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.

Sign up for GitHub

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

Jump to bottom

[GSoC] Add block quantized models #270

Open
wants to merge 12 commits into
base: main
Choose a base branch
from
Open

[GSoC] Add block quantized models #270

wants to merge 12 commits into from

Commits on Aug 4, 2024

  1. Gemm and MatMul block quantization support

    @DaniAffCH
    DaniAffCH committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    4698403 View commit details
    Browse the repository at this point in the history

  2. refactoring

    @DaniAffCH
    DaniAffCH committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    10cbbeb View commit details
    Browse the repository at this point in the history

  3. fix indentation

    @DaniAffCH
    DaniAffCH committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    974d32e View commit details
    Browse the repository at this point in the history

Commits on Aug 7, 2024

  1. node name independent

    @DaniAffCH
    DaniAffCH committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    00b8dde View commit details
    Browse the repository at this point in the history

Commits on Aug 15, 2024

  1. Merge branch 'main' of https://github.com/DaniAffCH/opencv_zoo

    @DaniAffCH
    DaniAffCH committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    fb54356 View commit details
    Browse the repository at this point in the history

  2. Block quantization tool: 

    - constant weight category supported
- add data type saturation
- handled the case in which all the elements within a block are the same

benchmark script modified to support block quantized models

block quantized some models
    @DaniAffCH
    DaniAffCH committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    fd7c9fb View commit details
    Browse the repository at this point in the history

  3. add missing block quantized models

    @DaniAffCH
    DaniAffCH committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    5639eba View commit details
    Browse the repository at this point in the history

  4. formatting

    @DaniAffCH
    DaniAffCH committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    0009ab6 View commit details
    Browse the repository at this point in the history

Commits on Aug 17, 2024

  1. add blocked models to eval script. Evaluation yunet

    @DaniAffCH
    DaniAffCH committed Aug 17, 2024
    Configuration menu
    Copy the full SHA
    0fbcdaf View commit details
    Browse the repository at this point in the history

  2. Add sface and pphumanseg evaluation, block quantization tool fix, han… 

    …dpose blocked model fix, removed blocked CRNN EN,
    @DaniAffCH
    DaniAffCH committed Aug 17, 2024
    Configuration menu
    Copy the full SHA
    1642774 View commit details
    Browse the repository at this point in the history

Commits on Aug 18, 2024

  1. changed evaluation metric in block_quantize script and add verbose mode

    @DaniAffCH
    DaniAffCH committed Aug 18, 2024
    Configuration menu
    Copy the full SHA
    11806d7 View commit details
    Browse the repository at this point in the history

  2. Add evaluation for PP-ResNet and Mobilenet

    @DaniAffCH
    DaniAffCH committed Aug 18, 2024
    Configuration menu
    Copy the full SHA
    4f59fc7 View commit details
    Browse the repository at this point in the history