Rotoclear AI Chatbot ↗
A retrieval-augmented assistant connecting product knowledge with natural-language questions.
Organisation repository / AI & vision
Grayscale RTMDet
An RTMDet-style detection framework for grayscale industrial images, spanning training and Hailo edge deployment.
Discuss the work ↗Grayscale RTMDetA visual introduction
HUMAN + MACHINE
Look closer.
Synthetic inspection scene
01 / THE CONTEXTA closer look at
A closer look at
the work.
An RTMDet-style detection framework for grayscale industrial images, spanning training and Hailo edge deployment.
TOOLS & TECHNOLOGIES
RTMDetHailoComputer vision
This repository belongs to an organisation I work with. Inclusion describes the project landscape and is not a claim of individual authorship.
SYSTEM MAPSelect a component to explore ↙
One image channel, an edge target
Grayscale images
Single-channel industrial imagery defines the input.
Simplified architecture · illustrative, not a product screenshot
02 / INSIDE THE PROJECT
Behind the diagram.
Technical notes, when you want to go deeper.
01Implementation
An RTMDet-style detector is adapted to single-channel industrial imagery. The project combines a CSPNeXt-style backbone, feature aggregation and detection heads with staged training and augmentation.
02Key decision
Deployment constraints shape the model as well as the training. ONNX export and Hailo-friendly operations connect the research model to an accelerator compilation path.
03Current scope
Evaluation utilities and an edge-deployment direction are documented. No benchmark accuracy or target throughput is reported here without verified results.
REPOSITORY NOTES
A closer look.
Source code is private. The portfolio contains a high-level description, without internal files or customer data.
Discuss the work ↗- Repository
- rtmdet-grayscale-edge
- Editorial basis
- Repository documentation
- Default branch
- main