tensorflow/models · error · ValueError

Unrecognized pooling method: %s

Error message

Unrecognized pooling method: %s

What it means

Error "Unrecognized pooling method: %s" thrown in tensorflow/models.

Source

Thrown at official/projects/yt8m/modeling/yt8m_model_utils.py:135

      frames = tf.where(
          frame_mask,
          frames,
          tf.ones_like(frames, dtype=frames.dtype)
          * _large_compatible_negative(frames.dtype),
      )
    # Magic to avoid loss NaN when bfloat16 is enabled.
    # See yaqs/5377152819545505792 and b/214396297 for more discussion.
    reduced = tf.reduce_max(frames, 1) + tf.reduce_mean(frames, 1) * 0
  elif method == "swap":
    # Note we assume the frames are in the shape of
    # [batch_size, num_frames, feature_size]. Otherwise this function might
    # fail.
    reduced = frame_swap(frames, frame_mask)
  elif method == "none":
    feature_size = frames.shape.as_list()[2]
    reduced = tf.reshape(frames, [-1, feature_size])
  else:
    raise ValueError("Unrecognized pooling method: %s" % method)

  return reduced

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/yt8m/modeling/yt8m_model_utils.py:135 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/58484fe820e28a18. Report an issue: GitHub.