Python common.ModelOptions方法代码示例

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def get_params(ignore_label, num_classes, num_batches_per_epoch):
  """Build a dict of parameters from command line args."""
  params = {k: FLAGS[k].value for k in FLAGS}

  outputs_to_num_classes = {common.OUTPUT_TYPE: num_classes}
  model_options = common.ModelOptions(
      outputs_to_num_classes, FLAGS.crop_size, FLAGS.atrous_rates,
      FLAGS.output_stride,
      preprocessed_images_dtype=(
          tf.bfloat16 if params['use_bfloat16'] else tf.float32))
  params.update({'ignore_label': ignore_label,
                 'model_options': model_options,
                 'num_batches_per_epoch': num_batches_per_epoch,
                 'num_classes': num_classes,
                 'outputs_to_num_classes': outputs_to_num_classes})

  tf.logging.debug('Params: ')
  for k, v in sorted(params.items()):
    tf.logging.debug('%s: %s', k, v)
  return params 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testDeepcopy(self):
    num_classes = 21
    model_options = common.ModelOptions(
        outputs_to_num_classes={common.OUTPUT_TYPE: num_classes})
    model_options_new = copy.deepcopy(model_options)
    self.assertEqual((model_options_new.
                      outputs_to_num_classes[common.OUTPUT_TYPE]),
                     num_classes)

    num_classes_new = 22
    model_options_new.outputs_to_num_classes[common.OUTPUT_TYPE] = (
        num_classes_new)
    self.assertEqual(model_options.outputs_to_num_classes[common.OUTPUT_TYPE],
                     num_classes)
    self.assertEqual((model_options_new.
                      outputs_to_num_classes[common.OUTPUT_TYPE]),
                     num_classes_new) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testWrongDeepLabVariant(self):
    model_options = common.ModelOptions([])._replace(
        model_variant='no_such_variant')
    with self.assertRaises(ValueError):
      model._get_logits(images=[], model_options=model_options) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testForwardpassDeepLabv3plus(self):
    crop_size = [33, 33]
    outputs_to_num_classes = {'semantic': 3}

    model_options = common.ModelOptions(
        outputs_to_num_classes,
        crop_size,
        output_stride=16
    )._replace(
        add_image_level_feature=True,
        aspp_with_batch_norm=True,
        logits_kernel_size=1,
        model_variant='mobilenet_v2')  # Employ MobileNetv2 for fast test.

    g = tf.Graph()
    with g.as_default():
      with self.test_session(graph=g) as sess:
        inputs = tf.random_uniform(
            (1, crop_size[0], crop_size[1], 3))
        outputs_to_scales_to_logits = model.multi_scale_logits(
            inputs,
            model_options,
            image_pyramid=[1.0])

        sess.run(tf.global_variables_initializer())
        outputs_to_scales_to_logits = sess.run(outputs_to_scales_to_logits)

        # Check computed results for each output type.
        for output in outputs_to_num_classes:
          scales_to_logits = outputs_to_scales_to_logits[output]
          # Expect only one output.
          self.assertEquals(len(scales_to_logits), 1)
          for logits in scales_to_logits.values():
            self.assertTrue(logits.any()) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testOutputsToNumClasses(self):
    num_classes = 21
    model_options = common.ModelOptions(
        outputs_to_num_classes={common.OUTPUT_TYPE: num_classes})
    self.assertEqual(model_options.outputs_to_num_classes[common.OUTPUT_TYPE],
                     num_classes) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testForwardpassDeepLabv3plus(self):
    crop_size = [33, 33]
    outputs_to_num_classes = {'semantic': 3}

    model_options = common.ModelOptions(
        outputs_to_num_classes,
        crop_size,
        output_stride=16
    )._replace(
        add_image_level_feature=True,
        aspp_with_batch_norm=True,
        logits_kernel_size=1,
        decoder_output_stride=[4],
        model_variant='mobilenet_v2')  # Employ MobileNetv2 for fast test.

    g = tf.Graph()
    with g.as_default():
      with self.test_session(graph=g) as sess:
        inputs = tf.random_uniform(
            (1, crop_size[0], crop_size[1], 3))
        outputs_to_scales_to_logits = model.multi_scale_logits(
            inputs,
            model_options,
            image_pyramid=[1.0])

        sess.run(tf.global_variables_initializer())
        outputs_to_scales_to_logits = sess.run(outputs_to_scales_to_logits)

        # Check computed results for each output type.
        for output in outputs_to_num_classes:
          scales_to_logits = outputs_to_scales_to_logits[output]
          # Expect only one output.
          self.assertEqual(len(scales_to_logits), 1)
          for logits in scales_to_logits.values():
            self.assertTrue(logits.any()) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def testForwardpassDeepLabv3plus(self):
    crop_size = [33, 33]
    outputs_to_num_classes = {'semantic': 3}

    model_options = common.ModelOptions(
        outputs_to_num_classes,
        crop_size,
        output_stride=16
    )._replace(
        add_image_level_feature=True,
        aspp_with_batch_norm=True,
        logits_kernel_size=1,
        model_variant='mobilenet_v2')  # Employ MobileNetv2 for fast test.

    g = tf.Graph()
    with g.as_default():
      with self.test_session(graph=g) as sess:
        inputs = tf.random_uniform(
            (1, crop_size[0], crop_size[1], 3))
        outputs_to_scales_to_logits = model.multi_scale_logits(
            inputs,
            model_options,
            image_pyramid=[1.0])

        sess.run(tf.global_variables_initializer())
        outputs_to_scales_to_logits = sess.run(outputs_to_scales_to_logits)

        # Check computed results for each output type.
        for output in outputs_to_num_classes:
          scales_to_logits = outputs_to_scales_to_logits[output]
          # Expect only one output.
          self.assertEqual(len(scales_to_logits), 1)
          for logits in scales_to_logits.values():
            self.assertTrue(logits.any()) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [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 ModelOptions [as 别名]
def testBuildDeepLabv2(self):
    batch_size = 2
    crop_size = [41, 41]

    # Test with two image_pyramids.
    image_pyramids = [[1], [0.5, 1]]

    # Test two model variants.
    model_variants = ['xception_65', 'mobilenet_v2']

    # Test with two output_types.
    outputs_to_num_classes = {'semantic': 3,
                              'direction': 2}

    expected_endpoints = [['merged_logits'],
                          ['merged_logits',
                           'logits_0.50',
                           'logits_1.00']]
    expected_num_logits = [1, 3]

    for model_variant in model_variants:
      model_options = common.ModelOptions(outputs_to_num_classes)._replace(
          add_image_level_feature=False,
          aspp_with_batch_norm=False,
          aspp_with_separable_conv=False,
          model_variant=model_variant)

      for i, image_pyramid in enumerate(image_pyramids):
        g = tf.Graph()
        with g.as_default():
          with self.test_session(graph=g):
            inputs = tf.random_uniform(
                (batch_size, crop_size[0], crop_size[1], 3))
            outputs_to_scales_to_logits = model.multi_scale_logits(
                inputs, model_options, image_pyramid=image_pyramid)

            # Check computed results for each output type.
            for output in outputs_to_num_classes:
              scales_to_logits = outputs_to_scales_to_logits[output]
              self.assertListEqual(sorted(scales_to_logits.keys()),
                                   sorted(expected_endpoints[i]))

              # Expected number of logits = len(image_pyramid) + 1, since the
              # last logits is merged from all the scales.
              self.assertEqual(len(scales_to_logits), expected_num_logits[i]) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [as 别名]
def main(unused_argv):
  tf.logging.set_verbosity(tf.logging.INFO)
  tf.logging.info('Prepare to export model to: %s', FLAGS.export_path)

  with tf.Graph().as_default():
    image, image_size, resized_image_size = _create_input_tensors()

    model_options = common.ModelOptions(
        outputs_to_num_classes={common.OUTPUT_TYPE: FLAGS.num_classes},
        crop_size=FLAGS.crop_size,
        atrous_rates=FLAGS.atrous_rates,
        output_stride=FLAGS.output_stride)

    if tuple(FLAGS.inference_scales) == (1.0,):
      tf.logging.info('Exported model performs single-scale inference.')
      predictions = model.predict_labels(
          image,
          model_options=model_options,
          image_pyramid=FLAGS.image_pyramid)
    else:
      tf.logging.info('Exported model performs multi-scale inference.')
      predictions = model.predict_labels_multi_scale(
          image,
          model_options=model_options,
          eval_scales=FLAGS.inference_scales,
          add_flipped_images=FLAGS.add_flipped_images)

    # Crop the valid regions from the predictions.
    semantic_predictions = tf.slice(
        predictions[common.OUTPUT_TYPE],
        [0, 0, 0],
        [1, resized_image_size[0], resized_image_size[1]])
    # Resize back the prediction to the original image size.
    def _resize_label(label, label_size):
      # Expand dimension of label to [1, height, width, 1] for resize operation.
      label = tf.expand_dims(label, 3)
      resized_label = tf.image.resize_images(
          label,
          label_size,
          method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
          align_corners=True)
      return tf.squeeze(resized_label, 3)
    semantic_predictions = _resize_label(semantic_predictions, image_size)
    semantic_predictions = tf.identity(semantic_predictions, name=_OUTPUT_NAME)

    saver = tf.train.Saver(tf.model_variables())

    tf.gfile.MakeDirs(os.path.dirname(FLAGS.export_path))
    freeze_graph.freeze_graph_with_def_protos(
        tf.get_default_graph().as_graph_def(add_shapes=True),
        saver.as_saver_def(),
        FLAGS.checkpoint_path,
        _OUTPUT_NAME,
        restore_op_name=None,
        filename_tensor_name=None,
        output_graph=FLAGS.export_path,
        clear_devices=True,
        initializer_nodes=None) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [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 ModelOptions [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 ModelOptions [as 别名]
def main(unused_argv):
  tf.logging.set_verbosity(tf.logging.INFO)
  tf.logging.info('Prepare to export model to: %s', FLAGS.export_path)

  with tf.Graph().as_default():
    image, image_size, resized_image_size = _create_input_tensors()

    model_options = common.ModelOptions(
        outputs_to_num_classes={common.OUTPUT_TYPE: FLAGS.num_classes},
        crop_size=FLAGS.crop_size,
        atrous_rates=FLAGS.atrous_rates,
        output_stride=FLAGS.output_stride)

    if tuple(FLAGS.inference_scales) == (1.0,):
      tf.logging.info('Exported model performs single-scale inference.')
      predictions = model.predict_labels(
          image,
          model_options=model_options,
          image_pyramid=FLAGS.image_pyramid)
    else:
      tf.logging.info('Exported model performs multi-scale inference.')
      predictions = model.predict_labels_multi_scale(
          image,
          model_options=model_options,
          eval_scales=FLAGS.inference_scales,
          add_flipped_images=FLAGS.add_flipped_images)

    predictions = tf.cast(predictions[common.OUTPUT_TYPE], tf.float32)
    # Crop the valid regions from the predictions.
    semantic_predictions = tf.slice(
        predictions,
        [0, 0, 0],
        [1, resized_image_size[0], resized_image_size[1]])
    # Resize back the prediction to the original image size.
    def _resize_label(label, label_size):
      # Expand dimension of label to [1, height, width, 1] for resize operation.
      label = tf.expand_dims(label, 3)
      resized_label = tf.image.resize_images(
          label,
          label_size,
          method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
          align_corners=True)
      return tf.cast(tf.squeeze(resized_label, 3), tf.int32)
    semantic_predictions = _resize_label(semantic_predictions, image_size)
    semantic_predictions = tf.identity(semantic_predictions, name=_OUTPUT_NAME)

    saver = tf.train.Saver(tf.model_variables())

    tf.gfile.MakeDirs(os.path.dirname(FLAGS.export_path))
    freeze_graph.freeze_graph_with_def_protos(
        tf.get_default_graph().as_graph_def(add_shapes=True),
        saver.as_saver_def(),
        FLAGS.checkpoint_path,
        _OUTPUT_NAME,
        restore_op_name=None,
        filename_tensor_name=None,
        output_graph=FLAGS.export_path,
        clear_devices=True,
        initializer_nodes=None) 

# 需要导入模块: from deeplab import common [as 别名]
# 或者: from deeplab.common import ModelOptions [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