tensorflow/models · error · ValueError

Unsupported pooling type {}.

Error message

Unsupported pooling type {}.

What it means

Error "Unsupported pooling type {}." thrown in tensorflow/models.

Source

Thrown at official/projects/edgetpu/vision/modeling/heads/bifpn_head.py:262

  def _pool2d(self, inputs, height, width, target_height, target_width):
    """Pools the inputs to target height and width."""
    height_stride_size = int((height - 1) // target_height + 1)
    width_stride_size = int((width - 1) // target_width + 1)
    if self.pooling_type == 'max':
      return tf_keras.layers.MaxPooling2D(
          pool_size=[height_stride_size + 1, width_stride_size + 1],
          strides=[height_stride_size, width_stride_size],
          padding='SAME',
          data_format=self.data_format)(
              inputs)
    if self.pooling_type == 'avg':
      return tf_keras.layers.AveragePooling2D(
          pool_size=[height_stride_size + 1, width_stride_size + 1],
          strides=[height_stride_size, width_stride_size],
          padding='SAME',
          data_format=self.data_format)(
              inputs)
    raise ValueError('Unsupported pooling type {}.'.format(self.pooling_type))

  def _upsample2d(self, inputs, target_height, target_width, training):
    return resize(inputs, target_height, target_width, self.strategy, training,
                  self.upsampling_type)

  def _maybe_apply_1x1(self, feat, training, num_channels):
    """Applies 1x1 conv to change layer width if necessary."""
    target_num_channels = self.target_num_channels
    if target_num_channels is None or num_channels != target_num_channels:
      feat = self.conv2d(feat)
      if self.apply_bn:
        feat = self.bn(feat, training=training)
    return feat

  def build(self, feat_shape):
    num_channels = self.target_num_channels or feat_shape[-1]
    self.conv2d = tf_keras.layers.Conv2D(
        num_channels, (1, 1),

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/edgetpu/vision/modeling/heads/bifpn_head.py:262 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/e2d5c7c31b584e9d. Report an issue: GitHub.