Hide navigation sidebar

Hide table of contents sidebar

Skip to content

Toggle site navigation sidebar

Toggle table of contents sidebar

Version: 2.2.0
Other versions

Quick Start
Installation
User Guide
Toggle navigation of User Guide
Quantization Simulation Guide
Toggle navigation of Quantization Simulation Guide
Feature Guide
Toggle navigation of Feature Guide
- Adaptive rounding
- Sequential MSE
- Batch norm folding
- Cross-layer equalization
- Mixed precision
  Toggle navigation of Mixed precision
  - Manual mixed precision
  - Automatic mixed precision
- Automatic quantization
- Batch norm re-estimation
- Analysis tools
  Toggle navigation of Analysis tools
- Compression
  Toggle navigation of Compression
  - Compression guidebook
  - Greedy compression ratio selection
  - Visualization
  - Weight SVD
  - Spatial SVD
  - Channel pruning
    Toggle navigation of Channel pruning
    - Winnowing
- Quantized LoRa
  Toggle navigation of Quantized LoRa
  - QW-LoRa
  - QWA-LoRa
Example Notebooks
API Reference
Toggle navigation of API Reference
Release Notes

Toggle table of contents sidebar

aimet_onnx.adaround¶

Note

It is recommended to use onnx-simplifier before adarounding the model.

Top-level API

Adaround Parameters

aimet_onnx.seq_mse

aimet_onnx.quantsim

Copyright © 2020, Qualcomm Innovation Center, Inc.

Made with Sphinx and @pradyunsg's Furo