tensorflow/models · error · ValueError
Bad image rank: {}
Error message
Bad image rank: {} What it means
Error "Bad image rank: {}" thrown in tensorflow/models.
Source
Thrown at official/vision/ops/augment.py:599
"""Apply cutout (https://arxiv.org/abs/1708.04552) to image.
This operation applies a (2*pad_size x 2*pad_size) mask of zeros to
a random location within `image`. The pixel values filled in will be of the
value `replace`. The location where the mask will be applied is randomly
chosen uniformly over the whole image.
Args:
image: An image Tensor of type uint8.
pad_size: Specifies how big the zero mask that will be generated is that is
applied to the image. The mask will be of size (2*pad_size x 2*pad_size).
replace: What pixel value to fill in the image in the area that has the
cutout mask applied to it.
Returns:
An image Tensor that is of type uint8.
"""
if image.shape.rank not in [3, 4]:
raise ValueError('Bad image rank: {}'.format(image.shape.rank))
if image.shape.rank == 4:
return cutout_video(image, replace=replace)
image_height = tf.shape(image)[0]
image_width = tf.shape(image)[1]
# Sample the center location in the image where the zero mask will be applied.
cutout_center_height = tf.random.uniform(
shape=[], minval=0, maxval=image_height, dtype=tf.int32)
cutout_center_width = tf.random.uniform(
shape=[], minval=0, maxval=image_width, dtype=tf.int32)
image = _fill_rectangle(image, cutout_center_width, cutout_center_height,
pad_size, pad_size, replace)
return imageView on GitHub (pinned to e006f5f0d5)
Solutions
- Pass an image tensor of the supported rank (3 for HWC or 4 for NHWC as the op requires).
- Add or remove the batch/channel dimension to reach the expected image rank.
When it happens
Trigger: Thrown at official/vision/ops/augment.py:599 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24).
Data as JSON: /api/errors/5430c2b97d9a3a1c.
Report an issue: GitHub.