I have original images of the size 1935x1481. I am using labelme to annotate the images. I am creating polygons on the original image. Is there a way to resize the image along with their mask? I am planning to use TFOD mask-rcnn and I know it will resize the image but what happens to the mask?


In this tutorial they use the following to resize the image and mask.

Is it applicable to your use-case?

def load_image_train(datapoint):
  input_image = tf.image.resize(datapoint['image'], (128, 128))
  input_mask = tf.image.resize(datapoint['segmentation_mask'], (128, 128))

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.