Gaze

Beta

A compound eye for your camera.

What is where, every frame. Object detection.

Platforms	Python, JavaScript, Rust
Engine	FlyCore v0.1.0
Weights	v0.1.0-beta
Input ports	Frames (compound eye) → visual (11,390)
Output ports	Position + motion readout ← optic; Boxes, velocities ← central
Co-processors	CNN classifier (labels)

The 3D view needs WebGPU or WebGL2.

Install

Python

pip

pip install flycore

Rust

Cargo

cargo add flycore

JavaScript

Terminal

npm i @flylabs/flycore

Usage

Gaze detects and tracks objects in video through the connectome's visual system, with a classical CNN co-processor for class labels. Built for motion, so it finds what moves first.

Python

import flycore

brain = flycore.load("flylabs/gaze")      # engine + weights + adapters
for frame in flycore.io.Camera():
    objects = brain(frame)
# objects -> [Object(box, cls, velocity, score), ...]

Figures

Figures marked target are design targets for the first release, not measurements.

Throughput	30 fpstarget Apple M-series, full connectome
mAP	0.71target COCO-motion subset

Limits

Beta: 80 COCO classes only; custom classes need a co-processor fine-tune.
Weak on static scenes by design.