Skip to content

All projects

Research Platform

Garment Type Classification Vision AI

A CNN classifier and data pipeline for apparel categories whose definitions differ from storefront to storefront

category classification accuracy
90%+
images used to train the model on a single RTX 2080
32,474

What it does

  • I trained a CNN on 32,474 crawled images with a single RTX 2080.
  • I wrote the Python pipeline that does the vector-comparison data cleansing and post-processing.

Stack

Python TensorFlow Keras CNN

Skills demonstrated

  • Product & Full-stack

    TypeScript · JavaScript · Python · C/C++ · C# · Java · Next.js · Nuxt.js · Vue.js · React · React Native · Expo · PostgreSQL · Supabase · AWS · GCP · Docker · UX design for ERP, CRM and LMS operational screens

  • Research Methodology & Benchmarking

    Pre-registered hypotheses, rejection thresholds and the commit hash at registration · Paired statistical tests implemented directly (McNemar · Fisher · Wilcoxon · Holm-Bonferroni) · Same-arm controls to establish the noise floor; pooled replicates to test whether significance reproduces · Blinded LLM judge panels, false-negative controls, and deterministic scoring with no judge · Adversarial refutation rounds; null results and failures to reproduce on the public record; do-not-re-propose lists · Public benchmarks measured first-hand: SWE-bench · MuSiQue · DP-Bench · OmniDocBench

Recognised in