tensorflow/models · error · ValueError

The number of Decoder inputs and settings must match.

Error message

The number of Decoder inputs and settings must match.

What it means

Error "The number of Decoder inputs and settings must match." thrown in tensorflow/models.

Source

Thrown at official/projects/mosaic/qat/modeling/heads/mosaic_head.py:131

    # Assuming decoder_input_levels and the following lists are sorted and
    # follow the same order.
    if decoder_input_levels is None:
      decoder_input_levels = ['3', '2']
    if decoder_stage_merge_styles is None:
      decoder_stage_merge_styles = ['concat_merge', 'sum_merge']
    if decoder_filters is None:
      decoder_filters = [64, 64]
    if decoder_projected_filters is None:
      decoder_projected_filters = [32, 32]
    self._decoder_input_levels = decoder_input_levels
    self._decoder_stage_merge_styles = decoder_stage_merge_styles
    self._decoder_filters = decoder_filters
    self._decoder_projected_filters = decoder_projected_filters
    if (len(decoder_input_levels) != len(decoder_stage_merge_styles) or
        len(decoder_input_levels) != len(decoder_filters) or
        len(decoder_input_levels) != len(decoder_projected_filters)):
      raise ValueError('The number of Decoder inputs and settings must match.')
    self._merge_stages = []
    for (stage_merge_style, decoder_filter,
         decoder_projected_filter) in zip(decoder_stage_merge_styles,
                                          decoder_filters,
                                          decoder_projected_filters):
      if stage_merge_style == 'concat_merge':
        concat_merge_stage = nn_blocks.DecoderConcatMergeBlockQuantized(
            decoder_internal_depth=decoder_filter,
            decoder_projected_depth=decoder_projected_filter,
            output_size=(0, 0),
            use_sync_bn=use_sync_bn,
            batchnorm_momentum=batchnorm_momentum,
            batchnorm_epsilon=batchnorm_epsilon,
            activation=activation,
            kernel_initializer=kernel_initializer,
            kernel_regularizer=kernel_regularizer,
            interpolation=interpolation)
        self._merge_stages.append(concat_merge_stage)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/mosaic/qat/modeling/heads/mosaic_head.py:131 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/9f1a234d46249c6c. Report an issue: GitHub.