Python batcher.BatchQueue方法代码示例

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def _create_losses(input_queue, create_model_fn):
  """Creates loss function for a DetectionModel.

  Args:
    input_queue: BatchQueue object holding enqueued tensor_dicts.
    create_model_fn: A function to create the DetectionModel.
  """
  detection_model = create_model_fn()
  (images, groundtruth_boxes_list, groundtruth_classes_list,
   groundtruth_masks_list
  ) = _get_inputs(input_queue, detection_model.num_classes)
  images = [detection_model.preprocess(image) for image in images]
  images = tf.concat(images, 0)
  if any(mask is None for mask in groundtruth_masks_list):
    groundtruth_masks_list = None

  detection_model.provide_groundtruth(groundtruth_boxes_list,
                                      groundtruth_classes_list,
                                      groundtruth_masks_list)
  prediction_dict = detection_model.predict(images)

  losses_dict = detection_model.loss(prediction_dict)
  for loss_tensor in losses_dict.values():
    tf.losses.add_loss(loss_tensor) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def _create_input_queue(batch_size_per_clone, create_tensor_dict_fn,
                        batch_queue_capacity, num_batch_queue_threads,
                        prefetch_queue_capacity, data_augmentation_options):
  """Sets up reader, prefetcher and returns input queue.

  Args:
    batch_size_per_clone: batch size to use per clone.
    create_tensor_dict_fn: function to create tensor dictionary.
    batch_queue_capacity: maximum number of elements to store within a queue.
    num_batch_queue_threads: number of threads to use for batching.
    prefetch_queue_capacity: maximum capacity of the queue used to prefetch
                             assembled batches.
    data_augmentation_options: a list of tuples, where each tuple contains a
      data augmentation function and a dictionary containing arguments and their
      values (see preprocessor.py).

  Returns:
    input queue: a batcher.BatchQueue object holding enqueued tensor_dicts
      (which hold images, boxes and targets).  To get a batch of tensor_dicts,
      call input_queue.Dequeue().
  """
  tensor_dict = create_tensor_dict_fn()

  tensor_dict[fields.InputDataFields.image] = tf.expand_dims(
      tensor_dict[fields.InputDataFields.image], 0)

  images = tensor_dict[fields.InputDataFields.image]
  float_images = tf.to_float(images)
  tensor_dict[fields.InputDataFields.image] = float_images

  if data_augmentation_options:
    tensor_dict = preprocessor.preprocess(tensor_dict,
                                          data_augmentation_options)

  input_queue = batcher.BatchQueue(
      tensor_dict,
      batch_size=batch_size_per_clone,
      batch_queue_capacity=batch_queue_capacity,
      num_batch_queue_threads=num_batch_queue_threads,
      prefetch_queue_capacity=prefetch_queue_capacity)
  return input_queue 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def _get_inputs(input_queue, num_classes):
  """Dequeue batch and construct inputs to object detection model.

  Args:
    input_queue: BatchQueue object holding enqueued tensor_dicts.
    num_classes: Number of classes.

  Returns:
    images: a list of 3-D float tensor of images.
    locations_list: a list of tensors of shape [num_boxes, 4]
      containing the corners of the groundtruth boxes.
    classes_list: a list of padded one-hot tensors containing target classes.
    masks_list: a list of 3-D float tensors of shape [num_boxes, image_height,
      image_width] containing instance masks for objects if present in the
      input_queue. Else returns None.
  """
  read_data_list = input_queue.dequeue()
  label_id_offset = 1
  def extract_images_and_targets(read_data):
    image = read_data[fields.InputDataFields.image]
    location_gt = read_data[fields.InputDataFields.groundtruth_boxes]
    classes_gt = tf.cast(read_data[fields.InputDataFields.groundtruth_classes],
                         tf.int32)
    classes_gt -= label_id_offset
    classes_gt = util_ops.padded_one_hot_encoding(indices=classes_gt,
                                                  depth=num_classes, left_pad=0)
    masks_gt = read_data.get(fields.InputDataFields.groundtruth_instance_masks)
    return image, location_gt, classes_gt, masks_gt
  return zip(*map(extract_images_and_targets, read_data_list)) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def test_batch_and_unpad_2d_tensors_of_different_sizes_in_1st_dimension(self):
    with self.test_session() as sess:
      batch_size = 3
      num_batches = 2
      examples = tf.Variable(tf.constant(2, dtype=tf.int32))
      counter = examples.count_up_to(num_batches * batch_size + 2)
      boxes = tf.tile(
          tf.reshape(tf.range(4), [1, 4]), tf.stack([counter, tf.constant(1)]))
      batch_queue = batcher.BatchQueue(
          tensor_dict={'boxes': boxes},
          batch_size=batch_size,
          batch_queue_capacity=100,
          num_batch_queue_threads=1,
          prefetch_queue_capacity=100)
      batch = batch_queue.dequeue()

      for tensor_dict in batch:
        for tensor in tensor_dict.values():
          self.assertAllEqual([None, 4], tensor.get_shape().as_list())

      tf.initialize_all_variables().run()
      with slim.queues.QueueRunners(sess):
        i = 2
        for _ in range(num_batches):
          batch_np = sess.run(batch)
          for tensor_dict in batch_np:
            for tensor in tensor_dict.values():
              self.assertAllEqual(tensor, np.tile(np.arange(4), (i, 1)))
              i += 1
        with self.assertRaises(tf.errors.OutOfRangeError):
          sess.run(batch) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def test_batch_and_unpad_2d_tensors_of_different_sizes_in_all_dimensions(
      self):
    with self.test_session() as sess:
      batch_size = 3
      num_batches = 2
      examples = tf.Variable(tf.constant(2, dtype=tf.int32))
      counter = examples.count_up_to(num_batches * batch_size + 2)
      image = tf.reshape(
          tf.range(counter * counter), tf.stack([counter, counter]))
      batch_queue = batcher.BatchQueue(
          tensor_dict={'image': image},
          batch_size=batch_size,
          batch_queue_capacity=100,
          num_batch_queue_threads=1,
          prefetch_queue_capacity=100)
      batch = batch_queue.dequeue()

      for tensor_dict in batch:
        for tensor in tensor_dict.values():
          self.assertAllEqual([None, None], tensor.get_shape().as_list())

      tf.initialize_all_variables().run()
      with slim.queues.QueueRunners(sess):
        i = 2
        for _ in range(num_batches):
          batch_np = sess.run(batch)
          for tensor_dict in batch_np:
            for tensor in tensor_dict.values():
              self.assertAllEqual(tensor, np.arange(i * i).reshape((i, i)))
              i += 1
        with self.assertRaises(tf.errors.OutOfRangeError):
          sess.run(batch) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def test_batcher_when_batch_size_is_one(self):
    with self.test_session() as sess:
      batch_size = 1
      num_batches = 2
      examples = tf.Variable(tf.constant(2, dtype=tf.int32))
      counter = examples.count_up_to(num_batches * batch_size + 2)
      image = tf.reshape(
          tf.range(counter * counter), tf.stack([counter, counter]))
      batch_queue = batcher.BatchQueue(
          tensor_dict={'image': image},
          batch_size=batch_size,
          batch_queue_capacity=100,
          num_batch_queue_threads=1,
          prefetch_queue_capacity=100)
      batch = batch_queue.dequeue()

      for tensor_dict in batch:
        for tensor in tensor_dict.values():
          self.assertAllEqual([None, None], tensor.get_shape().as_list())

      tf.initialize_all_variables().run()
      with slim.queues.QueueRunners(sess):
        i = 2
        for _ in range(num_batches):
          batch_np = sess.run(batch)
          for tensor_dict in batch_np:
            for tensor in tensor_dict.values():
              self.assertAllEqual(tensor, np.arange(i * i).reshape((i, i)))
              i += 1
        with self.assertRaises(tf.errors.OutOfRangeError):
          sess.run(batch) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def test_batch_and_unpad_2d_tensors_of_same_size_in_all_dimensions(self):
    with self.test_session() as sess:
      batch_size = 3
      num_batches = 2
      examples = tf.Variable(tf.constant(1, dtype=tf.int32))
      counter = examples.count_up_to(num_batches * batch_size + 1)
      image = tf.reshape(tf.range(1, 13), [4, 3]) * counter
      batch_queue = batcher.BatchQueue(
          tensor_dict={'image': image},
          batch_size=batch_size,
          batch_queue_capacity=100,
          num_batch_queue_threads=1,
          prefetch_queue_capacity=100)
      batch = batch_queue.dequeue()

      for tensor_dict in batch:
        for tensor in tensor_dict.values():
          self.assertAllEqual([4, 3], tensor.get_shape().as_list())

      tf.initialize_all_variables().run()
      with slim.queues.QueueRunners(sess):
        i = 1
        for _ in range(num_batches):
          batch_np = sess.run(batch)
          for tensor_dict in batch_np:
            for tensor in tensor_dict.values():
              self.assertAllEqual(tensor, np.arange(1, 13).reshape((4, 3)) * i)
              i += 1
        with self.assertRaises(tf.errors.OutOfRangeError):
          sess.run(batch) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def _create_losses(input_queue, create_model_fn, train_config):
  """Creates loss function for a DetectionModel.

  Args:
    input_queue: BatchQueue object holding enqueued tensor_dicts.
    create_model_fn: A function to create the DetectionModel.
    train_config: a train_pb2.TrainConfig protobuf.
  """
  detection_model = create_model_fn()
  (images, _, groundtruth_boxes_list, groundtruth_classes_list,
   groundtruth_masks_list, groundtruth_keypoints_list, _) = get_inputs(
       input_queue,
       detection_model.num_classes,
       train_config.merge_multiple_label_boxes)

  preprocessed_images = []
  true_image_shapes = []
  for image in images:
    resized_image, true_image_shape = detection_model.preprocess(image)
    preprocessed_images.append(resized_image)
    true_image_shapes.append(true_image_shape)

  images = tf.concat(preprocessed_images, 0)
  true_image_shapes = tf.concat(true_image_shapes, 0)

  if any(mask is None for mask in groundtruth_masks_list):
    groundtruth_masks_list = None
  if any(keypoints is None for keypoints in groundtruth_keypoints_list):
    groundtruth_keypoints_list = None

  detection_model.provide_groundtruth(groundtruth_boxes_list,
                                      groundtruth_classes_list,
                                      groundtruth_masks_list,
                                      groundtruth_keypoints_list)
  prediction_dict = detection_model.predict(images, true_image_shapes)

  losses_dict = detection_model.loss(prediction_dict, true_image_shapes)
  for loss_tensor in losses_dict.values():
    tf.losses.add_loss(loss_tensor) 

# 需要导入模块: from object_detection.core import batcher [as 别名]
# 或者: from object_detection.core.batcher import BatchQueue [as 别名]
def _create_losses(input_queue, create_model_fn, train_config):
  """Creates loss function for a DetectionModel.

  Args:
    input_queue: BatchQueue object holding enqueued tensor_dicts.
    create_model_fn: A function to create the DetectionModel.
    train_config: a train_pb2.TrainConfig protobuf.
  """
  detection_model = create_model_fn()
  (images, _, groundtruth_boxes_list, groundtruth_classes_list,
   groundtruth_masks_list, groundtruth_keypoints_list, _) = get_inputs(
       input_queue,
       detection_model.num_classes,
       train_config.merge_multiple_label_boxes,
       train_config.use_multiclass_scores)

  preprocessed_images = []
  true_image_shapes = []
  for image in images:
    resized_image, true_image_shape = detection_model.preprocess(image)
    preprocessed_images.append(resized_image)
    true_image_shapes.append(true_image_shape)

  images = tf.concat(preprocessed_images, 0)
  true_image_shapes = tf.concat(true_image_shapes, 0)

  if any(mask is None for mask in groundtruth_masks_list):
    groundtruth_masks_list = None
  if any(keypoints is None for keypoints in groundtruth_keypoints_list):
    groundtruth_keypoints_list = None

  detection_model.provide_groundtruth(groundtruth_boxes_list,
                                      groundtruth_classes_list,
                                      groundtruth_masks_list,
                                      groundtruth_keypoints_list)
  prediction_dict = detection_model.predict(images, true_image_shapes)

  losses_dict = detection_model.loss(prediction_dict, true_image_shapes)
  for loss_tensor in losses_dict.values():
    tf.losses.add_loss(loss_tensor)