E0403 — NonFiniteWeights

​

What happened

​

Why

​

How to fix

1. Identify the source. Check where in training the weights diverge. Add gradient clipping:
   torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
   
2. Check your loss function for instability — a log(0) or division by zero in the loss will propagate Inf through the backward pass.
3. Re-export the model after fixing the training issue and verify with:
   for name, param in model.named_parameters():
       assert torch.isfinite(param).all(), f"{name} contains non-finite values"
   
4. Recompile the corrected model for akida-akd1500.

​

Example

E0403: layer[2] weights_b64 contains non-finite values.
Observed: 14 NaN or Inf values found in decoded weight tensor.
Why: AKD1500 requires integer-quantizable weights. Quantization of non-finite
     floats is undefined and would produce silent garbage output.
What to do: Check the training pipeline for numerical instability.
            Re-export the model with finite weights.
Docs: https://docs.thrindex.com/errors/E0403