aimet_onnx.apply_seq_mse

Top level APIs

aimet_onnx.apply_seq_mse(sim, inputs, num_candidates=20, nodes_to_exclude=None)[source]

Sequentially optimizes the QuantizationSimModel’s weight encodings to reduce MSE loss at layer outputs.

Parameters:

  • sim (QuantizationSimModel) – QuantizationSimModel instance to optimize

  • inputs (Collection[Dict[str, np.ndarray]]) – The set of input samples to use during optimization

  • num_candidates (int) – Number of encoding candidates to sweep for each weight. Decreasing this can reduce runtime but may lead to lower accuracy.

  • nodes_to_exclude (Optional[List[str]]) – List of supported node name(s) to exclude from sequential MSE optimization