tensorflow/models · error · ValueError

Bad conversion, model outputs do not match.

Error message

Bad conversion, model outputs do not match.

What it means

Error "Bad conversion, model outputs do not match." thrown in tensorflow/models.

Source

Thrown at official/projects/movinet/tools/convert_3d_2plus1d.py:98

    else:
      if var_3d_2plus1d.shape[0] == 1:
        weight = var_3d_2plus1d[0]
      else:
        weight = var_3d_2plus1d[:, 0]
      if weight.shape[-1] != var_2plus1d.shape[-1]:
        # Transpose any depthwise kernels (conv3d --> depthwise_conv2d)
        weight = tf.transpose(weight, perm=(0, 1, 3, 2))
      weights.append(weight)
  model_2plus1d.set_weights(weights)

  if FLAGS.verify_output:
    inputs = tf.random.uniform([1, 6, 64, 64, 3], dtype=tf.float32)

    logits_2plus1d = model_2plus1d(inputs)
    logits_3d_2plus1d = model_3d_2plus1d(inputs)

    if tf.reduce_mean(logits_2plus1d - logits_3d_2plus1d) > 1e-5:
      raise ValueError('Bad conversion, model outputs do not match.')

  save_checkpoint = tf.train.Checkpoint(
      model=model_2plus1d, backbone=backbone_2plus1d)
  save_checkpoint.save(FLAGS.output_checkpoint_path)


if __name__ == '__main__':
  flags.mark_flag_as_required('input_checkpoint_path')
  flags.mark_flag_as_required('output_checkpoint_path')
  app.run(main)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/movinet/tools/convert_3d_2plus1d.py:98 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/cd51ea34f3b99250. Report an issue: GitHub.