def __init__(self,
model_spec,
index_to_label,
shuffle=True,
hparams=hub_lib.get_default_hparams(),
use_augmentation=False,
representative_data=None):
"""Init function for ImageClassifier class.
Args:
model_spec: Specification for the model.
index_to_label: A list that map from index to label class name.
shuffle: Whether the data should be shuffled.
hparams: A namedtuple of hyperparameters. This function expects
.dropout_rate: The fraction of the input units to drop, used in dropout
layer.
.do_fine_tuning: If true, the Hub module is trained together with the
classification layer on top.
use_augmentation: Use data augmentation for preprocessing.
representative_data: Representative dataset for full integer
quantization. Used when converting the keras model to the TFLite model
with full interger quantization.
"""
super(ImageClassifier, self).__init__(model_spec, index_to_label,
shuffle, hparams.do_fine_tuning)
num_classes = len(index_to_label)
self._hparams = hparams
self.preprocess = image_preprocessing.Preprocessor(
self.model_spec.input_image_shape,
num_classes,
self.model_spec.mean_rgb,
self.model_spec.stddev_rgb,
use_augmentation=use_augmentation)
self.history = None # Training history that returns from `keras_model.fit`.
self.representative_data = representative_data
def __init__(self,
model_spec,
index_to_label,
num_classes,
shuffle=True,
hparams=hub_lib.get_default_hparams(),
use_augmentation=False):
"""Init function for ImageClassifier class.
Args:
model_spec: Specification for the model.
index_to_label: A list that map from index to label class name.
num_classes: Number of label classes.
shuffle: Whether the data should be shuffled.
hparams: A namedtuple of hyperparameters. This function expects
.dropout_rate: The fraction of the input units to drop, used in dropout
layer.
.do_fine_tuning: If true, the Hub module is trained together with the
classification layer on top.
use_augmentation: Use data augmentation for preprocessing.
"""
super(ImageClassifier,
self).__init__(model_spec, index_to_label, num_classes, shuffle,
hparams.do_fine_tuning)
self.hparams = hparams
self.model = self._create_model()
self.preprocessor = image_preprocessing.Preprocessor(
self.model_spec.input_image_shape,
num_classes,
self.model_spec.mean_rgb,
self.model_spec.stddev_rgb,
use_augmentation=use_augmentation)
self.history = None # Training history that returns from `keras_model.fit`.
def __init__(self,
model_export_format,
model_spec,
index_to_label,
num_classes,
shuffle=True,
hparams=lib.get_default_hparams(),
use_augmentation=False):
"""Init function for ImageClassifier class.
Args:
model_export_format: Model export format such as saved_model / tflite.
model_spec: Specification for the model.
index_to_label: A list that map from index to label class name.
num_classes: Number of label classes.
shuffle: Whether the data should be shuffled.
hparams: A namedtuple of hyperparameters. This function expects
.dropout_rate: The fraction of the input units to drop, used in dropout
layer.
use_augmentation: Use data augmentation for preprocessing.
"""
super(ImageClassifier,
self).__init__(model_export_format, model_spec, index_to_label,
num_classes, shuffle, hparams.do_fine_tuning)
self.hparams = hparams
self.model = self._create_model()
self.preprocessor = image_preprocessing.Preprocessor(
self.model_spec.input_image_shape,
num_classes,
self.model_spec.mean_rgb,
self.model_spec.stddev_rgb,
use_augmentation=use_augmentation)
def test_without_augmentation(self):
preprocessor = image_preprocessing.Preprocessor([2, 2],
2,
mean_rgb=[0.0],
stddev_rgb=[255.0],
use_augmentation=False)
actual_image = np.array([[[0., 0.00392157, 0.00784314],
[0.14117648, 0.14509805, 0.14901961]],
[[0.37647063, 0.3803922, 0.38431376],
[0.5176471, 0.52156866, 0.5254902]]])
image = _get_preprocessed_image(preprocessor)
self.assertTrue(np.allclose(image, actual_image, atol=1e-05))
def test_with_augmentation(self):
image_preprocessing.CROP_PADDING = 1
preprocessor = image_preprocessing.Preprocessor([2, 2],
2,
mean_rgb=[0.0],
stddev_rgb=[255.0],
use_augmentation=True)
# Tests validation image.
actual_eval_image = np.array([[[0.17254902, 0.1764706, 0.18039216],
[0.26666668, 0.27058825, 0.27450982]],
[[0.42352945, 0.427451, 0.43137258],
[0.5176471, 0.52156866, 0.5254902]]])
image = _get_preprocessed_image(preprocessor, is_training=False)
self.assertTrue(np.allclose(image, actual_eval_image, atol=1e-05))
# Tests training image.
image1 = _get_preprocessed_image(preprocessor, is_training=True)
image2 = _get_preprocessed_image(preprocessor, is_training=True)
self.assertFalse(np.allclose(image1, image2, atol=1e-05))
self.assertEqual(image1.shape, (2, 2, 3))
self.assertEqual(image2.shape, (2, 2, 3))
