据我所知，model.fit（epochs=NUM_EPOCHS）不会为每个epoch重置指标。我的指标和model.fit（）代码看起来像这样（简化）：

import tensorflow as tf
from tensorflow.keras import applications

NUM_CLASSES = 4
INPUT_SHAPE = (256, 256, 3)
MODELS = {
    'DenseNet121': applications.DenseNet121,
    'DenseNet169': applications.DenseNet169
}
REDUCE_LR_PATIENCE = 2
REDUCE_LR_FACTOR = 0.7
EARLY_STOPPING_PATIENCE = 4

for modelName, model in MODELS.items():

    loadedModel = model(include_top=False, weights='imagenet',
                        pooling='avg', input_shape=INPUT_SHAPE)

    sequentialModel = tf.keras.models.Sequential()
    sequentialModel.add(loadedModel)
    sequentialModel.add(tf.keras.layers.Dense(NUM_CLASSES, activation='softmax'))

    aucCurve = tf.keras.metrics.AUC(curve = 'ROC', multi_label = True)
    categoricalAccuracy = tf.keras.metrics.CategoricalAccuracy()
    F1Score  = tfa.metrics.F1Score(num_classes = NUM_CLASSES, average = 'macro', threshold = None)
    metrics = [aucCurve, categoricalAccuracy, F1Score]

    sequentialModel.compile(metrics=metrics)

    callbacks = [
    tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', patience=REDUCE_LR_PATIENCE, verbose=1, factor=REDUCE_LR_FACTOR),
    tf.keras.callbacks.EarlyStopping(monitor='val_loss', verbose=1, patience=EARLY_STOPPING_PATIENCE),
    tf.keras.callbacks.ModelCheckpoint(filepath=modelName + '_epoch-{epoch:02d}.h5', monitor='val_loss', save_best_only=False, verbose=1),
    tf.keras.callbacks.CSVLogger(modelName + '_training.csv')]

    sequentialModel.fit(epochs=NUM_EPOCHS)

字符串
也许我可以通过在NUM_EPOCHS范围内执行for循环来重置指标，并在for循环中初始化指标，但我不确定这是否是一个好的解决方案。此外，我有ModelCheckpoint和CSVLogger回调，它们需要来自model.fit（）的epoch编号，所以如果我执行for循环，它不会真正工作。
你对如何重置每个epoch的指标有什么建议吗？在NUM_EPOCHS范围内进行for循环是唯一的解决方案吗？谢谢。