Skip to content
View fcakyon's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.

Highlights

  • Pro

Organizations

@ultralytics

Block or report fcakyon

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fcakyon/README.md

Follow me for more!
        

about me

  • Spending less time writing code, more time understanding the Psychiatry of AI | my claude & codex settings
  • Passionate about open-source, explainable vision-language models, ai agents for dataset curation
  • PhD in Informatics (explainable content moderation & agentic dataset curation)
  • BSc and MSc in Engineering (sequence models & computer vision)

some of my open-source works:

claude-codex-settings claude-codex-settings stars

sahi sahi stars Downloads

safetext safetext stars Downloads

balanced-loss balanced-loss stars Downloads

streamlit-image-comparison streamlit-image-comparison stars Downloads

labelme2coco labelme2coco stars Downloads

midv500 midv500 stars Downloads

yolov5-pip yolov5 stars Downloads

ultralyticsplus ultralyticsplus stars Downloads

video-transformers video-transformers stars Downloads

craft-text-detector craft stars Downloads

autollm autollm stars Downloads

some of my published/preprint papers:

Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection (ICIP, 2022) (600+ citations)

AI-supported web application for reducing polypharmacy side effects (Frontiers in Medicine, 2023) (40+ citations)

Automated question generation and question answering from Turkish texts (SCI Journal, 2022) (20+ citations)

Evaluating generative AI tools in analyzing medical articles (JMIR, 2024) (10+ citations)

Drone-vs-Bird Detection Challenge at IEEE AVSS2021 (AVSS, 2021) (200+ citations)

Instagram Fake and Automated Account Detection (INISTA, 2019) (100+ citations)

Track Boosting and Synthetic Data Aided Drone Detection (AVSS, 2021) (30+ citations)

State-of-the-Art in Nudity Classification: A Comparative Analysis (ICASSP, 2023) (10+ citations)

Deep Architectures for Content Moderation and Movie Content Rating (Preprint) (10+ citations)

Enhancing clinical management skills through artificial intelligence simulated patients (WONCA, 2024)

Pinned Loading

  1. claude-codex-settings claude-codex-settings Public

    My personal Claude Code and OpenAI Codex setup with battle-tested skills, commands, hooks, agents and MCP servers that I use daily.

    Python 394 39

  2. obss/sahi obss/sahi Public

    Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

    Python 5.1k 724

  3. content-moderation-deep-learning content-moderation-deep-learning Public

    Deep learning based content moderation from text, audio, video & image input modalities.

    387 24

  4. viddexa/moderators viddexa/moderators Public

    One package to moderate them all

    Python 5

  5. viddexa/safetext viddexa/safetext Public

    Fast profanity word, curse word, swear word, bad word filtering tool for English, Spanish, Chinese, Turkish and more.

    Python 47 7

  6. small-object-detection-benchmark small-object-detection-benchmark Public

    icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors

    Python 189 22