Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[QUANTIZE] Refactor quantization codebase and fix model accuracy #3762

Closed
wants to merge 8 commits into from

Conversation

ZihengJiang
Copy link
Contributor

A mirror PR of #3543 due to CI error.

  • Separate quantization code base into different files: partition.cc, annotate.cc, realize.cc
  • Change rewrite_for_vta to extra partition pass and enable it by default
  • Change annotation.force_cast(x) to annotation.cast_hint(x, dtype)
  • Remove qconfig.store_lowbit_output and enable it by default
  • Fixed accuracy of models like mobilenet:
    • resnet18_v1(8-16bit): 69.29%
    • resnet18_v1(8-32bit): 69.29%
    • resnet34_v1: 73.33%
    • resnet50_v1: 74.78%
    • resnet101_v1: 75.66%
    • mobilenetv2_1.0: 66.64%

@tmoreau89
Copy link
Contributor

@nhynes do you happen to know why the rust CI error is occurring on this PR? Thanks!

@ZihengJiang ZihengJiang deleted the quantize-test-ci branch August 15, 2019 09:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants