Skipping Quantization

Raef YoussefRaef Youssef
in AI Model migration

Is it possible to skip quantization when migrating an ONNX model? I'm experimenting with pytorch quantization and I'm worried the two might interfere with each other.

Tagged:

Comments

  • kiddkidd

    Kneron quantization is different than PyTorch's method, and the quantization has to do with the hardware implementation. So to run the model in the Kneron device, users cannot use models that already quantize from another platform. So you should always provide a floating model for the Kneron toolchain.

  • Raef YoussefRaef Youssef

    Thanks kidd, is there anyway to implement quantization aware training (QAT) with models before exporting to Kneron?

The discussion has been closed due to inactivity. To continue with the topic, please feel free to post a new discussion.

© Kneron, Inc.