zoukankan      html  css  js  c++  java
  • keras检查点的保存

    来自 keras的文档:https://keras.io/callbacks/#callback

    ModelCheckpoint

    keras.callbacks.ModelCheckpoint(filepath, monitor='val_loss', verbose=0, save_best_only=False, save_weights_only=False, mode='auto', period=1)
    

    Save the model after every epoch.

    filepath can contain named formatting options, which will be filled with the values of epoch and keys in logs (passed in on_epoch_end).

    For example: if filepath is weights.{epoch:02d}-{val_loss:.2f}.hdf5, then the model checkpoints will be saved with the epoch number and the validation loss in the filename.

    Arguments

    • filepath: string, path to save the model file.
    • monitor: quantity to monitor.
    • verbose: verbosity mode, 0 or 1.
    • save_best_only: if save_best_only=True, the latest best model according to the quantity monitored will not be overwritten.
    • save_weights_only: if True, then only the model's weights will be saved (model.save_weights(filepath)), else the full model is saved (model.save(filepath)).
    • mode: one of {auto, min, max}. If save_best_only=True, the decision to overwrite the current save file is made based on either the maximization or the minimization of the monitored quantity. For val_acc, this should be max, for val_loss this should be min, etc. In automode, the direction is automatically inferred from the name of the monitored quantity.
    • period: Interval (number of epochs) between checkpoints.
  • 相关阅读:
    C语言I博客作业02
    C语言I—2019秋作业01
    C语言I作业10
    C语言I作业09
    C语言I作业08
    C语言I作业07
    C语言I|作业06
    C语言I作业05
    C语言I作业004:第八周作业
    c语言|作业003
  • 原文地址:https://www.cnblogs.com/superxuezhazha/p/10815507.html
Copyright © 2011-2022 走看看