Python tensorflow.python.estimator.estimator._load_global_step_from_checkpoint_dir() Examples

The following are 5 code examples of tensorflow.python.estimator.estimator._load_global_step_from_checkpoint_dir(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.estimator.estimator , or try the search function .
Example #1
Source File: preview.py    From cwavegan with MIT License 4 votes vote down vote up 
def main(argv):
    del argv
    tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver(
        FLAGS.tpu,
        zone=FLAGS.tpu_zone,
        project=FLAGS.gcp_project)

    config = tf.contrib.tpu.RunConfig(
        cluster=tpu_cluster_resolver,
        model_dir=FLAGS.model_dir,
        tpu_config=tf.contrib.tpu.TPUConfig(
            num_shards=FLAGS.num_shards,
            iterations_per_loop=FLAGS.iterations_per_loop))

    # Set module-level global variable so that model_fn and input_fn can be
    # identical for each different kind of dataset and model
    global dataset, model
    dataset = bias_input
    model = bias_model

    # TPU-based estimator used for TRAIN and EVAL
    est = tf.contrib.tpu.TPUEstimator(
        model_fn=model_fn,
        use_tpu=FLAGS.use_tpu,
        config=config,
        train_batch_size=FLAGS.batch_size,
        eval_batch_size=FLAGS.batch_size)

    # CPU-based estimator used for PREDICT (generating images)
    cpu_est = tf.contrib.tpu.TPUEstimator(
        model_fn=model_fn,
        use_tpu=False,
        config=config,
        predict_batch_size=_NUM_VIZ_AUDIO)

    current_step = estimator._load_global_step_from_checkpoint_dir(
        FLAGS.model_dir)  # pylint: disable=protected-access,line-too-long
    tf.logging.info('Starting training for %d steps, current step: %d' %
                    (FLAGS.train_steps, current_step))

    # Render some generated images
    G_z = cpu_est.predict(input_fn=noise_input_fn)
    G_z = [p['generated_audio'][:, :] for p in G_z]
    G_z = np.array(G_z)
    preview_dir = './preview'
    if not os.path.isdir(preview_dir):
        os.makedirs(preview_dir)

    for i in range(len(G_z)):
      audio = np.int16(G_z[i]/np.max(np.abs(G_z[i])) * 32767)
      preview_fp = os.path.join(preview_dir, '{}_{}_{}.wav'.format(str(i % 10), str(current_step), str(i)))
      wavwrite(preview_fp, _FS, audio)

    tf.logging.info('Finished generating images')
Example #2
Source File: tpu_main.py    From cwavegan with MIT License 4 votes vote down vote up 
def main(argv):
  del argv

  global is_bias
  global noise_dim
  is_bias = True if FLAGS.condition == 'bias' else False
  noise_dim = 100 if is_bias else 90

  tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver(
      FLAGS.tpu,
      zone=FLAGS.tpu_zone,
      project=FLAGS.gcp_project)

  config = tf.contrib.tpu.RunConfig(
      cluster=tpu_cluster_resolver,
      model_dir=FLAGS.model_dir,
      keep_checkpoint_max=None,
      tpu_config=tf.contrib.tpu.TPUConfig(
          num_shards=FLAGS.num_shards,
          iterations_per_loop=FLAGS.iterations_per_loop))

  # Set module-level global variable so that model_fn and input_fn can be
  # identical for each different kind of dataset and model
  global dataset, model
  dataset = tpu_input
  model = tpu_model
  
  # TPU-based estimator used for TRAIN and EVAL
  est = tf.contrib.tpu.TPUEstimator(
      model_fn=model_fn,
      use_tpu=FLAGS.use_tpu,
      config=config,
      train_batch_size=FLAGS.batch_size,
      eval_batch_size=FLAGS.batch_size)

  # CPU-based estimator used for PREDICT (generating images)
  cpu_est = tf.contrib.tpu.TPUEstimator(
      model_fn=model_fn,
      use_tpu=False,
      config=config,
      predict_batch_size=_NUM_VIZ_AUDIO)

  current_step = estimator._load_global_step_from_checkpoint_dir(FLAGS.model_dir)   # pylint: disable=protected-access,line-too-long
  tf.logging.info('Starting training for %d steps, current step: %d' %
                  (FLAGS.train_steps, current_step))

  while current_step < FLAGS.train_steps:
    next_checkpoint = min(current_step + FLAGS.train_steps_per_eval,
                          FLAGS.train_steps)
    est.train(input_fn=generate_input_fn(True),
             max_steps=next_checkpoint)
    current_step = next_checkpoint
    tf.logging.info('Finished training step %d' % current_step)

    if FLAGS.eval_loss:
      # Evaluate loss on test set
      metrics = est.evaluate(input_fn=generate_input_fn(False),
                             steps=dataset.NUM_EVAL_IMAGES // FLAGS.batch_size)
      tf.logging.info('Finished evaluating')
      tf.logging.info(metrics)
Example #3
Source File: main.py    From training_results_v0.5 with Apache License 2.0 4 votes vote down vote up 
def train_and_eval(deeplab_estimator, train_dataset, eval_dataset,
                   num_batches_per_epoch):
  """Interleaves training and evaluation."""
  # pylint: disable=protected-access
  current_step = estimator._load_global_step_from_checkpoint_dir(
      FLAGS.model_dir)
  tf.logging.info('Training for %d steps (%.2f epochs in total). Current'
                  ' step %d.' %
                  (FLAGS.train_steps,
                   FLAGS.train_steps / num_batches_per_epoch,
                   current_step))
  start_timestamp = time.time()
  while current_step < FLAGS.train_steps:
    # Train for up to steps_per_eval number of steps. At the end of training,
    # a checkpoint will be written to --model_dir.
    next_checkpoint = min(current_step + FLAGS.steps_per_eval,
                          FLAGS.train_steps)

    train_input_fn = data_pipeline.InputReader(
        train_dataset,
        FLAGS.train_split,
        is_training=True,
        model_variant=FLAGS.model_variant
    )
    deeplab_estimator.train(
        input_fn=train_input_fn,
        max_steps=next_checkpoint
    )
    current_step = next_checkpoint

    elapsed_time = int(time.time() - start_timestamp)
    tf.logging.info('Finished training up to step %d. Elapsed seconds %d.' %
                    (current_step, elapsed_time))

    tf.logging.info('Starting to evaluate.')

    eval_input_fn = data_pipeline.InputReader(
        eval_dataset,
        FLAGS.eval_split,
        is_training=False,
        model_variant=FLAGS.model_variant
    )
    eval_results = deeplab_estimator.evaluate(
        input_fn=eval_input_fn,
        steps=eval_dataset.num_samples // FLAGS.eval_batch_size
    )
    tf.logging.info('Eval results: %s' % eval_results)
Example #4
Source File: main.py    From tpu_models with Apache License 2.0 4 votes vote down vote up 
def train_and_eval(deeplab_estimator, train_dataset, eval_dataset,
                   num_batches_per_epoch):
  """Interleaves training and evaluation."""
  # pylint: disable=protected-access
  current_step = estimator._load_global_step_from_checkpoint_dir(
      FLAGS.model_dir)
  tf.logging.info('Training for %d steps (%.2f epochs in total). Current'
                  ' step %d.' %
                  (FLAGS.train_steps,
                   FLAGS.train_steps / num_batches_per_epoch,
                   current_step))
  start_timestamp = time.time()
  while current_step < FLAGS.train_steps:
    # Train for up to steps_per_eval number of steps. At the end of training,
    # a checkpoint will be written to --model_dir.
    next_checkpoint = min(current_step + FLAGS.steps_per_eval,
                          FLAGS.train_steps)

    train_input_fn = data_pipeline.InputReader(
        train_dataset,
        FLAGS.train_split,
        is_training=True,
        model_variant=FLAGS.model_variant
    )
    deeplab_estimator.train(
        input_fn=train_input_fn,
        max_steps=next_checkpoint
    )
    current_step = next_checkpoint

    elapsed_time = int(time.time() - start_timestamp)
    tf.logging.info('Finished training up to step %d. Elapsed seconds %d.' %
                    (current_step, elapsed_time))

    tf.logging.info('Starting to evaluate.')

    eval_input_fn = data_pipeline.InputReader(
        eval_dataset,
        FLAGS.eval_split,
        is_training=False,
        model_variant=FLAGS.model_variant
    )
    eval_results = deeplab_estimator.evaluate(
        input_fn=eval_input_fn,
        steps=eval_dataset.num_samples // FLAGS.eval_batch_size
    )
    tf.logging.info('Eval results: %s' % eval_results)
Example #5
Source File: main.py    From class-balanced-loss with MIT License 4 votes vote down vote up 
def train_and_eval(deeplab_estimator, train_dataset, eval_dataset,
                   num_batches_per_epoch):
  """Interleaves training and evaluation."""
  # pylint: disable=protected-access
  current_step = estimator._load_global_step_from_checkpoint_dir(
      FLAGS.model_dir)
  tf.logging.info('Training for %d steps (%.2f epochs in total). Current'
                  ' step %d.' %
                  (FLAGS.train_steps,
                   FLAGS.train_steps / num_batches_per_epoch,
                   current_step))
  start_timestamp = time.time()
  while current_step < FLAGS.train_steps:
    # Train for up to steps_per_eval number of steps. At the end of training,
    # a checkpoint will be written to --model_dir.
    next_checkpoint = min(current_step + FLAGS.steps_per_eval,
                          FLAGS.train_steps)

    train_input_fn = data_pipeline.InputReader(
        train_dataset,
        FLAGS.train_split,
        is_training=True,
        model_variant=FLAGS.model_variant
    )
    deeplab_estimator.train(
        input_fn=train_input_fn,
        max_steps=next_checkpoint
    )
    current_step = next_checkpoint

    elapsed_time = int(time.time() - start_timestamp)
    tf.logging.info('Finished training up to step %d. Elapsed seconds %d.' %
                    (current_step, elapsed_time))

    tf.logging.info('Starting to evaluate.')

    eval_input_fn = data_pipeline.InputReader(
        eval_dataset,
        FLAGS.eval_split,
        is_training=False,
        model_variant=FLAGS.model_variant
    )
    eval_results = deeplab_estimator.evaluate(
        input_fn=eval_input_fn,
        steps=eval_dataset.num_samples // FLAGS.eval_batch_size
    )
    tf.logging.info('Eval results: %s' % eval_results)