tensorflow/models · error · ValueError

Unsupported activation

Error message

Unsupported activation `{}`.

What it means

Enum guard in the ResNet backbone constructor: the activation argument is neither 'relu' nor 'swish', so the backbone's norm-activation blocks cannot select an activation function. The input at fault is the activation parameter (often mirrored into a norm_activation builder with 'relu').

Solutions

1. Pass activation='relu' or 'swish' when constructing the Resnet backbone
2. Align the activation value with the norm_activation builder configuration

When it happens

Trigger: Thrown at official/legacy/detection/modeling/architecture/resnet.py:56 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/15bf1c6165442921. Report an issue: GitHub.

Appendix: source

Thrown at official/legacy/detection/modeling/architecture/resnet.py:56

      norm_activation=nn_ops.norm_activation_builder(activation='relu'),
      data_format='channels_last'):
    """ResNet initialization function.

    Args:
      resnet_depth: `int` depth of ResNet backbone model.
      activation: the activation function.
      norm_activation: an operation that includes a normalization layer followed
        by an optional activation layer.
      data_format: `str` either "channels_first" for `[batch, channels, height,
        width]` or "channels_last for `[batch, height, width, channels]`.
    """
    self._resnet_depth = resnet_depth
    if activation == 'relu':
      self._activation_op = tf.nn.relu
    elif activation == 'swish':
      self._activation_op = tf.nn.swish
    else:
      raise ValueError('Unsupported activation `{}`.'.format(activation))
    self._norm_activation = norm_activation
    self._data_format = data_format

    model_params = {
        10: {
            'block': self.residual_block,
            'layers': [1, 1, 1, 1]
        },
        18: {
            'block': self.residual_block,
            'layers': [2, 2, 2, 2]
        },
        34: {
            'block': self.residual_block,
            'layers': [3, 4, 6, 3]
        },
        50: {
            'block': self.bottleneck_block,

View on GitHub (pinned to e006f5f0d5)