def resize_im(image, image_size, pad_val, channels, elements_boxes=None):
"""Decodes and resizes the image.
Args:
image: Image to resize.
image_size: The desired max image size.
pad_val: The value to pad with.
channels: The number of channels in the image.
elements_boxes: The boxes from elements to resize.
Returns:
Resized image with possible padded regions,
and possibly the resized elements boxes.
"""
[width, height, got_channels] = preprocess_utils.resolve_shape(image, rank=3)
new_width, new_height = get_resize_dim(width, height, image_size)
image = tf.reshape(image, [width, height, -1])
image = tf.cond(
tf.logical_and(channels == 3, tf.equal(got_channels, 1)),
true_fn=lambda: tf.image.grayscale_to_rgb(image),
false_fn=lambda: image,
)
image = tf.image.resize_images(image, [new_width, new_height])
image = preprocess_utils.pad_to_bounding_box(image, 0, 0, image_size,
image_size, pad_val)
if elements_boxes is not None:
return image, elements_boxes / tf.to_float(tf.maximum(width, height))
return image
def resize_im(image, image_size, pad_val, channels, features=None):
"""Decodes and resizes the image.
Args:
image: Image to resize.
image_size: The desired max image size.
pad_val: The value to pad with.
channels: The number of channels in the image.
features: Other features to resize.
Returns:
Resized image with possible padded regions,
and possibly the resized elements boxes.
"""
[height, width, got_channels] = preprocess_utils.resolve_shape(image,
rank=3)
new_height, new_width = get_resize_dim(height, width, image_size)
image = tf.reshape(image, [height, width, -1])
image = tf.cond(
tf.logical_and(channels == 3, tf.equal(got_channels, 1)),
true_fn=lambda: tf.image.grayscale_to_rgb(image),
false_fn=lambda: image,
)
image = tf.image.resize_images(image, [new_height, new_width])
image = preprocess_utils.pad_to_bounding_box(image, 0, 0, image_size,
image_size, pad_val)
if features is not None:
width, height = tf.to_float(width), tf.to_float(height)
max_dim = tf.to_float(tf.maximum(width, height))
features[ELEMENTS_BOX_ID] = features[ELEMENTS_BOX_ID] / max_dim
if GROUNDTRUTH_XMIN_ID in features:
features[GROUNDTRUTH_XMIN_ID] *= width / max_dim
features[GROUNDTRUTH_XMAX_ID] *= width / max_dim
features[GROUNDTRUTH_YMIN_ID] *= height / max_dim
features[GROUNDTRUTH_YMAX_ID] *= height / max_dim
return image