keras-team/keras · error · ValueError
Invalid images rank: expected rank 3 (single image) or rank
Error message
Invalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received input with shape: images.shape={images.shape} What it means
Error "Invalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received input with shape: images.shape={images.shape}" thrown in keras-team/keras.
Source
Thrown at keras/src/backend/openvino/image.py:57
"nearest": "nearest",
"bicubic": "cubic",
}
# Lanczos methods are handled via _ov_scale_and_translate
# instead of ov_opset.interpolate, which does not support them natively.
LANCZOS_INTERPOLATIONS = {
"lanczos3": "lanczos3",
"lanczos5": "lanczos5",
}
ALL_RESIZE_INTERPOLATIONS = tuple(RESIZE_INTERPOLATIONS) + tuple(
LANCZOS_INTERPOLATIONS
)
def rgb_to_grayscale(images, data_format=None):
images = get_ov_output(images)
data_format = backend.standardize_data_format(data_format)
if images.get_partial_shape().rank not in (3, 4):
raise ValueError(
"Invalid images rank: expected rank 3 (single image) "
"or rank 4 (batch of images). Received input with shape: "
f"images.shape={images.shape}"
)
channel_axis = -3 if data_format == "channels_first" else -1
if images.shape[channel_axis] not in (1, 3):
raise ValueError(
"Invalid channel size: expected 3 (RGB) or 1 (Grayscale). "
f"Received input with shape: images.shape={images.shape}"
)
if images.shape[channel_axis] == 3:
original_type = images.get_element_type()
rgb_weights = ov_opset.constant(
[0.2989, 0.5870, 0.1140], dtype=original_type
).output(0)
if data_format == "channels_first":
rgb_weights = ov_opset.unsqueeze(rgb_weights, axes=[-2, -1]).output(View on GitHub (pinned to 7a34a03db6)
When it happens
Trigger: Thrown at keras/src/backend/openvino/image.py:57 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25).
Data as JSON: /api/errors/b375d9f105bdf151.
Report an issue: GitHub.