写点什么

Introduction to the Keras Tuner

用户头像
毛显新
关注
发布于: 2021 年 07 月 31 日

Overview

The Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyperparameters for your machine learning (ML) application is called hyperparameter tuning or hypertuning.

Hyperparameters are the variables that govern the training process and the topology of an ML model. These variables remain constant over the training process and directly impact the performance of your ML program. Hyperparameters are of two types:

  1. Model hyperparameters which influence model selection such as the number and width of hidden layers

  2. Algorithm hyperparameters which influence the speed and quality of the learning algorithm such as the learning rate for Stochastic Gradient Descent (SGD) and the number of nearest neighbors for a k Nearest Neighbors (KNN) classifier

In this tutorial, you will use the Keras Tuner to perform hypertuning for an image classification application.

Setup

import tensorflow as tffrom tensorflow import keras
复制代码


import keras_tuner as kt
复制代码

Download and prepare the dataset

In this tutorial, you will use the Keras Tuner to find the best hyperparameters for a machine learning model that classifies images of clothing from the Fashion MNIST dataset.

Load the data.

(img_train, label_train), (img_test, label_test) = keras.datasets.fashion_mnist.load_data()
复制代码


# Normalize pixel values between 0 and 1img_train = img_train.astype('float32') / 255.0img_test = img_test.astype('float32') / 255.0
复制代码

Define the model

When you build a model for hypertuning, you also define the hyperparameter search space in addition to the model architecture. The model you set up for hypertuning is called a hypermodel.

You can define a hypermodel through two approaches:

  • By using a model builder function

  • By subclassing the HyperModel class of the Keras Tuner API

You can also use two pre-defined HyperModel classes - HyperXception and HyperResNet for computer vision applications.

In this tutorial, you use a model builder function to define the image classification model. The model builder function returns a compiled model and uses hyperparameters you define inline to hypertune the model.

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 32-512  hp_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 0.0001  hp_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
复制代码

Instantiate the tuner and perform hypertuning

Instantiate the tuner to perform the hypertuning. The Keras Tuner has four tuners available - RandomSearch, Hyperband, BayesianOptimization, and Sklearn. In this tutorial, you use the Hyperband tuner.

To instantiate the Hyperband tuner, you must specify the hypermodel, the objective to optimize and the maximum number of epochs to train (max_epochs).

tuner = kt.Hyperband(model_builder,                     objective='val_accuracy',                     max_epochs=10,                     factor=3,                     directory='my_dir',                     project_name='intro_to_kt')
复制代码

The Hyperband tuning algorithm uses adaptive resource allocation and early-stopping to quickly converge on a high-performing model. This is done using a sports championship style bracket. The algorithm trains a large number of models for a few epochs and carries forward only the top-performing half of models to the next round. Hyperband determines the number of models to train in a bracket by computing 1 + logfactor(max_epochs) and rounding it up to the nearest integer.

Create a callback to stop training early after reaching a certain value for the validation loss.

stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5)
复制代码

Run the hyperparameter search. The arguments for the search method are the same as those used for tf.keras.model.fit in addition to the callback above.

tuner.search(img_train, label_train, epochs=50, validation_split=0.2, callbacks=[stop_early])# Get the optimal hyperparametersbest_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-connectedlayer is {best_hps.get('units')} and the optimal learning rate for the optimizeris {best_hps.get('learning_rate')}.""")
复制代码

Train the model

Find the optimal number of epochs to train the model with the hyperparameters obtained from the search.

# Build the model with the optimal hyperparameters and train it on the data for 50 epochsmodel = 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)) + 1print('Best epoch: %d' % (best_epoch,))
复制代码

Re-instantiate the hypermodel and train it with the optimal number of epochs from above.

hypermodel = tuner.hypermodel.build(best_hps)# Retrain the modelhypermodel.fit(img_train, label_train, epochs=best_epoch, validation_split=0.2)
复制代码

To finish this tutorial, evaluate the hypermodel on the test data.

eval_result = hypermodel.evaluate(img_test, label_test)print("[test loss, test accuracy]:", eval_result)
复制代码

The my_dir/intro_to_kt directory contains detailed logs and checkpoints for every trial (model configuration) run during the hyperparameter search. If you re-run the hyperparameter search, the Keras Tuner uses the existing state from these logs to resume the search. To disable this behavior, pass an additional overwrite=True argument while instantiating the tuner.

代码地址: https://codechina.csdn.net/csdn_codechina/enterprise_technology/-/blob/master/Hypertuner/Introduction%20to%20the%20Keras%20Tuner.ipynb

用户头像

毛显新

关注

还未添加个人签名 2021.07.26 加入

还未添加个人简介

评论

发布
暂无评论
Introduction to the Keras Tuner