Skip to content

Repository files navigation

DeskMate Deep Learning Demo

This repository contains the Deep Learning and behavior-decision subproject for a NUS Deep Learning and robotics summer-school demo. The current directory is the project-structure root, even when it is checked out inside a larger course workspace. All project plans, logs, rules, code, tests, and documentation are relative to this directory.

Current Direction

Work is split into two sequential phases:

Official Baseline (now, due 17 July)
robot stream -> five-breed cat classifier -> visible console/UI -> census
                          |
                          v reuse proven infrastructure
DeskMate Advanced (only after Baseline Gate B4)
multi-expert perception -> WorldState -> FSM -> safety gate -> robot adapter

The current P0 is the official Great Cat Census: fine-tune the Ultralytics yolo26s-cls.pt whole-image classifier for Ragdoll, Singapura, Persian, Sphynx, and Pallas cat plus an internal not_target rejection output; run it on quality-gated, operator-aligned multi-scale ROIs from the live robot camera; calibrate and aggregate correlated probabilities; print only confirmed target species; and support the remotely piloted 15-minute course. Baseline does not train an object detector or implement autonomous search. Model selection, calibration, and untouched robot final testing use separate data. Advanced work is paused until the Baseline passes three complete rehearsals and its offline release is frozen.

Both phases target the local NVIDIA RTX 4070 plus CPU and must remain usable without cloud inference. Advanced reuses the Baseline's Ultralytics/PyTorch toolchain, bounded-queue frame capture, reconnect, model packaging, generic ModelRunner lifecycle, UI, telemetry, replay tests, and robot video configuration. Cat classification weights, heads, labels, datasets, thresholds, and Results.probs are not reused as detection assets.

Current Gate Status

Baseline Gate B0 is NOT PASSED. The software and data-pilot checks are complete. The requested camera profile is now 480 x 480 JPEG quality 85 at 8 FPS, upright and not mirrored, with OpenCV BGR output after decode. Two human inputs remain: one consented frame from the actual robot camera and its delivery protocol/endpoint. The exact collection steps and ownership blanks are exposed in the Phase 0 manual-action dashboard.

Gate B1 human image review is now IN PROGRESS. The latest machine audit still has 2,321 pending candidates and zero accepted images until reviewer decisions are written back. This is a separate dataset-freeze blocker, not a third Gate B0 failure.

Entry Documents

Development Workflow

From this /project root:

  1. Run git status --short --branch and audit existing dirty files.
  2. Create plan/<YYYY-MM-DD-target-name>/plan.md from the repository template.
  3. Declare owned and read-only paths before editing.
  4. Implement only the bounded target.
  5. Run target-specific validation plus git diff --check and git status --short --branch.
  6. Record the factual outcome in plan/log.md.
  7. Commit or push only when explicitly requested.

Repository Boundary

This directory is the independent chenzc24/DeskMate repository and is tracked as the project Git submodule by the containing course repository. The parent checkout remains outside this project's workflow boundary. Large datasets, downloaded model weights, private videos, and training outputs are local artifacts and must not be committed.

About

Multi-expert deep-learning and robotics demo for the NUS SoC Summer Workshop

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages