Python object_detection.core.preprocessor.preprocess() Examples

The following are 30 code examples of object_detection.core.preprocessor.preprocess(). 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 object_detection.core.preprocessor , or try the search function .
Example #1
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testRandomAdjustHue(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_hue, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_hue = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_hue_shape = tf.shape(images_hue)
    with self.test_session() as sess:
      (image_original_shape_, image_hue_shape_) = sess.run(
          [image_original_shape, image_hue_shape])
      self.assertAllEqual(image_original_shape_, image_hue_shape_)
Example #2
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testNormalizeImage(self):
    preprocess_options = [(preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 256,
        'target_minval': -1,
        'target_maxval': 1
    })]
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    images_expected = self.expectedImagesAfterNormalization()

    with self.test_session() as sess:
      (images_, images_expected_) = sess.run(
          [images, images_expected])
      images_shape_ = images_.shape
      images_expected_shape_ = images_expected_.shape
      expected_shape = [1, 4, 4, 3]
      self.assertAllEqual(images_expected_shape_, images_shape_)
      self.assertAllEqual(images_shape_, expected_shape)
      self.assertAllClose(images_, images_expected_)
Example #3
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomAdjustBrightness(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_brightness, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_bright = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_bright_shape = tf.shape(images_bright)
    with self.test_session() as sess:
      (image_original_shape_, image_bright_shape_) = sess.run(
          [image_original_shape, image_bright_shape])
      self.assertAllEqual(image_original_shape_, image_bright_shape_)
Example #4
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomImageScale(self):
    preprocess_options = [(preprocessor.random_image_scale, {})]
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images_scaled = tensor_dict[fields.InputDataFields.image]
    images_original_shape = tf.shape(images_original)
    images_scaled_shape = tf.shape(images_scaled)
    with self.test_session() as sess:
      (images_original_shape_, images_scaled_shape_) = sess.run(
          [images_original_shape, images_scaled_shape])
      self.assertTrue(
          images_original_shape_[1] * 0.5 <= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[1] * 2.0 >= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[2] * 0.5 <= images_scaled_shape_[2])
      self.assertTrue(
          images_original_shape_[2] * 2.0 >= images_scaled_shape_[2])
Example #5
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomAdjustContrast(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_contrast, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_contrast = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_contrast_shape = tf.shape(images_contrast)
    with self.test_session() as sess:
      (image_original_shape_, image_contrast_shape_) = sess.run(
          [image_original_shape, image_contrast_shape])
      self.assertAllEqual(image_original_shape_, image_contrast_shape_)
Example #6
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomDistortColor(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_distort_color, {}))
    images_original = self.createTestImages()
    images_original_shape = tf.shape(images_original)
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_distorted_color = tensor_dict[fields.InputDataFields.image]
    images_distorted_color_shape = tf.shape(images_distorted_color)
    with self.test_session() as sess:
      (images_original_shape_, images_distorted_color_shape_) = sess.run(
          [images_original_shape, images_distorted_color_shape])
      self.assertAllEqual(images_original_shape_, images_distorted_color_shape_)
Example #7
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testRandomAdjustContrast(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_contrast, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_contrast = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_contrast_shape = tf.shape(images_contrast)
    with self.test_session() as sess:
      (image_original_shape_, image_contrast_shape_) = sess.run(
          [image_original_shape, image_contrast_shape])
      self.assertAllEqual(image_original_shape_, image_contrast_shape_)
Example #8
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomPixelValueScale(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_pixel_value_scale, {}))
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_min = tf.to_float(images) * 0.9 / 255.0
    images_max = tf.to_float(images) * 1.1 / 255.0
    images = tensor_dict[fields.InputDataFields.image]
    values_greater = tf.greater_equal(images, images_min)
    values_less = tf.less_equal(images, images_max)
    values_true = tf.fill([1, 4, 4, 3], True)
    with self.test_session() as sess:
      (values_greater_, values_less_, values_true_) = sess.run(
          [values_greater, values_less, values_true])
      self.assertAllClose(values_greater_, values_true_)
      self.assertAllClose(values_less_, values_true_)
Example #9
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testRandomImageScale(self):
    preprocess_options = [(preprocessor.random_image_scale, {})]
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images_scaled = tensor_dict[fields.InputDataFields.image]
    images_original_shape = tf.shape(images_original)
    images_scaled_shape = tf.shape(images_scaled)
    with self.test_session() as sess:
      (images_original_shape_, images_scaled_shape_) = sess.run(
          [images_original_shape, images_scaled_shape])
      self.assertTrue(
          images_original_shape_[1] * 0.5 <= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[1] * 2.0 >= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[2] * 0.5 <= images_scaled_shape_[2])
      self.assertTrue(
          images_original_shape_[2] * 2.0 >= images_scaled_shape_[2])
Example #10
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testRandomAdjustBrightness(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_brightness, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_bright = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_bright_shape = tf.shape(images_bright)
    with self.test_session() as sess:
      (image_original_shape_, image_bright_shape_) = sess.run(
          [image_original_shape, image_bright_shape])
      self.assertAllEqual(image_original_shape_, image_bright_shape_)
Example #11
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomAdjustHue(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_hue, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_hue = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_hue_shape = tf.shape(images_hue)
    with self.test_session() as sess:
      (image_original_shape_, image_hue_shape_) = sess.run(
          [image_original_shape, image_hue_shape])
      self.assertAllEqual(image_original_shape_, image_hue_shape_)
Example #12
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testRandomAdjustHue(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_hue, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_hue = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_hue_shape = tf.shape(images_hue)
    with self.test_session() as sess:
      (image_original_shape_, image_hue_shape_) = sess.run(
          [image_original_shape, image_hue_shape])
      self.assertAllEqual(image_original_shape_, image_hue_shape_)
Example #13
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomVerticalFlipWithEmptyBoxes(self):
    preprocess_options = [(preprocessor.random_vertical_flip, {})]
    images = self.expectedImagesAfterNormalization()
    boxes = self.createEmptyTestBoxes()
    tensor_dict = {fields.InputDataFields.image: images,
                   fields.InputDataFields.groundtruth_boxes: boxes}
    images_expected1 = self.expectedImagesAfterUpDownFlip()
    boxes_expected = self.createEmptyTestBoxes()
    images_expected2 = images
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]

    images_diff1 = tf.squared_difference(images, images_expected1)
    images_diff2 = tf.squared_difference(images, images_expected2)
    images_diff = tf.multiply(images_diff1, images_diff2)
    images_diff_expected = tf.zeros_like(images_diff)

    with self.test_session() as sess:
      (images_diff_, images_diff_expected_, boxes_,
       boxes_expected_) = sess.run([images_diff, images_diff_expected, boxes,
                                    boxes_expected])
      self.assertAllClose(boxes_, boxes_expected_)
      self.assertAllClose(images_diff_, images_diff_expected_)
Example #14
Source File: trainer.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
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)
Example #15
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testRandomAdjustContrast(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_contrast, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_contrast = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_contrast_shape = tf.shape(images_contrast)
    with self.test_session() as sess:
      (image_original_shape_, image_contrast_shape_) = sess.run(
          [image_original_shape, image_contrast_shape])
      self.assertAllEqual(image_original_shape_, image_contrast_shape_)
Example #16
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testRandomAdjustBrightness(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_adjust_brightness, {}))
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    images_bright = tensor_dict[fields.InputDataFields.image]
    image_original_shape = tf.shape(images_original)
    image_bright_shape = tf.shape(images_bright)
    with self.test_session() as sess:
      (image_original_shape_, image_bright_shape_) = sess.run(
          [image_original_shape, image_bright_shape])
      self.assertAllEqual(image_original_shape_, image_bright_shape_)
Example #17
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testRandomImageScale(self):
    preprocess_options = [(preprocessor.random_image_scale, {})]
    images_original = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images_original}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images_scaled = tensor_dict[fields.InputDataFields.image]
    images_original_shape = tf.shape(images_original)
    images_scaled_shape = tf.shape(images_scaled)
    with self.test_session() as sess:
      (images_original_shape_, images_scaled_shape_) = sess.run(
          [images_original_shape, images_scaled_shape])
      self.assertTrue(
          images_original_shape_[1] * 0.5 <= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[1] * 2.0 >= images_scaled_shape_[1])
      self.assertTrue(
          images_original_shape_[2] * 0.5 <= images_scaled_shape_[2])
      self.assertTrue(
          images_original_shape_[2] * 2.0 >= images_scaled_shape_[2])
Example #18
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testNormalizeImage(self):
    preprocess_options = [(preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 256,
        'target_minval': -1,
        'target_maxval': 1
    })]
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    images_expected = self.expectedImagesAfterNormalization()

    with self.test_session() as sess:
      (images_, images_expected_) = sess.run(
          [images, images_expected])
      images_shape_ = images_.shape
      images_expected_shape_ = images_expected_.shape
      expected_shape = [1, 4, 4, 3]
      self.assertAllEqual(images_expected_shape_, images_shape_)
      self.assertAllEqual(images_shape_, expected_shape)
      self.assertAllClose(images_, images_expected_)
Example #19
Source File: trainer.py    From object_detector_app with MIT License 6 votes vote down vote up 
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)
Example #20
Source File: preprocessor_test.py    From object_detector_app with MIT License 6 votes vote down vote up 
def testRandomResizeMethod(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_resize_method, {
        'target_size': (75, 150)
    }))
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    resized_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                  preprocessing_options)
    resized_images = resized_tensor_dict[fields.InputDataFields.image]
    resized_images_shape = tf.shape(resized_images)
    expected_images_shape = tf.constant([1, 75, 150, 3], dtype=tf.int32)

    with self.test_session() as sess:
      (expected_images_shape_, resized_images_shape_) = sess.run(
          [expected_images_shape, resized_images_shape])
      self.assertAllEqual(expected_images_shape_,
                          resized_images_shape_)
Example #21
Source File: preprocessor_test.py    From DOTA_models with Apache License 2.0 6 votes vote down vote up 
def testRandomResizeMethod(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_resize_method, {
        'target_size': (75, 150)
    }))
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    resized_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                  preprocessing_options)
    resized_images = resized_tensor_dict[fields.InputDataFields.image]
    resized_images_shape = tf.shape(resized_images)
    expected_images_shape = tf.constant([1, 75, 150, 3], dtype=tf.int32)

    with self.test_session() as sess:
      (expected_images_shape_, resized_images_shape_) = sess.run(
          [expected_images_shape, resized_images_shape])
      self.assertAllEqual(expected_images_shape_,
                          resized_images_shape_)
Example #22
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testNormalizeImage(self):
    preprocess_options = [(preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 256,
        'target_minval': -1,
        'target_maxval': 1
    })]
    images = self.createTestImages()
    tensor_dict = {fields.InputDataFields.image: images}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    images_expected = self.expectedImagesAfterNormalization()

    with self.test_session() as sess:
      (images_, images_expected_) = sess.run(
          [images, images_expected])
      images_shape_ = images_.shape
      images_expected_shape_ = images_expected_.shape
      expected_shape = [1, 4, 4, 3]
      self.assertAllEqual(images_expected_shape_, images_shape_)
      self.assertAllEqual(images_shape_, expected_shape)
      self.assertAllClose(images_, images_expected_)
Example #23
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomHorizontalFlipWithEmptyBoxes(self):
    preprocess_options = [(preprocessor.random_horizontal_flip, {})]
    images = self.expectedImagesAfterNormalization()
    boxes = self.createEmptyTestBoxes()
    tensor_dict = {fields.InputDataFields.image: images,
                   fields.InputDataFields.groundtruth_boxes: boxes}
    images_expected1 = self.expectedImagesAfterLeftRightFlip()
    boxes_expected = self.createEmptyTestBoxes()
    images_expected2 = images
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]

    images_diff1 = tf.squared_difference(images, images_expected1)
    images_diff2 = tf.squared_difference(images, images_expected2)
    images_diff = tf.multiply(images_diff1, images_diff2)
    images_diff_expected = tf.zeros_like(images_diff)

    with self.test_session() as sess:
      (images_diff_, images_diff_expected_, boxes_,
       boxes_expected_) = sess.run([images_diff, images_diff_expected, boxes,
                                    boxes_expected])
      self.assertAllClose(boxes_, boxes_expected_)
      self.assertAllClose(images_diff_, images_diff_expected_)
Example #24
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def testRandomRotation90WithEmptyBoxes(self):
    preprocess_options = [(preprocessor.random_rotation90, {})]
    images = self.expectedImagesAfterNormalization()
    boxes = self.createEmptyTestBoxes()
    tensor_dict = {fields.InputDataFields.image: images,
                   fields.InputDataFields.groundtruth_boxes: boxes}
    images_expected1 = self.expectedImagesAfterRot90()
    boxes_expected = self.createEmptyTestBoxes()
    images_expected2 = images
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
    images = tensor_dict[fields.InputDataFields.image]
    boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]

    images_diff1 = tf.squared_difference(images, images_expected1)
    images_diff2 = tf.squared_difference(images, images_expected2)
    images_diff = tf.multiply(images_diff1, images_diff2)
    images_diff_expected = tf.zeros_like(images_diff)

    with self.test_session() as sess:
      (images_diff_, images_diff_expected_, boxes_,
       boxes_expected_) = sess.run([images_diff, images_diff_expected, boxes,
                                    boxes_expected])
      self.assertAllClose(boxes_, boxes_expected_)
      self.assertAllClose(images_diff_, images_diff_expected_)
Example #25
Source File: preprocessor_test.py    From object_detector_app with MIT License 5 votes vote down vote up 
def testRandomCropImageGrayscale(self):
    preprocessing_options = [(preprocessor.rgb_to_gray, {}),
                             (preprocessor.normalize_image, {
                                 'original_minval': 0,
                                 'original_maxval': 255,
                                 'target_minval': 0,
                                 'target_maxval': 1,
                             }),
                             (preprocessor.random_crop_image, {})]
    images = self.createTestImages()
    boxes = self.createTestBoxes()
    labels = self.createTestLabels()
    tensor_dict = {
        fields.InputDataFields.image: images,
        fields.InputDataFields.groundtruth_boxes: boxes,
        fields.InputDataFields.groundtruth_classes: labels
    }
    distorted_tensor_dict = preprocessor.preprocess(
        tensor_dict, preprocessing_options)
    distorted_images = distorted_tensor_dict[fields.InputDataFields.image]
    distorted_boxes = distorted_tensor_dict[
        fields.InputDataFields.groundtruth_boxes]
    boxes_rank = tf.rank(boxes)
    distorted_boxes_rank = tf.rank(distorted_boxes)
    images_rank = tf.rank(images)
    distorted_images_rank = tf.rank(distorted_images)
    self.assertEqual(1, distorted_images.get_shape()[3])

    with self.test_session() as sess:
      session_results = sess.run([
          boxes_rank, distorted_boxes_rank, images_rank, distorted_images_rank
      ])
      (boxes_rank_, distorted_boxes_rank_, images_rank_,
       distorted_images_rank_) = session_results
      self.assertAllEqual(boxes_rank_, distorted_boxes_rank_)
      self.assertAllEqual(images_rank_, distorted_images_rank_)
Example #26
Source File: preprocessor_test.py    From vehicle_counting_tensorflow with MIT License 5 votes vote down vote up 
def testRandomJitterBoxes(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.random_jitter_boxes, {}))
    boxes = self.createTestBoxes()
    boxes_shape = tf.shape(boxes)
    tensor_dict = {fields.InputDataFields.groundtruth_boxes: boxes}
    tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options)
    distorted_boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]
    distorted_boxes_shape = tf.shape(distorted_boxes)

    with self.test_session() as sess:
      (boxes_shape_, distorted_boxes_shape_) = sess.run(
          [boxes_shape, distorted_boxes_shape])
      self.assertAllEqual(boxes_shape_, distorted_boxes_shape_)
Example #27
Source File: trainer.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
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
Example #28
Source File: preprocessor_test.py    From object_detector_app with MIT License 5 votes vote down vote up 
def testRandomCropImageWithBoxOutOfImage(self):
    preprocessing_options = []
    preprocessing_options.append((preprocessor.normalize_image, {
        'original_minval': 0,
        'original_maxval': 255,
        'target_minval': 0,
        'target_maxval': 1
    }))
    preprocessing_options.append((preprocessor.random_crop_image, {}))
    images = self.createTestImages()
    boxes = self.createTestBoxesOutOfImage()
    labels = self.createTestLabels()
    tensor_dict = {fields.InputDataFields.image: images,
                   fields.InputDataFields.groundtruth_boxes: boxes,
                   fields.InputDataFields.groundtruth_classes: labels}
    distorted_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                    preprocessing_options)
    distorted_images = distorted_tensor_dict[fields.InputDataFields.image]
    distorted_boxes = distorted_tensor_dict[
        fields.InputDataFields.groundtruth_boxes]
    boxes_rank = tf.rank(boxes)
    distorted_boxes_rank = tf.rank(distorted_boxes)
    images_rank = tf.rank(images)
    distorted_images_rank = tf.rank(distorted_images)

    with self.test_session() as sess:
      (boxes_rank_, distorted_boxes_rank_, images_rank_,
       distorted_images_rank_) = sess.run(
           [boxes_rank, distorted_boxes_rank, images_rank,
            distorted_images_rank])
      self.assertAllEqual(boxes_rank_, distorted_boxes_rank_)
      self.assertAllEqual(images_rank_, distorted_images_rank_)
Example #29
Source File: preprocessor_test.py    From object_detector_app with MIT License 5 votes vote down vote up 
def testSSDRandomCropPad(self):
    images = self.createTestImages()
    boxes = self.createTestBoxes()
    labels = self.createTestLabels()
    preprocessing_options = [
        (preprocessor.normalize_image, {
            'original_minval': 0,
            'original_maxval': 255,
            'target_minval': 0,
            'target_maxval': 1
        }),
        (preprocessor.ssd_random_crop_pad, {})]
    tensor_dict = {fields.InputDataFields.image: images,
                   fields.InputDataFields.groundtruth_boxes: boxes,
                   fields.InputDataFields.groundtruth_classes: labels}
    distorted_tensor_dict = preprocessor.preprocess(tensor_dict,
                                                    preprocessing_options)
    distorted_images = distorted_tensor_dict[fields.InputDataFields.image]
    distorted_boxes = distorted_tensor_dict[
        fields.InputDataFields.groundtruth_boxes]

    images_rank = tf.rank(images)
    distorted_images_rank = tf.rank(distorted_images)
    boxes_rank = tf.rank(boxes)
    distorted_boxes_rank = tf.rank(distorted_boxes)

    with self.test_session() as sess:
      (boxes_rank_, distorted_boxes_rank_, images_rank_,
       distorted_images_rank_) = sess.run([
           boxes_rank, distorted_boxes_rank, images_rank, distorted_images_rank
       ])
      self.assertAllEqual(boxes_rank_, distorted_boxes_rank_)
      self.assertAllEqual(images_rank_, distorted_images_rank_)
Example #30
Source File: preprocessor_test.py    From object_detector_app with MIT License 5 votes vote down vote up 
def testRunRetainBoxesAboveThresholdWithMasks(self):
    boxes = self.createTestBoxes()
    labels = self.createTestLabels()
    label_scores = self.createTestLabelScores()
    masks = self.createTestMasks()

    tensor_dict = {
        fields.InputDataFields.groundtruth_boxes: boxes,
        fields.InputDataFields.groundtruth_classes: labels,
        fields.InputDataFields.groundtruth_label_scores: label_scores,
        fields.InputDataFields.groundtruth_instance_masks: masks
    }

    preprocessor_arg_map = preprocessor.get_default_func_arg_map(
        include_instance_masks=True)

    preprocessing_options = [
        (preprocessor.retain_boxes_above_threshold, {'threshold': 0.6})
    ]

    retained_tensor_dict = preprocessor.preprocess(
        tensor_dict, preprocessing_options, func_arg_map=preprocessor_arg_map)
    retained_masks = retained_tensor_dict[
        fields.InputDataFields.groundtruth_instance_masks]

    with self.test_session() as sess:
      (retained_masks_, expected_masks_) = sess.run(
          [retained_masks,
           self.expectedMasksAfterThresholding()])
      self.assertAllClose(retained_masks_, expected_masks_)