tensorflow/models · error · ValueError

Expected rank 4 input, was: %d

Error message

Expected rank 4 input, was: %d

What it means

Error "Expected rank 4 input, was: %d" thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/backbones/mobiledet.py:448

  def _get_divisible_by(self):
    return self._divisible_by

  def _mobiledet_base(self,
                      inputs: tf.Tensor
                      ) -> Tuple[tf.Tensor, Dict[str, tf.Tensor], int]:
    """Builds the base MobileDet architecture.

    Args:
      inputs: A `tf.Tensor` of shape `[batch_size, height, width, channels]`.

    Returns:
      A tuple of output Tensor and dictionary that collects endpoints.
    """

    input_shape = inputs.get_shape().as_list()
    if len(input_shape) != 4:
      raise ValueError('Expected rank 4 input, was: %d' % len(input_shape))

    net = inputs
    endpoints = {}
    endpoint_level = 1
    for i, block_def in enumerate(self._decoded_specs):
      block_name = 'block_group_{}_{}'.format(block_def.block_fn, i)

      if block_def.block_fn == 'convbn':

        net = mobilenet.Conv2DBNBlock(
            filters=block_def.filters,
            kernel_size=block_def.kernel_size,
            strides=block_def.strides,
            activation=block_def.activation,
            use_bias=block_def.use_bias,
            use_normalization=block_def.use_normalization,
            kernel_initializer=self._kernel_initializer,
            kernel_regularizer=self._kernel_regularizer,

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Feed a rank-4 tensor [batch, height, width, channels] as input.
2. Add the missing batch or channel dimension, e.g. with tf.expand_dims, before calling the backbone.

When it happens

Trigger: Thrown at official/vision/modeling/backbones/mobiledet.py:448 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/3439b28c3515a327. Report an issue: GitHub.