hpcaitech/Open-Sora · error · ValueError
shortcut {shortcut} is not supported for encoder project out
Error message
shortcut {shortcut} is not supported for encoder project out What it means
The encoder project_out block supports only None and 'averaging' shortcut modes. Any other shortcut string in the encoder's project_out config raises this ValueError during Encoder construction.
Source
Thrown at opensora/models/dc_ae/models/dc_ae.py:310
out_channels=out_channels,
kernel_size=3,
stride=1,
use_bias=True,
norm=None,
act_func=None,
is_video=is_video,
),
]
)
if shortcut is None:
pass
elif shortcut == "averaging":
shortcut_block = PixelUnshuffleChannelAveragingDownSampleLayer(
in_channels=in_channels, out_channels=out_channels, factor=1
)
block = ResidualBlock(block, shortcut_block)
else:
raise ValueError(f"shortcut {shortcut} is not supported for encoder project out")
return block
def build_decoder_project_in_block(in_channels: int, out_channels: int, shortcut: Optional[str], is_video: bool):
block = ConvLayer(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=3,
stride=1,
use_bias=True,
norm=None,
act_func=None,
is_video=is_video,
)
if shortcut is None:
pass
elif shortcut == "duplicating":
shortcut_block = ChannelDuplicatingPixelShuffleUpSampleLayer(View on GitHub (pinned to 7ad6a96a13)
Solutions
- Set the encoder project_out shortcut to null/None or 'averaging'
- Validate the whole config against a shipped example before model init
Example fix
# before shortcut: duplicating # encoder project_out # after shortcut: averaging
Defensive patterns
Strategy: validation
Validate before calling
assert shortcut in (None, 'averaging'), f'unsupported encoder project_out shortcut: {shortcut}' Prevention
- Validate shortcut per block kind
- Keep a reference config and diff against it
When it happens
Trigger: Setting project_out shortcut to a value other than null or 'averaging' (e.g. 'identity', 'duplicating') in the DCAE encoder config.
Common situations: Copy-pasting shortcut settings between encoder/decoder stages whose allowed vocabularies differ; hand-edited configs.
Understand the failure class
Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.
Related errors
- block_type {block_type} is not supported
- block_type {block_type} is not supported for downsampling
- shortcut {shortcut} is not supported for downsample
- block_type {block_type} is not supported for upsampling
- shortcut {shortcut} is not supported for upsample
AI-assisted analysis of hpcaitech/Open-Sora@7ad6a96a13 (2026-08-28).
Data as JSON: /api/errors/2cb62b9bf589eb22.
Report an issue: GitHub.