def _parse_train_data(self, decoded_tensors):
"""Parses data for training."""
label = tf.cast(decoded_tensors['image/class/label'], dtype=tf.int32)
image_bytes = decoded_tensors['image/encoded']
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Crops image.
# TODO(pengchong): support image format other than JPEG.
cropped_image = preprocess_ops.random_crop_image_v2(
image_bytes, image_shape)
image = tf.cond(
tf.reduce_all(tf.equal(tf.shape(cropped_image), image_shape)),
lambda: preprocess_ops.center_crop_image_v2(
image_bytes, image_shape), lambda: cropped_image)
if self._aug_rand_hflip:
image = tf.image.random_flip_left_right(image)
# Resizes image.
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
return image, label
def _parse_train_image(self, decoded_tensors):
"""Parses image data for training."""
image_bytes = decoded_tensors[self._image_field_key]
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Crops image.
# TODO(pengchong): support image format other than JPEG.
cropped_image = preprocess_ops.random_crop_image_v2(
image_bytes, image_shape)
image = tf.cond(
tf.reduce_all(tf.equal(tf.shape(cropped_image), image_shape)),
lambda: preprocess_ops.center_crop_image_v2(image_bytes, image_shape),
lambda: cropped_image)
if self._aug_rand_hflip:
image = tf.image.random_flip_left_right(image)
# Resizes image.
image = tf.image.resize(
image, self._output_size, method=tf.image.ResizeMethod.BILINEAR)
# Apply autoaug or randaug.
if self._augmenter is not None:
image = self._augmenter.distort(image)
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
return image
def _parse_eval_data(self, decoded_tensors):
"""Parses data for evaluation."""
label = tf.cast(decoded_tensors['image/class/label'], dtype=tf.int32)
image_bytes = decoded_tensors['image/encoded']
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Center crops and resizes image.
image = preprocess_ops.center_crop_image_v2(image_bytes, image_shape)
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image = tf.reshape(image,
[self._output_size[0], self._output_size[1], 3])
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
return image, label
def _parse_eval_image(self, decoded_tensors):
"""Parses image data for evaluation."""
image_bytes = decoded_tensors[self._image_field_key]
if self._decode_jpeg_only:
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Center crops.
image = preprocess_ops.center_crop_image_v2(
image_bytes, image_shape)
else:
# Decodes image.
image = tf.io.decode_image(image_bytes, channels=3)
image.set_shape([None, None, 3])
# Center crops.
image = preprocess_ops.center_crop_image(image)
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image.set_shape([self._output_size[0], self._output_size[1], 3])
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
return image
def _parse_eval_image(self, decoded_tensors):
"""Parses image data for evaluation."""
image_bytes = decoded_tensors[self._image_field_key]
if self._decode_jpeg_only:
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Center crops.
image = preprocess_ops.center_crop_image_v2(
image_bytes, image_shape)
else:
# Decodes image.
image = tf.io.decode_image(image_bytes, channels=3)
image.set_shape([None, None, 3])
# Center crops.
image = preprocess_ops.center_crop_image(image)
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image.set_shape([self._output_size[0], self._output_size[1], 3])
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
image = image / 255.0
return image
def _parse_train_image(self, decoded_tensors):
"""Parses image data for training."""
image_bytes = decoded_tensors[self._image_field_key]
if self._decode_jpeg_only:
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Crops image.
cropped_image = preprocess_ops.random_crop_image_v2(
image_bytes, image_shape)
image = tf.cond(
tf.reduce_all(tf.equal(tf.shape(cropped_image), image_shape)),
lambda: preprocess_ops.center_crop_image_v2(
image_bytes, image_shape), lambda: cropped_image)
else:
# Decodes image.
image = tf.io.decode_image(image_bytes, channels=3)
image.set_shape([None, None, 3])
# Crops image.
cropped_image = preprocess_ops.random_crop_image(image)
image = tf.cond(
tf.reduce_all(
tf.equal(tf.shape(cropped_image), tf.shape(image))),
lambda: preprocess_ops.center_crop_image(image),
lambda: cropped_image)
if self._aug_rand_hflip:
image = tf.image.random_flip_left_right(image)
# Color jitter.
if self._color_jitter > 0:
image = preprocess_ops.color_jitter(image, self._color_jitter,
self._color_jitter,
self._color_jitter)
# Resizes image.
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image.set_shape([self._output_size[0], self._output_size[1], 3])
# Apply autoaug or randaug.
if self._augmenter is not None:
image = self._augmenter.distort(image)
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Random erasing after the image has been normalized
if self._random_erasing is not None:
image = self._random_erasing.distort(image)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
return image
def _parse_eval_data(self, decoded_tensors):
"""Parses data for evaluation."""
image_bytes = decoded_tensors['image/encoded']
image_shape = tf.image.extract_jpeg_shape(image_bytes)
if self._test_crop:
image = preprocess_ops.center_crop_image_v2(
image_bytes, image_shape)
else:
image = tf.image.decode_jpeg(image_bytes, channels=3)
# This line convert the image to float 0.0 - 1.0
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image = tf.reshape(image,
[self._output_size[0], self._output_size[1], 3])
image = tf.clip_by_value(image, 0., 1.)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
if self._parse_label:
label = tf.cast(decoded_tensors['image/class/label'],
dtype=tf.int32)
return image, label
return image
def _parse_eval_data(self, decoded_tensors):
"""Parses data for evaluation."""
label = tf.cast(decoded_tensors[self._label_field_key], dtype=tf.int32)
image_bytes = decoded_tensors[self._image_field_key]
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Center crops and resizes image.
image = preprocess_ops.center_crop_image_v2(image_bytes, image_shape)
image = tf.image.resize(
image, self._output_size, method=tf.image.ResizeMethod.BILINEAR)
image = tf.reshape(image, [self._output_size[0], self._output_size[1], 3])
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
if self._is_multilabel:
if isinstance(label, tf.sparse.SparseTensor):
label = tf.sparse.to_dense(label)
label = tf.reduce_sum(tf.one_hot(label, self._num_classes), axis=0)
return image, label
def testCenterCropImageV2(self, input_height, input_width):
image_bytes = tf.constant(_encode_image(np.uint8(
np.random.rand(input_height, input_width, 3) * 255),
fmt='JPEG'),
dtype=tf.string)
cropped_image = preprocess_ops.center_crop_image_v2(
image_bytes, tf.constant([input_height, input_width, 3], tf.int32))
cropped_image_shape = tf.shape(cropped_image)
self.assertAllEqual([350, 350, 3], cropped_image_shape.numpy())
def _parse_train_image(self, decoded_tensors):
"""Parses image data for training."""
image_bytes = decoded_tensors[self._image_field_key]
if self._decode_jpeg_only:
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Crops image.
cropped_image = preprocess_ops.random_crop_image_v2(
image_bytes, image_shape)
image = tf.cond(
tf.reduce_all(tf.equal(tf.shape(cropped_image), image_shape)),
lambda: preprocess_ops.center_crop_image_v2(
image_bytes, image_shape), lambda: cropped_image)
else:
# Decodes image.
image = tf.io.decode_image(image_bytes, channels=3)
image.set_shape([None, None, 3])
# Crops image.
cropped_image = preprocess_ops.random_crop_image(image)
image = tf.cond(
tf.reduce_all(
tf.equal(tf.shape(cropped_image), tf.shape(image))),
lambda: preprocess_ops.center_crop_image(image),
lambda: cropped_image)
if self._aug_rand_hflip:
image = tf.image.random_flip_left_right(image)
# Resizes image.
image = tf.image.resize(image,
self._output_size,
method=tf.image.ResizeMethod.BILINEAR)
image.set_shape([self._output_size[0], self._output_size[1], 3])
# Apply autoaug or randaug.
if self._augmenter is not None:
image = self._augmenter.distort(image)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
image = image / 255.0
return image
def _parse_train_data(self, decoded_tensors):
"""Parses data for training."""
label = tf.cast(decoded_tensors[self._label_field_key], dtype=tf.int32)
image_bytes = decoded_tensors[self._image_field_key]
image_shape = tf.image.extract_jpeg_shape(image_bytes)
# Crops image.
# TODO(pengchong): support image format other than JPEG.
cropped_image = preprocess_ops.random_crop_image_v2(
image_bytes, image_shape)
image = tf.cond(
tf.reduce_all(tf.equal(tf.shape(cropped_image), image_shape)),
lambda: preprocess_ops.center_crop_image_v2(image_bytes, image_shape),
lambda: cropped_image)
if self._aug_rand_hflip:
image = tf.image.random_flip_left_right(image)
# Resizes image.
image = tf.image.resize(
image, self._output_size, method=tf.image.ResizeMethod.BILINEAR)
# Apply autoaug or randaug.
if self._augmenter is not None:
image = self._augmenter.distort(image)
# Normalizes image with mean and std pixel values.
image = preprocess_ops.normalize_image(image,
offset=MEAN_RGB,
scale=STDDEV_RGB)
# Convert image to self._dtype.
image = tf.image.convert_image_dtype(image, self._dtype)
if self._is_multilabel:
if isinstance(label, tf.sparse.SparseTensor):
label = tf.sparse.to_dense(label)
label = tf.reduce_sum(tf.one_hot(label, self._num_classes), axis=0)
return image, label
