keras.callbacks.ModelCheckpoint(self.checkpoint_path,
                                verbose=0, save_weights_only=True,mode="max",save_best_only=True),

預設是每一次poch,但是這樣硬碟空間很快就會被耗光. 

將save_best_only 設定為True使其只儲存最好的模型,值得一提的是其記錄的acc是來自於一個monitor_op,其預設為"val_loss",其實現是取self.best為 -np.Inf.  所以,第一次的訓練結果總是被儲存.

mode模式自動為auto 和 max一樣,還有一個min的選項...應該是loss沒有負號的時候用的....

https://keras.io/callbacks/  瀏覽上面的文件.

# Print the batch number at the beginning of every batch.
batch_print_callback = LambdaCallback(
    on_batch_begin=lambda batch,logs: print(batch))

# Stream the epoch loss to a file in JSON format. The file content
# is not well-formed JSON but rather has a JSON object per line.
import json
json_log = open('loss_log.json', mode='wt', buffering=1)
json_logging_callback = LambdaCallback(
    on_epoch_end=lambda epoch, logs: json_log.write(
        json.dumps({'epoch': epoch, 'loss': logs['loss']}) + '\n'),
    on_train_end=lambda logs: json_log.close()
)

# Terminate some processes after having finished model training.
processes = ...
cleanup_callback = LambdaCallback(
    on_train_end=lambda logs: [
        p.terminate() for p in processes if p.is_alive()])

model.fit(...,
          callbacks=[batch_print_callback,
                     json_logging_callback,
                     cleanup_callback])
 

Keras的callback 一般在model.fit函式使用,由於Keras的便利性.有很多模型策略以及日誌的策略.

比如 當loss不再變化時停止訓練

keras.callbacks.EarlyStopping(monitor='val_loss', min_delta=0, patience=0, verbose=0, mode='auto', baseline=None, restore_best_weights=False)

比如日誌傳送遠端伺服器等,以及自適應的學習率scheduler.

確實很便利....