©2020-2024 ioDraw All rights reserved
知识要点
*
fetch_california_housing：加利福尼亚的房价数据，总计20640个样本，每个样本8个属性表示，以及房价作为target
*
超参数搜索的方式: 网格搜索, 随机搜索, 遗传算法搜索, 启发式搜索
*
超参数训练后用： gv.estimator调取最佳模型
*
函数式添加神经网络:
*
model.add(keras.layers.Dense(layer_size, activation = 'relu'))
*
model.compile(loss = 'mse', optimizer = optimizer) # optimizer =
keras.optimizers.SGD (learning_rate)
*
sklearn_model = KerasRegressor(build_fn = build_model)
from tensorflow.keras.wrappers.scikit_learn import KerasRegressor # 回归神经网络 #
搜索最佳学习率 def build_model(hidden_layers = 1, layer_size = 30, learning_rate =
3e-3): model = keras.models.Sequential()
model.add(keras.layers.Dense(layer_size, activation = 'relu', input_shape =
x_train.shape[1:])) for _ in range(hidden_layers - 1):
model.add(keras.layers.Dense(layer_size, activation = 'relu'))
model.add(keras.layers.Dense(1)) optimizer =
keras.optimizers.SGD(learning_rate) model.compile(loss = 'mse', optimizer =
optimizer) # model.summary() return model sklearn_model =
KerasRegressor(build_fn = build_model)
*
callbacks = [keras.callbacks.EarlyStopping(patience = 5, min_delta = 1e-3)] #
回调函数设置
*
gv = GridSearchCV(sklearn_model, param_grid = params, n_jobs = 1, cv=
5,verbose = 1) # 找最佳参数
*
gv.fit(x_train_scaled, y_train)
1 导包
from tensorflow import keras import pandas as pd import numpy as np import
matplotlib.pyplot as plt import tensorflow as tf
cpu=tf.config.list_physical_devices("CPU") tf.config.set_visible_devices(cpu)
print(tf.config.list_logical_devices())
2 导入数据
from sklearn.model_selection import train_test_split from sklearn.datasets
import fetch_california_housing housing = fetch_california_housing()
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)
3 标准化处理数据
from sklearn.preprocessing import StandardScaler, MinMaxScaler scaler
=StandardScaler() x_train_scaled = scaler.fit_transform(x_train) x_valid_scaled
= scaler.transform(x_valid) x_test_scaled = scaler.transform(x_test)
4 函数式定义模型
from tensorflow.keras.wrappers.scikit_learn import KerasRegressor # 回归神经网络 #
搜索最佳学习率 def build_model(hidden_layers = 1, layer_size = 30, learning_rate =
3e-3): model = keras.models.Sequential()
model.add(keras.layers.Dense(layer_size, activation = 'relu', input_shape =
x_train.shape[1:])) for _ in range(hidden_layers - 1):
model.add(keras.layers.Dense(layer_size, activation = 'relu'))
model.add(keras.layers.Dense(1)) optimizer =
keras.optimizers.SGD(learning_rate) model.compile(loss = 'mse', optimizer =
optimizer) # model.summary() return model sklearn_model =
KerasRegressor(build_fn = build_model)
5 模型训练
callbacks = [keras.callbacks.EarlyStopping(patience = 5, min_delta = 1e-3)]
history = sklearn_model.fit(x_train_scaled, y_train, epochs = 10,
validation_data = (x_valid_scaled, y_valid), callbacks = callbacks)
6 超参数搜索
超参数搜索的方式:
*
网格搜索
*
定义n维方格
*
每个方格对应一组超参数
*
一组一组参数尝试
*
随机搜索
*
遗传算法搜索
*
对自然界的模拟
*
A: 初始化候选参数集合 --> 训练---> 得到模型指标作为生存概率
*
B: 选择 --> 交叉--> 变异 --> 产生下一代集合
*
C: 重新到A, 循环.
*
启发式搜索
*
研究热点-- AutoML的一部分
*
使用循环神经网络来生成参数
*
使用强化学习来进行反馈, 使用模型来训练生成参数.
# 使用sklearn 的网格搜索, 或者随机搜索 from sklearn.model_selection import GridSearchCV,
RandomizedSearchCV params = { 'learning_rate' : [1e-4, 3e-4, 1e-3, 3e-3, 1e-2,
3e-2], 'hidden_layers': [2, 3, 4, 5], 'layer_size': [20, 60, 100]} gv =
GridSearchCV(sklearn_model, param_grid = params, n_jobs = 1, cv= 5,verbose = 1)
gv.fit(x_train_scaled, y_train)
* 输出最佳参数 # 最佳得分 print(gv.best_score_) # -0.47164334654808043 # 最佳参数
print(gv.best_params_) # {'hidden_layers': 5,'layer_size':
100,'learning_rate':0.01} # 最佳模型 print(gv.estimator)
'''<keras.wrappers.scikit_learn.KerasRegressor object at 0x0000025F5BB12220>'''
gv.score
7 最佳参数建模
model = keras.models.Sequential() model.add(keras.layers.Dense(100, activation
= 'relu', input_shape = x_train.shape[1:])) for _ in range(4):
model.add(keras.layers.Dense(100, activation = 'relu'))
model.add(keras.layers.Dense(1)) optimizer = keras.optimizers.SGD(0.01)
model.compile(loss = 'mse', optimizer = optimizer) model.summary()
callbacks = [keras.callbacks.EarlyStopping(patience = 5, min_delta = 1e-3)]
history = model.fit(x_train_scaled, y_train, epochs = 10, validation_data =
(x_valid_scaled, y_valid), callbacks = callbacks)
8 手动实现超参数搜索
* 根据参数进行多次模型的训练, 然后记录 loss # 搜索最佳学习率 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 = 'mse', optimizer = optimizer,
metrics = ['mse']) 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)
# 画图 import pandas as pd 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(lr) plot_learning_curves(history)