09_keras_Tuner使用keras Tuner调整超参数(超参数优化)

"""
09_keras_Tuner使用keras Tuner调整超参数
"""import  tensorflow as tf
from tensorflow import keras
import keras_tuner as kt#加载数据集
(img_train, label_train),\
(img_test, label_test)\=keras.datasets.fashion_mnist.load_data()# Normalize pixel values between 0 and 1
img_train = img_train.astype('float32') / 255.0
img_test = img_test.astype('float32') / 255.0#定义模型
def model_builder(hp):model = keras.Sequential()model.add(keras.layers.Flatten(input_shape=(28, 28)))# Tune the number of units in the first Dense layer# Choose an optimal value between 32-512hp_units = hp.Int('units', min_value=32, max_value=512, step=32)model.add(keras.layers.Dense(units=hp_units, activation='relu'))model.add(keras.layers.Dense(10))# Tune the learning rate for the optimizer# Choose an optimal value from 0.01, 0.001, or 0.0001hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate),loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])return model"""
Keras Tuner 提供了四种调节器：
RandomSearch、Hyperband、BayesianOptimization和Sklearn
"""
#实例化调节器并执行超调
tuner = kt.Hyperband(model_builder,objective='val_accuracy',max_epochs=10,factor=3,directory='my_dir',project_name='intro_to_kt')tuner.search(img_train, label_train, epochs=50, validation_split=0.2, callbacks=[stop_early])# Get the optimal hyperparameters
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]print(f"""
The hyperparameter search is complete. The optimal number of units in the first densely-connected
layer is {best_hps.get('units')} and the optimal learning rate for the optimizer
is {best_hps.get('learning_rate')}.
""")# 生命达到特定值后提前停止训练
stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss',patience=5)# 运行超参数搜索
tuner.search(img_train, label_train, epochs=50, validation_split=0.2, callbacks=[stop_early])# Get the optimal hyperparameters
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]print(f"""
The hyperparameter search is complete. The optimal number of units in the first densely-connected
layer is {best_hps.get('units')} and the optimal learning rate for the optimizer
is {best_hps.get('learning_rate')}.
""")#训练模型
"""
使用从搜索中获得的超参数找到训练模型的最佳生命周期数。
"""
# Build the model with the optimal hyperparameters and train it on the data for 50 epochs
model = tuner.hypermodel.build(best_hps)
history = model.fit(img_train, label_train, epochs=50, validation_split=0.2)val_acc_per_epoch = history.history['val_accuracy']
best_epoch = val_acc_per_epoch.index(max(val_acc_per_epoch)) + 1
print('Best epoch: %d' % (best_epoch,))#最佳循环数不再进行训练
hypermodel = tuner.hypermodel.build(best_hps)# Retrain the model
hypermodel.fit(img_train, label_train, epochs=best_epoch, validation_split=0.2)#测试数据上评估超模型
eval_result = hypermodel.evaluate(img_test, label_test)
print("[test loss, test accuracy]:", eval_result)

09_keras_Tuner使用keras Tuner调整超参数(超参数优化)相关推荐

使用keras Tuner调整超参数
Keras Tuner是一个库,可以为TensorFlow程序选择最佳的超参数集.为机器学习(ML)应用程序选择正确的超参数集的过程称为超参数调整或超调整. 超参数是控制训练过程和ML模型拓扑结构的变 ...
TensorFlow2中使用Keras Tuner搜索网络的超参数
1. 导入所需的库 import tensorflow as tf import kerastuner as kt import IPythonfor i in [tf, kt]:print(i.__ ...
tensorflow官方Blog-使用Keras Tuner超参数优化框架进行超参数调整 ,具体实现版本
文章目录进入正题,keras tuner超参数优化框架模型构建def build_model(hp): 实例化tuner 加载数据集,进行超参数搜索tuner.search() 找到最佳的模型tu ...
Tensorflow2.0学习-Keras Tuner 妙用 (六)
文章目录 Keras Tuner调整超参数引包数据准备模型准备跑起来 Keras Tuner调整超参数 Keras Tuner 是一个库,可帮助您为 TensorFlow 程序选择最佳的超参数 ...
Keras Tuner自动调参工具使用入门教程
主体是翻译的Keras Tuner的说明:https://keras-team.github.io/keras- tuner/documentation/tuners/ github地址:https: ...
机器学习笔记 - 使用Keras Tuner进行自动化超参数调整
一.什么是超参数调整? 在机器学习工作流程中,您已经根据对数据集的先验分析为模型选择或提取了特征和目标 - 可能使用了PCA等降维技术. 训练机器学习模型时会进行如下迭代: 在训练开始之前,以随机或几 ...
用keras tuner 来优化tensorflw超参数
用keras tuner 来优化tensorflw超参数安装依赖包 !pip install --upgrade pip 导入模块 import tensorflow as tf from tens ...
Keras Tuner模型自动超参数调优
Keras Tuner安装 pip install keras-tuner from tensorflow.keras import layers from tensorflow import ker ...
sklearn自学指南(part61)--调整估计器的超参数
学习笔记,仅供参考,有错必纠文章目录调整估计器的超参数详尽的网格搜索随机参数优化连续减半法寻找最优参数选择`min_resources`和候选数[(略)](https://scikit-l ...

09_keras_Tuner使用keras Tuner调整超参数(超参数优化)

09_keras_Tuner使用keras Tuner调整超参数(超参数优化)相关推荐

最新文章

热门文章