tensorflow/models · error · ValueError

Unsupported conv_type: {}

Error message

Unsupported conv_type: {}

What it means

Error "Unsupported conv_type: {}" thrown in tensorflow/models.

Source

Thrown at official/projects/s3d/modeling/net_utils.py:179

          dict(
              filters=self._filters,
              kernel_size=[1, self._kernel_size, 1],
              strides=[1, self._strides[1], 1],
              dilation_rate=[1, self._rates[1], 1],
              kernel_initializer=tf_utils.clone_initializer(
                  self._kernel_initializer),
          ))
      conv_layer_params.append(
          dict(
              filters=self._filters,
              kernel_size=[self._kernel_size, 1, 1],
              strides=[self._strides[0], 1, 1],
              dilation_rate=[self._rates[0], 1, 1],
              kernel_initializer=tf_utils.clone_initializer(
                  self._kernel_initializer),
          ))
    else:
      raise ValueError('Unsupported conv_type: {}'.format(self._conv_type))
    return conv_layer_params

  def _build_norm_layer_params(self, conv_param):
    """Builds params for the norm layer after one conv layer."""
    return dict(
        axis=self._channel_axis,
        momentum=self._norm_momentum,
        epsilon=self._norm_epsilon,
        scale=False,
        gamma_initializer='ones')

  def _build_activation_layer_params(self, conv_param):
    """Builds params for the activation layer after one conv layer."""
    return {}

  def _append_conv_layer(self, param):
    """Appends conv, normalization and activation layers."""
    self._parameterized_conv_layers.append(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/s3d/modeling/net_utils.py:179 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/c4f665c3e972f9c7. Report an issue: GitHub.