Python common.IMAGE属性代码示例

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _get_data(data_provider, dataset_split):
  """Gets data from data provider.

  Args:
    data_provider: An object of slim.data_provider.
    dataset_split: Dataset split.

  Returns:
    image: Image Tensor.
    label: Label Tensor storing segmentation annotations.
    image_name: Image name.
    height: Image height.
    width: Image width.

  Raises:
    ValueError: Failed to find label.
  """
  if common.LABELS_CLASS not in data_provider.list_items():
    raise ValueError('Failed to find labels.')

  image, height, width = data_provider.get(
      [common.IMAGE, common.HEIGHT, common.WIDTH])

  # Some datasets do not contain image_name.
  if common.IMAGE_NAME in data_provider.list_items():
    image_name, = data_provider.get([common.IMAGE_NAME])
  else:
    image_name = tf.constant('')

  label = None
  if dataset_split != common.TEST_SET:
    label, = data_provider.get([common.LABELS_CLASS])

  return image, label, image_name, height, width 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def testPascalVocSegTestData(self):
    dataset = data_generator.Dataset(
        dataset_name='pascal_voc_seg',
        split_name='val',
        dataset_dir=
        'deeplab/testing/pascal_voc_seg',
        batch_size=1,
        crop_size=[3, 3],  # Use small size for testing.
        min_resize_value=3,
        max_resize_value=3,
        resize_factor=None,
        min_scale_factor=0.01,
        max_scale_factor=2.0,
        scale_factor_step_size=0.25,
        is_training=False,
        model_variant='mobilenet_v2')

    self.assertAllEqual(dataset.num_of_classes, 21)
    self.assertAllEqual(dataset.ignore_label, 255)

    num_of_images = 3
    with self.test_session() as sess:
      iterator = dataset.get_one_shot_iterator()

      for i in range(num_of_images):
        batch = iterator.get_next()
        batch, = sess.run([batch])
        image_attributes = _get_attributes_of_image(i)

        self.assertAllEqual(batch[common.IMAGE][0], image_attributes.image)
        self.assertAllEqual(batch[common.LABEL][0], image_attributes.label)
        self.assertEqual(batch[common.HEIGHT][0], image_attributes.height)
        self.assertEqual(batch[common.WIDTH][0], image_attributes.width)
        self.assertEqual(batch[common.IMAGE_NAME][0],
                         image_attributes.image_name)

      # All data have been read.
      with self.assertRaisesRegexp(tf.errors.OutOfRangeError, ''):
        sess.run([iterator.get_next()]) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _log_summaries(input_image, label, num_of_classes, output):
  """Logs the summaries for the model.

  Args:
    input_image: Input image of the model. Its shape is [batch_size, height,
      width, channel].
    label: Label of the image. Its shape is [batch_size, height, width].
    num_of_classes: The number of classes of the dataset.
    output: Output of the model. Its shape is [batch_size, height, width].
  """
  # Add summaries for model variables.
  for model_var in tf.model_variables():
    tf.summary.histogram(model_var.op.name, model_var)

  # Add summaries for images, labels, semantic predictions.
  if FLAGS.save_summaries_images:
    tf.summary.image('samples/%s' % common.IMAGE, input_image)

    # Scale up summary image pixel values for better visualization.
    pixel_scaling = max(1, 255 // num_of_classes)
    summary_label = tf.cast(label * pixel_scaling, tf.uint8)
    tf.summary.image('samples/%s' % common.LABEL, summary_label)

    predictions = tf.expand_dims(tf.argmax(output, 3), -1)
    summary_predictions = tf.cast(predictions * pixel_scaling, tf.uint8)
    tf.summary.image('samples/%s' % common.OUTPUT_TYPE, summary_predictions) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _build_deeplab(self, inputs_queue, outputs_to_num_classes, ignore_label):
    """Builds a clone of DeepLab.

    Args:
      inputs_queue: A prefetch queue for images and labels.
      outputs_to_num_classes: A map from output type to the number of classes.
        For example, for the task of semantic segmentation with 21 semantic
        classes, we would have outputs_to_num_classes['semantic'] = 21.
      ignore_label: Ignore label.

    Returns:
      A map of maps from output_type (e.g., semantic prediction) to a
        dictionary of multi-scale logits names to logits. For each output_type,
        the dictionary has keys which correspond to the scales and values which
        correspond to the logits. For example, if `scales` equals [1.0, 1.5],
        then the keys would include 'merged_logits', 'logits_1.00' and
        'logits_1.50'.
    """
    training_configs = self.training_configs

    samples = inputs_queue.dequeue()

    model_options = common.ModelOptions(
        outputs_to_num_classes=outputs_to_num_classes,
        crop_size=training_configs['learning_params']['train_crop_size'],
        atrous_rates=training_configs['fine_tuning_params']['atrous_rates'],
        output_stride=training_configs['fine_tuning_params']['output_stride'])
    outputs_to_scales_to_logits = model.multi_scale_logits(
        samples[common.IMAGE],
        model_options=model_options,
        image_pyramid=training_configs['common']['image_pyramid'],
        weight_decay=training_configs['learning_params']['weight_decay'],
        is_training=True,
        fine_tune_batch_norm=training_configs['fine_tuning_params']['fine_tune_batch_norm'])

    for output, num_classes in outputs_to_num_classes.items():
      train_utils.add_softmax_cross_entropy_loss_for_each_scale(
          outputs_to_scales_to_logits[output],
          samples[common.LABEL],
          num_classes,
          ignore_label,
          loss_weight=1.0,
          upsample_logits=training_configs['learning_params']['upsample_logits'],
          scope=output)

    return outputs_to_scales_to_logits 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _build_deeplab(inputs_queue, outputs_to_num_classes, ignore_label):
  """Builds a clone of DeepLab.

  Args:
    inputs_queue: A prefetch queue for images and labels.
    outputs_to_num_classes: A map from output type to the number of classes.
      For example, for the task of semantic segmentation with 21 semantic
      classes, we would have outputs_to_num_classes['semantic'] = 21.
    ignore_label: Ignore label.

  Returns:
    A map of maps from output_type (e.g., semantic prediction) to a
      dictionary of multi-scale logits names to logits. For each output_type,
      the dictionary has keys which correspond to the scales and values which
      correspond to the logits. For example, if `scales` equals [1.0, 1.5],
      then the keys would include 'merged_logits', 'logits_1.00' and
      'logits_1.50'.
  """
  samples = inputs_queue.dequeue()

  # add name to input and label nodes so we can add to summary
  samples[common.IMAGE] = tf.identity(samples[common.IMAGE], name = common.IMAGE)
  samples[common.LABEL] = tf.identity(samples[common.LABEL], name = common.LABEL)

  model_options = common.ModelOptions(
      outputs_to_num_classes=outputs_to_num_classes,
      crop_size=FLAGS.train_crop_size,
      atrous_rates=FLAGS.atrous_rates,
      output_stride=FLAGS.output_stride)
  outputs_to_scales_to_logits = model.multi_scale_logits(
      samples[common.IMAGE],
      model_options=model_options,
      image_pyramid=FLAGS.image_pyramid,
      weight_decay=FLAGS.weight_decay,
      is_training=True,
      fine_tune_batch_norm=FLAGS.fine_tune_batch_norm)

  # add name to graph node so we can add to summary
  outputs_to_scales_to_logits[common.OUTPUT_TYPE][model._MERGED_LOGITS_SCOPE] = tf.identity( 
    outputs_to_scales_to_logits[common.OUTPUT_TYPE][model._MERGED_LOGITS_SCOPE],
    name = common.OUTPUT_TYPE
  )

  for output, num_classes in six.iteritems(outputs_to_num_classes):
    train_utils.add_softmax_cross_entropy_loss_for_each_scale(
        outputs_to_scales_to_logits[output],
        samples[common.LABEL],
        num_classes,
        ignore_label,
        loss_weight=1.0,
        upsample_logits=FLAGS.upsample_logits,
        scope=output)

  return outputs_to_scales_to_logits 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _preprocess_image(self, sample):
    """Preprocesses the image and label.

    Args:
      sample: A sample containing image and label.

    Returns:
      sample: Sample with preprocessed image and label.

    Raises:
      ValueError: Ground truth label not provided during training.
    """
    image = sample[common.IMAGE]
    label = sample[common.LABELS_CLASS]

    original_image, image, label = input_preprocess.preprocess_image_and_label(
        image=image,
        label=label,
        crop_height=self.crop_size[0],
        crop_width=self.crop_size[1],
        min_resize_value=self.min_resize_value,
        max_resize_value=self.max_resize_value,
        resize_factor=self.resize_factor,
        min_scale_factor=self.min_scale_factor,
        max_scale_factor=self.max_scale_factor,
        scale_factor_step_size=self.scale_factor_step_size,
        ignore_label=self.ignore_label,
        is_training=self.is_training,
        model_variant=self.model_variant)

    sample[common.IMAGE] = image

    if not self.is_training:
      # Original image is only used during visualization.
      sample[common.ORIGINAL_IMAGE] = original_image

    if label is not None:
      sample[common.LABEL] = label

    # Remove common.LABEL_CLASS key in the sample since it is only used to
    # derive label and not used in training and evaluation.
    sample.pop(common.LABELS_CLASS, None)

    return sample 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _build_deeplab(iterator, outputs_to_num_classes, ignore_label):
  """Builds a clone of DeepLab.

  Args:
    iterator: An iterator of type tf.data.Iterator for images and labels.
    outputs_to_num_classes: A map from output type to the number of classes. For
      example, for the task of semantic segmentation with 21 semantic classes,
      we would have outputs_to_num_classes['semantic'] = 21.
    ignore_label: Ignore label.
  """
  samples = iterator.get_next()

  # Add name to input and label nodes so we can add to summary.
  samples[common.IMAGE] = tf.identity(samples[common.IMAGE], name=common.IMAGE)
  samples[common.LABEL] = tf.identity(samples[common.LABEL], name=common.LABEL)

  model_options = common.ModelOptions(
      outputs_to_num_classes=outputs_to_num_classes,
      crop_size=FLAGS.train_crop_size,
      atrous_rates=FLAGS.atrous_rates,
      output_stride=FLAGS.output_stride)

  outputs_to_scales_to_logits = model.multi_scale_logits(
      samples[common.IMAGE],
      model_options=model_options,
      image_pyramid=FLAGS.image_pyramid,
      weight_decay=FLAGS.weight_decay,
      is_training=True,
      fine_tune_batch_norm=FLAGS.fine_tune_batch_norm,
      nas_training_hyper_parameters={
          'drop_path_keep_prob': FLAGS.drop_path_keep_prob,
          'total_training_steps': FLAGS.training_number_of_steps,
      })

  # Add name to graph node so we can add to summary.
  output_type_dict = outputs_to_scales_to_logits[common.OUTPUT_TYPE]
  output_type_dict[model.MERGED_LOGITS_SCOPE] = tf.identity(
      output_type_dict[model.MERGED_LOGITS_SCOPE], name=common.OUTPUT_TYPE)

  for output, num_classes in six.iteritems(outputs_to_num_classes):
    train_utils.add_softmax_cross_entropy_loss_for_each_scale(
        outputs_to_scales_to_logits[output],
        samples[common.LABEL],
        num_classes,
        ignore_label,
        loss_weight=1.0,
        upsample_logits=FLAGS.upsample_logits,
        hard_example_mining_step=FLAGS.hard_example_mining_step,
        top_k_percent_pixels=FLAGS.top_k_percent_pixels,
        scope=output)

    # Log the summary
    _log_summaries(samples[common.IMAGE], samples[common.LABEL], num_classes,
                   output_type_dict[model.MERGED_LOGITS_SCOPE]) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _preprocess_image(self, sample):
    """Preprocesses the image and label.

    Args:
      sample: A sample containing image and label.

    Returns:
      sample: Sample with preprocessed image and label.

    Raises:
      ValueError: Ground truth label not provided during training.
    """
    image = sample[common.IMAGE]
    label = sample[common.LABELS_CLASS]

    # print(self.crop_size)
    original_image, image, label = input_preprocess.preprocess_image_and_label(
        image=image,
        label=label,
        crop_height=self.crop_size[0],
        crop_width=self.crop_size[1],
        min_resize_value=self.min_resize_value,
        max_resize_value=self.max_resize_value,
        resize_factor=self.resize_factor,
        min_scale_factor=self.min_scale_factor,
        max_scale_factor=self.max_scale_factor,
        scale_factor_step_size=self.scale_factor_step_size,
        ignore_label=self.ignore_label,
        is_training=self.is_training,
        model_variant=self.model_variant)

    sample[common.IMAGE] = image

    if not self.is_training:
      # Original image is only used during visualization.
      sample[common.ORIGINAL_IMAGE] = original_image

    if label is not None:
      sample[common.LABEL] = label

    # Remove common.LABEL_CLASS key in the sample since it is only used to
    # derive label and not used in training and evaluation.
    sample.pop(common.LABELS_CLASS, None)

    return sample 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _build_deeplab(inputs_queue, outputs_to_num_classes, ignore_label):
  """Builds a clone of DeepLab.

  Args:
    inputs_queue: A prefetch queue for images and labels.
    outputs_to_num_classes: A map from output type to the number of classes.
      For example, for the task of semantic segmentation with 21 semantic
      classes, we would have outputs_to_num_classes['semantic'] = 21.
    ignore_label: Ignore label.

  Returns:
    A map of maps from output_type (e.g., semantic prediction) to a
      dictionary of multi-scale logits names to logits. For each output_type,
      the dictionary has keys which correspond to the scales and values which
      correspond to the logits. For example, if `scales` equals [1.0, 1.5],
      then the keys would include 'merged_logits', 'logits_1.00' and
      'logits_1.50'.
  """
  samples = inputs_queue.dequeue()

  # Add name to input and label nodes so we can add to summary.
  samples[common.IMAGE] = tf.identity(
      samples[common.IMAGE], name=common.IMAGE)
  samples[common.LABEL] = tf.identity(
      samples[common.LABEL], name=common.LABEL)

  model_options = common.ModelOptions(
      outputs_to_num_classes=outputs_to_num_classes,
      crop_size=FLAGS.train_crop_size,
      atrous_rates=FLAGS.atrous_rates,
      output_stride=FLAGS.output_stride)
  outputs_to_scales_to_logits = model.multi_scale_logits(
      samples[common.IMAGE],
      model_options=model_options,
      image_pyramid=FLAGS.image_pyramid,
      weight_decay=FLAGS.weight_decay,
      is_training=True,
      fine_tune_batch_norm=FLAGS.fine_tune_batch_norm)

  # Add name to graph node so we can add to summary.
  output_type_dict = outputs_to_scales_to_logits[common.OUTPUT_TYPE]
  output_type_dict[model.MERGED_LOGITS_SCOPE] = tf.identity(
      output_type_dict[model.MERGED_LOGITS_SCOPE],
      name=common.OUTPUT_TYPE)

  for output, num_classes in six.iteritems(outputs_to_num_classes):
    train_utils.add_softmax_cross_entropy_loss_for_each_scale(
        outputs_to_scales_to_logits[output],
        samples[common.LABEL],
        num_classes,
        ignore_label,
        loss_weight=1.0,
        upsample_logits=FLAGS.upsample_logits,
        scope=output)

  return outputs_to_scales_to_logits 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import IMAGE [as 别名]
def _build_deeplab(iterator, outputs_to_num_classes, ignore_label):
  """Builds a clone of DeepLab.

  Args:
    iterator: An iterator of type tf.data.Iterator for images and labels.
    outputs_to_num_classes: A map from output type to the number of classes. For
      example, for the task of semantic segmentation with 21 semantic classes,
      we would have outputs_to_num_classes['semantic'] = 21.
    ignore_label: Ignore label.
  """
  samples = iterator.get_next()

  # Add name to input and label nodes so we can add to summary.
  samples[common.IMAGE] = tf.identity(samples[common.IMAGE], name=common.IMAGE)
  samples[common.LABEL] = tf.identity(samples[common.LABEL], name=common.LABEL)

  model_options = common.ModelOptions(
      outputs_to_num_classes=outputs_to_num_classes,
      crop_size=[int(sz) for sz in FLAGS.train_crop_size],
      atrous_rates=FLAGS.atrous_rates,
      output_stride=FLAGS.output_stride)

  outputs_to_scales_to_logits = model.multi_scale_logits(
      samples[common.IMAGE],
      model_options=model_options,
      image_pyramid=FLAGS.image_pyramid,
      weight_decay=FLAGS.weight_decay,
      is_training=True,
      fine_tune_batch_norm=FLAGS.fine_tune_batch_norm,
      nas_training_hyper_parameters={
          'drop_path_keep_prob': FLAGS.drop_path_keep_prob,
          'total_training_steps': FLAGS.training_number_of_steps,
      })

  # Add name to graph node so we can add to summary.
  output_type_dict = outputs_to_scales_to_logits[common.OUTPUT_TYPE]
  output_type_dict[model.MERGED_LOGITS_SCOPE] = tf.identity(
      output_type_dict[model.MERGED_LOGITS_SCOPE], name=common.OUTPUT_TYPE)

  for output, num_classes in six.iteritems(outputs_to_num_classes):
    train_utils.add_softmax_cross_entropy_loss_for_each_scale(
        outputs_to_scales_to_logits[output],
        samples[common.LABEL],
        num_classes,
        ignore_label,
        loss_weight=model_options.label_weights,
        upsample_logits=FLAGS.upsample_logits,
        hard_example_mining_step=FLAGS.hard_example_mining_step,
        top_k_percent_pixels=FLAGS.top_k_percent_pixels,
        scope=output)