|View source on GitHub|
Extracts crops from the input image tensor and resizes them.
tf.image.crop_and_resize( image, boxes, box_indices, crop_size, method='bilinear', extrapolation_value=0, name=None )
Extracts crops from the input image tensor and resizes them using bilinear sampling or nearest neighbor sampling (possibly with aspect ratio change) to a common output size specified by
crop_size. This is more general than the
crop_to_bounding_box op which extracts a fixed size slice from the input image and does not allow resizing or aspect ratio change.
Returns a tensor with
crops from the input
image at positions defined at the bounding box locations in
boxes. The cropped boxes are all resized (with bilinear or nearest neighbor interpolation) to a fixed
size = [crop_height, crop_width]. The result is a 4-D tensor
[num_boxes, crop_height, crop_width, depth]. The resizing is corner aligned. In particular, if
boxes = [[0, 0, 1, 1]], the method will give identical results to using
tf.compat.v1.image.resize_nearest_neighbor()(depends on the
method argument) with
| || A 4-D tensor of shape |
| || A 2-D tensor of shape |
| || A 1-D tensor of shape |
| || A 1-D tensor of 2 elements, |
| || An optional string specifying the sampling method for resizing. It can be either |
| || An optional |
| ||A name for the operation (optional).|
| A 4-D tensor of shape |
import tensorflow as tf BATCH_SIZE = 1 NUM_BOXES = 5 IMAGE_HEIGHT = 256 IMAGE_WIDTH = 256 CHANNELS = 3 CROP_SIZE = (24, 24) image = tf.random.normal(shape=(BATCH_SIZE, IMAGE_HEIGHT, IMAGE_WIDTH, CHANNELS) ) boxes = tf.random.uniform(shape=(NUM_BOXES, 4)) box_indices = tf.random.uniform(shape=(NUM_BOXES,), minval=0, maxval=BATCH_SIZE, dtype=tf.int32) output = tf.image.crop_and_resize(image, boxes, box_indices, CROP_SIZE) output.shape #=> (5, 24, 24, 3)
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.