tensorflow/models · error · ValueError
Only bifpn config is supported
Error message
Only bifpn config is supported
What it means
Error "Only bifpn config is supported" thrown in tensorflow/models.
Source
Thrown at official/projects/edgetpu/vision/modeling/heads/bifpn_head.py:589
max_level=7,
fpn_num_filters=80,
apply_bn_for_resampling=True,
is_training_bn=True,
conv_after_downsample=True,
conv_bn_act_pattern=True,
conv_type='sep_3',
act_type='swish',
strategy='tpu',
fpn_weight_method='sum',
data_format='channels_last',
pooling_type='avg',
upsampling_type='bilinear',
fpn_name='bifpn',
name='fpn_cell',
**kwargs):
super(FPNCell, self).__init__(**kwargs)
if fpn_name != 'bifpn':
raise ValueError('Only bifpn config is supported')
self.fpn_config = bifpn_config(min_level, max_level)
self.fnodes = []
for i, fnode_cfg in enumerate(self.fpn_config['nodes']):
logging.info('fnode %d : %s', i, fnode_cfg)
fnode = FNode(
fnode_cfg['feat_level'] - min_level,
fnode_cfg['inputs_offsets'],
fpn_num_filters=fpn_num_filters,
apply_bn_for_resampling=apply_bn_for_resampling,
is_training_bn=is_training_bn,
conv_after_downsample=conv_after_downsample,
conv_bn_act_pattern=conv_bn_act_pattern,
conv_type=conv_type,
act_type=act_type,
strategy=strategy,
weight_method=fpn_weight_method,
data_format=data_format,
pooling_type=pooling_type,View on GitHub (pinned to e006f5f0d5)
When it happens
Trigger: Thrown at official/projects/edgetpu/vision/modeling/heads/bifpn_head.py:589 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/46cecbe733c3c910.
Report an issue: GitHub.