tensorflow/models · error · ValueError
Got mismatched input and output state shapes: {}
Error message
Got mismatched input and output state shapes: {} What it means
Error "Got mismatched input and output state shapes: {}" thrown in tensorflow/models.
Source
Thrown at official/projects/movinet/modeling/movinet_model.py:142
new_states = set(after_states) - set(before_states)
if new_states:
raise ValueError(
'Expected input and output states to be the same. Got extra states '
'{}, expected {}'.format(new_states, set(before_states)))
mismatched_shapes = {}
for name in after_states:
before_shape = before_states[name].shape
after_shape = after_states[name].shape
if len(before_shape) != len(after_shape):
mismatched_shapes[name] = (before_shape, after_shape)
continue
for before, after in zip(before_shape, after_shape):
if before is not None and after is not None and before != after:
mismatched_shapes[name] = (before_shape, after_shape)
break
if mismatched_shapes:
raise ValueError(
'Got mismatched input and output state shapes: {}'.format(
mismatched_shapes))
else:
endpoints, states = backbone(inputs)
return inputs, endpoints, states
def _build_network(
self,
backbone: tf_keras.Model,
input_specs: Mapping[str, tf_keras.layers.InputSpec],
state_specs: Optional[Mapping[str, tf_keras.layers.InputSpec]] = None,
) -> Tuple[Mapping[str, tf_keras.Input], Union[Tuple[Mapping[ # pytype: disable=invalid-annotation # typed-keras
str, tf.Tensor], Mapping[str, tf.Tensor]], Mapping[str, tf.Tensor]]]:
"""Builds the model network.
Args:
backbone: the model backbone.
input_specs: the model input spec to use.View on GitHub (pinned to e006f5f0d5)
When it happens
Trigger: Thrown at official/projects/movinet/modeling/movinet_model.py:142 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/92222e7ea824a3e0.
Report an issue: GitHub.