tensorflow/models · error · ValueError

Activation {} not implemented.

Error message

Activation {} not implemented.

What it means

Error "Activation {} not implemented." thrown in tensorflow/models.

Source

Thrown at official/legacy/detection/modeling/architecture/spinenet.py:155

    self._block_specs = (
        build_block_specs() if block_specs is None else block_specs
    )
    self._endpoints_num_filters = endpoints_num_filters
    self._resample_alpha = resample_alpha
    self._block_repeats = block_repeats
    self._filter_size_scale = filter_size_scale
    self._kernel_initializer = kernel_initializer
    self._kernel_regularizer = kernel_regularizer
    self._bias_regularizer = bias_regularizer
    self._use_sync_bn = use_sync_bn
    self._norm_momentum = norm_momentum
    self._norm_epsilon = norm_epsilon
    if activation == 'relu':
      self._activation = tf.nn.relu
    elif activation == 'swish':
      self._activation = tf.nn.swish
    else:
      raise ValueError('Activation {} not implemented.'.format(activation))
    self._init_block_fn = 'bottleneck'
    self._num_init_blocks = 2

    if use_sync_bn:
      self._norm = layers.experimental.SyncBatchNormalization
    else:
      self._norm = layers.BatchNormalization

    if tf_keras.backend.image_data_format() == 'channels_last':
      self._bn_axis = -1
    else:
      self._bn_axis = 1

    # Build SpineNet.
    inputs = tf_keras.Input(shape=input_specs.shape[1:])

    net = self._build_stem(inputs=inputs)
    net = self._build_scale_permuted_network(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/legacy/detection/modeling/architecture/spinenet.py:155 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/91cf8f9e489029fc. Report an issue: GitHub.