如何在 Keras 中创建自定义回调？

Question

我有兴趣在拟合我的 keras 模型时创建回调。更详细地说，我想在每次 epoch 结束时从带有 val_acc 的机器人电报中收到一条消息。我知道你可以添加一个 callback_list 作为参数，classifier.fit()但是许多回调是由 keras 预先构建的，我不知道如何添加自定义的。

谢谢！

Answer 1

这是我如何向回调添加验证准确性的示例：

class AccuracyHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.acc = []

    def on_epoch_end(self, batch, logs={}):
        self.acc.append(logs.get('val_acc'))

history = AccuracyHistory()

model.fit(x, y,
          ...
          callbacks=[history])

Answer 2

例如，我提供了带有 F1 指标的自定义回调。它在每个 epoch 结束时计算 F1，不是分批计算，而是针对所有通过的训练数据（以及可选的验证）。可以使用其他所有指标轻松自定义

class F1History(tf.keras.callbacks.Callback):

    def __init__(self, train, validation=None):
        super(F1History, self).__init__()
        self.validation = validation
        self.train = train

    def on_epoch_end(self, epoch, logs={}):

        logs['F1_score_train'] = float('-inf')
        X_train, y_train = self.train[0], self.train[1]
        y_pred = (self.model.predict(X_train).ravel()>0.5)+0
        score = f1_score(y_train, y_pred)       

        if (self.validation):
            logs['F1_score_val'] = float('-inf')
            X_valid, y_valid = self.validation[0], self.validation[1]
            y_val_pred = (self.model.predict(X_valid).ravel()>0.5)+0
            val_score = f1_score(y_valid, y_val_pred)
            logs['F1_score_train'] = np.round(score, 5)
            logs['F1_score_val'] = np.round(val_score, 5)
        else:
            logs['F1_score_train'] = np.round(score, 5)

适合：

es = EarlyStopping(patience=3, verbose=1, min_delta=0.001, monitor='F1_score_val', mode='max', restore_best_weights=True)
model.fit(x_train,y_train, epochs=10, 
          callbacks=[F1History(train=(x_train,y_train),validation=(x_val,y_val)),es])