tensorflow/models · error · ValueError
filter_size_scale is not greater than zero.
Error message
filter_size_scale is not greater than zero.
What it means
Error "filter_size_scale is not greater than zero." thrown in tensorflow/models.
Source
Thrown at official/vision/modeling/backbones/mobiledet.py:401
kernel_regularizer: A `tf_keras.regularizers.Regularizer` object for
Conv2D. Default to None.
bias_regularizer: A `tf_keras.regularizers.Regularizer` object for Conv2D.
Default to None.
min_depth: An `int` of minimum depth (number of channels) for all
convolution ops. Enforced when filter_size_scale < 1, and not an active
constraint when filter_size_scale >= 1.
divisible_by: An `int` that ensures all inner dimensions are divisible by
this number.
regularize_depthwise: If Ture, apply regularization on depthwise.
use_sync_bn: If True, use synchronized batch normalization.
**kwargs: Additional keyword arguments to be passed.
"""
if model_id not in SUPPORTED_SPECS_MAP:
raise ValueError('The MobileDet version {} '
'is not supported'.format(model_id))
if filter_size_scale <= 0:
raise ValueError('filter_size_scale is not greater than zero.')
self._model_id = model_id
self._input_specs = input_specs
self._filter_size_scale = filter_size_scale
self._min_depth = min_depth
self._divisible_by = divisible_by
self._regularize_depthwise = regularize_depthwise
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
inputs = tf_keras.Input(shape=input_specs.shape[1:])
block_specs = SUPPORTED_SPECS_MAP.get(model_id)
self._decoded_specs = block_spec_decoder(View on GitHub (pinned to e006f5f0d5)
Solutions
- Set filter_size_scale to a positive float (e.g. 1.0).
- Remove filter_size_scale from the config to use the default scaling.
When it happens
Trigger: Thrown at official/vision/modeling/backbones/mobiledet.py:401 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/59ccfb025f28dcbf.
Report an issue: GitHub.