Python 基于tensorflow keras模型的动态年代数

我想有一个神经网络，它可以训练直到达到一定的精确度。是否有一个内置的函数来代替单独运行每个历元，直到达到精度

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer=tf.train.AdamOptimizer(), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

epochs = 0
train_acc = 0
while 1-train_acc > .01:
    model.fit(train_images, train_labels,  initial_epoch=epochs, epochs=epochs+1,verbose=0)
    epochs += 1
    train_loss, train_acc = model.evaluate(train_images,train_labels)

---

不，没有任何内置函数来执行此操作。但是，您可以轻松定义一个自定义回调，该回调在训练精度达到某个阈值时停止训练：

import keras


class AccuracyStopping(keras.callbacks.Callback):
    def __init__(self, acc_threshold):
        super(AccuracyStopping, self).__init__()
        self._acc_threshold = acc_threshold

    def on_epoch_end(self, batch, logs={}):
        train_acc = logs.get('acc')
        self.model.stop_training = 1 - train_acc <= self._acc_threshold

import numpy as np
from keras.layers import Dense
from keras.models import Sequential

x = np.random.normal(size=(100,))
y = x > 0

model = Sequential()
model.add(Dense(1, input_dim=1, activation='sigmoid'))
model.compile('sgd', 'binary_crossentropy', metrics=['accuracy'])

acc_callback = AccuracyStopping(0.05)
model.fit(x, y, batch_size=8, epochs=1000, callbacks=[acc_callback])