tensorflow/models · error · ValueError

Temporal conv with spatial kernel is not supported.

Error message

Temporal conv with spatial kernel is not supported.

What it means

Error "Temporal conv with spatial kernel is not supported." thrown in tensorflow/models.

Source

Thrown at official/projects/movinet/modeling/movinet_layers.py:154

    self._groups = groups
    self._use_bias = use_bias
    self._kernel_initializer = kernel_initializer
    self._bias_initializer = bias_initializer
    self._kernel_regularizer = kernel_regularizer
    self._bias_regularizer = bias_regularizer
    self._activity_regularizer = activity_regularizer
    self._kernel_constraint = kernel_constraint
    self._bias_constraint = bias_constraint
    self._use_depthwise = use_depthwise
    self._use_temporal = use_temporal
    self._use_buffered_input = use_buffered_input
    self._batch_norm_op = batch_norm_op
    self._activation_op = activation_op

    kernel_size = normalize_tuple(kernel_size, 2, 'kernel_size')  # pyrefly: ignore[bad-argument-type]

    if self._use_temporal and kernel_size[1] > 1:
      raise ValueError('Temporal conv with spatial kernel is not supported.')

    if use_depthwise:
      self._conv = nn_layers.DepthwiseConv2D(
          kernel_size=kernel_size,
          strides=strides,
          padding=padding,
          depth_multiplier=1,
          data_format=data_format,
          dilation_rate=dilation_rate,
          use_bias=use_bias,
          depthwise_initializer=kernel_initializer,
          bias_initializer=bias_initializer,
          depthwise_regularizer=kernel_regularizer,
          bias_regularizer=bias_regularizer,
          activity_regularizer=activity_regularizer,
          depthwise_constraint=kernel_constraint,
          bias_constraint=bias_constraint,
          use_buffered_input=use_buffered_input)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/movinet/modeling/movinet_layers.py:154 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/857d4a0db5d6f6c7. Report an issue: GitHub.