TensorFlow Addons 回调：TimeStopping

在 TensorFlow.org 上查看

在 Google Colab 中运行

在 GitHub 上查看源代码

下载笔记本

概述

此笔记本将演示如何使用 TensorFlow Addons 中的 TimeStopping 回调。

设置

import tensorflow_addons as tfa

from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten

导入并归一化数据

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# normalize data
x_train, x_test = x_train / 255.0, x_test / 255.0

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11493376/11490434 [==============================] - 0s 0us/step

构建简单的 MNIST CNN 模型

# build the model using the Sequential API
model = Sequential()
model.add(Flatten(input_shape=(28, 28)))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))

model.compile(optimizer='adam',
              loss = 'sparse_categorical_crossentropy',
              metrics=['accuracy'])

简单的 TimeStopping 用法

# initialize TimeStopping callback 
time_stopping_callback = tfa.callbacks.TimeStopping(seconds=5, verbose=1)

# train the model with tqdm_callback
# make sure to set verbose = 0 to disable
# the default progress bar.
model.fit(x_train, y_train,
          batch_size=64,
          epochs=100,
          callbacks=[time_stopping_callback],
          validation_data=(x_test, y_test))

Train on 60000 samples, validate on 10000 samples
Epoch 1/100
60000/60000 [==============================] - 5s 81us/sample - loss: 0.3432 - accuracy: 0.9003 - val_loss: 0.1601 - val_accuracy: 0.9529
Epoch 2/100
60000/60000 [==============================] - 4s 67us/sample - loss: 0.1651 - accuracy: 0.9515 - val_loss: 0.1171 - val_accuracy: 0.9642
Timed stopping at epoch 2 after training for 0:00:05

<tensorflow.python.keras.callbacks.History at 0x7f91e075fe80>