Skip to content

[FEATURE] Optimization of Image Embedding & Clustering Inference #1240

@anzinmhd

Description

@anzinmhd

Describe the feature

While exploring the codebase, I noticed that the current face clustering and image embedding generation could be optimized for multi-core systems.

I recently completed a research internship at IIT Palakkad specifically focusing on matrix multiplication optimization in multi-core systems. I'd like to propose a project for GSoC 2026 to implement high-performance inference pipelines for PictoPy, ensuring it handles large libraries smoothly on modern hardware (like Apple Silicon/M-series chips).

I am already familiar with the Python ML stack and would love to discuss how I can integrate these optimizations into the core logic.

Image

Add ScreenShots

Validated the PictoPy backend on macOS 15 (M5 ARM64). Successfully resolved dependency conflicts and confirmed native execution via the Apple Silicon process 'Python' (PID 2822). The server is active and listening on port 52123.

Record

  • I agree to follow this project's Code of Conduct
  • I want to work on this issue

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions