),
                        epochs = 100,
                        callbacks = callbacks)
    histories.append(history)

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()
for lr, history in zip(learning_rates, histories):
    print("Learning rate: ", lr)
    plot_learning_curves(history)