E0007 — WeightShapeMismatch - THRINDEX

E0007: weight shape mismatch

What happened

The artifact declares a Dense layer with in_features × out_features weights, but the decoded base64 array has a different number of f32 values.

Why

The artifact is corrupt. The base64-decoded bytes decode successfully, but their length is inconsistent with the declared layer dimensions. Likely cause: truncated or modified artifact file.

How to fix

Recompile from scratch: thx.compile(model, "model.thx").
Verify artifact integrity: thrindex doctor --check model.thx. A CRC32 mismatch will accompany this error.

Example

E0007: weight shape mismatch in layer 0: declared 358400 f32 values but decoded 1433596 bytes (358399 f32 values).
Why: the artifact's weight data is corrupt.
Fix: recompile the model from scratch.
Docs: https://docs.thrindex.com/errors/E0007

Notes

Each f32 value is 4 bytes. If the decoded byte count is not divisible by 4, the error reports the byte count and the floor of bytes / 4.