tensorflow中设置保存checkpoint的最大数量

最新推荐文章于 2022-11-17 10:15:51 发布

橘的皮瓜着披。

最新推荐文章于 2022-11-17 10:15:51 发布

阅读量4.3k

点赞数 1

分类专栏： tensorflow

本文链接：https://blog.csdn.net/lfs666666/article/details/85377406

版权

tensorflow 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

tensorflow中设置保存checkpoint的最大数量

1、例如：

  # Set up a RunConfig to only save checkpoints once per training cycle.
  run_config = tf.estimator.RunConfig(save_checkpoints_secs=1e9,keep_checkpoint_max = 10)
  model = tf.estimator.Estimator(
      model_fn=deeplab_model_focal_class_imbalance_loss_adaptive.deeplabv3_plus_model_fn,
      model_dir=FLAGS.model_dir,
      config=run_config,
      params={
          'output_stride': FLAGS.output_stride,
          'batch_size': FLAGS.batch_size,
          'base_architecture': FLAGS.base_architecture,
          'pre_trained_model': FLAGS.pre_trained_model,
          'batch_norm_decay': _BATCH_NORM_DECAY,
          'num_classes': _NUM_CLASSES,
          'tensorboard_images_max_outputs': FLAGS.tensorboard_images_max_outputs,
          'weight_decay': FLAGS.weight_decay,
          'learning_rate_policy': FLAGS.learning_rate_policy,
          'num_train': _NUM_IMAGES['train'],
          'initial_learning_rate': FLAGS.initial_learning_rate,
          'max_iter': FLAGS.max_iter,
          'end_learning_rate': FLAGS.end_learning_rate,
          'power': _POWER,
          'momentum': _MOMENTUM,
          'freeze_batch_norm': FLAGS.freeze_batch_norm,
          'initial_global_step': FLAGS.initial_global_step
      })