Keras具有CSVLogger回调，该回调似乎完全可以满足您的需要；从文档:

Keras has the CSVLogger callback which appears to do exactly what you need; from the documentation:

将纪元结果流式传输到CSV文件的回调.

Callback that streams epoch results to a CSV file.

它具有用于添加到文件的附加参数.再次，从文档中:

It has an append parameter for adding to the file. Again, from the documentation:

追加:布尔值.True:如果文件存在，则追加(用于继续培训).False:覆盖现有文件

append: Boolean. True: append if file exists (useful for continuing training). False: overwrite existing file

来自keras.callbacks的

from keras.callbacks import CSVLogger

csv_logger = CSVLogger("model_history_log.csv", append=True)
model.fit_generator(...,callbacks=[csv_logger])