tensorflow/models · error · ValueError

Stem type {stem_type} not supported.

Error message

Stem type {stem_type} not supported.

What it means

Error "Stem type {stem_type} not supported." thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/backbones/resnet_3d.py:284

      x = tf_utils.get_activation(self._activation)(x)
      x = layers.Conv3D(
          filters=64,
          kernel_size=[1, 3, 3],
          strides=[1, 1, 1],
          use_bias=False,
          padding='same',
          kernel_initializer=self._kernel_initializer,
          kernel_regularizer=self._kernel_regularizer,
          bias_regularizer=self._bias_regularizer)(
              x)
      x = self._norm(
          axis=self._bn_axis,
          momentum=self._norm_momentum,
          epsilon=self._norm_epsilon,
          synchronized=self._use_sync_bn)(x)
      x = tf_utils.get_activation(self._activation)(x)
    else:
      raise ValueError(f'Stem type {stem_type} not supported.')

    return x

  def _block_group(self,
                   inputs: tf.Tensor,
                   filters: int,
                   temporal_kernel_sizes: Tuple[int],
                   temporal_strides: int,
                   spatial_strides: int,
                   block_fn: Callable[
                       ...,
                       tf_keras.layers.Layer] = nn_blocks_3d.BottleneckBlock3D,
                   block_repeats: int = 1,
                   stochastic_depth_drop_rate: float = 0.0,
                   use_self_gating: bool = False,
                   name: str = 'block_group'):
    """Creates one group of blocks for the ResNet3D model.

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use stem_type 'v0' or 'v1' in the ResNet3D backbone config.
2. Remove stem_type to use the default stem.

When it happens

Trigger: Thrown at official/vision/modeling/backbones/resnet_3d.py:284 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/f2b84e88c7a4e23b. Report an issue: GitHub.