Meta tags:
description= Computer Vision
& Machine Learning
& Bio-Medical Imaging
& #DeepLearn
& Kaggle Master - Borda;
Headings (most frequently used words):
track, jirka, borovec, borda, navigation, achievements, footer, stats, block, or, report, menu, sponsoring, highlights, organizations, pinned, loading, hi, there, impact, ledger, developer, manager, academic, open, source, projects, github, kaggle, support, consulting, uh, oh,
Text of the page (most frequently used words):
and (78), the (46), for (34), #github (21), lightning (20), with (19), pytorch (16), maintainer (16), that (15), vision (15), from (15), python (14), projects (14), across (13), code (12), detection (11), training (11), ecosystem (11), you (10), support (10), source (10), more (10), yolo (9), gpu (9), your (9), repositories (9), research (9), segmentation (8), release (8), oss (8), reproducible (8), public (7), computer (7), any (7), open (7), contributor (7), team (7), all (7), tooling (7), user (7), this (6), image (6), model (6), systems (6), api (6), one (6), session (6), sponsoring (6), into (6), borda (6), not (5), community (5), security (5), while (5), delivery (5), workflows (5), rig (5), tracking (5), pipeline (5), copilot (5), kaggle (5), medical (5), imaging (5), developers (5), built (5), datasets (5), developer (5), packages (5), grade (5), block (5), reload (4), refresh (4), problem (4), clean (4), lucid (4), independent (4), synth (4), agent (4), skills (4), run (4), real (4), agents (4), pydeprecate (4), teams (4), review (4), migration (4), sponsors (4), work (4), data (4), registration (4), published (4), unlike (4), out (4), build (4), notebooks (4), tutorials (4), baseline (4), metrics (4), production (4), emeritus (4), quality (4), jirka (4), borovec (4), stars (4), overview (4), report (4), about (4), learn (4), can (3), personal (3), contact (3), status (3), please (3), page (3), nms (3), free (3), oriented (3), boxes (3), augmentation (3), compatible (3), ready (3), take (3), claude (3), affordable (3), collection (3), warnings (3), checks (3), human (3), loop (3), reproducibility (3), reliability (3), libraries (3), signature (3), practitioner (3), own (3), platform (3), actions (3), day (3), full (3), workshops (3), histological (3), anhir (3), engine (3), used (3), analysis (3), results (3), past (3), frameworks (3), litgpt (3), automatically (3), every (3), changes (3), documentation (3), instead (3), tested (3), fusion (3), thunder (3), distributed (3), classification (3), object (3), learning (3), implementations (3), fixes (3), testing (3), utilities (3), core (3), cachier (3), without (3), library (3), ships (3), torchmetrics (3), users (3), business (3), pipelines (3), papers (3), detr (3), supervision (3), sort (3), track (3), former (3), director (3), creator (3), benchmarks (3), abuse (3), https (3), follow (3), another (3), tab (3), window (3), sign (3), changelog (3), customer (3), enterprise (3), features (3), time (2), information (2), docs (2), terms (2), footer (2), navigation (2), there (2), loading (2), persists (2), room (2), reproduction (2), keypoints (2), write (2), transforms (2), geometry (2), deployed (2), codex (2), agentic (2), tests (2), coding (2), specialist (2), automated (2), optimized (2), development (2), deprecate (2), redirect (2), functions (2), classes (2), keep (2), codebase (2), compatibility (2), make (2), maintainable (2), safe (2), defaults (2), evidence (2), assisted (2), sprint (2), layers (2), repository (2), issue (2), experience (2), audit (2), sessions (2), governance (2), engineering (2), two (2), four (2), what (2), recorded (2), consulting (2), stats (2), behind (2), challenge (2), isbi (2), methods (2), accuracy (2), benchmarking (2), birl (2), cuts (2), designed (2), pyimsegm (2), uses (2), still (2), box (2), plain (2), entire (2), runs (2), against (2), before (2), they (2), ship (2), don (2), based (2), format (2), through (2), customize (2), tasks (2), flash (2), reference (2), bolts (2), shared (2), place (2), improvements (2), like (2), standard (2), automatic (2), works (2), multi (2), framework (2), thousands (2), academic (2), lets (2), large (2), zero (2), shipped (2), video (2), its (2), compose (2), coco (2), synthetic (2), scratch (2), implementation (2), paper (2), rebuilt (2), detector (2), assumptions (2), glue (2), pre (2), trackers (2), custom (2), world (2), active (2), maintain (2), long (2), term (2), reviewer (2), articles (2), technical (2), prague (2), linkedin (2), leadership (2), led (2), applied (2), automation (2), reviews (2), organizer (2), reliable (2), friendly (2), infra (2), medium (2), 926 (2), 136 (2), note (2), will (2), add (2), content (2), achievements (2), com (2), shepherd (2), signed (2), universe (2), integrations (2), stories (2), center (2), products (2), secret (2), perform, action, share, manage, cookies, privacy, 2026, inc, was, error, something, went, wrong, try, again, check, execute, fewer, resampling, passes, harness, nvidia, hardware, pennies, triggered, label, powered, modal, serverlesss, archive, assistant, configurations, smoothly, smart, auto, routing, maintaining, backward, pinned, sell, generic, adoption, help, testable, style, cards, workflow, setup, adapter, fixture, evaluation, gaps, versioning, strategy, deprecation, policy, notes, lifecycle, structure, process, flow, maintenance, risk, health, priced, bought, tiers, areas, polyglot, estates, supply, chain, half, package, site, programme, prices, useful, consider, who, funded, dipy, ultralytics, yolov5, notable, contributions, other, grand, which, brought, together, worldwide, compare, automates, running, evaluating, using, expert, annotated, landmarks, alignment, complete, developed, during, combining, superpixels, graph, region, growing, multiple, studies, tissue, raw, final, opinionated, working, llms, gpt, llama, mistral, heavyweight, abstraction, making, easy, modify, part, getting, performance, hackable, safety, net, catches, ensuring, hundreds, dependent, break, upgrade, breaking, candidate, nightly, downstream, test, suites, official, powering, script, heavy, converting, cpu, tpu, ensure, example, actually, executable, tutorial, delivers, inference, kernel, operator, optimization, memory, management, opaque, compilers, provides, transparent, inspect, composable, plugins, cuda, graphs, quantization, pythonic, faster, compiler, made, simple, few, lines, text, tabular, let, practitioners, idea, minutes, hours, transfer, driven, vaes, gans, simclr, give, researchers, battle, command, extend, their, experiments, reproduce, baselines, foundation, keeps, consistent, extracts, common, patterns, cli, propagate, packaging, helpers, even, machines, ideal, caching, expensive, computations, calls, processing, supports, backends, handling, cached, stay, fresh, manual, invalidation, staleness, file, mongodb, functools, lru_cache, solving, surprisingly, hard, computing, correct, regression, nlp, retrieval, accumulation, just, setups, device, synchronization, 100, most, widely, adopted, labs, fortune, 500, companies, eliminates, same, laptop, 000, cluster, bridging, gap, between, prototypes, boilerplate, scaling, created, partially, supervise, born, pain, managing, tool, authors, rename, get, clear, silent, breakage, call, forwarding, dependency, execution, layer, calibrated, maintainers, control, plugin, describe, operational, outcome, need, images, turns, task, definition, success, gate, recommendation, checking, recommending, limits, acceptance, stays, decision, sentinel, halves, building, generates, torch, fixed, seeds, configurable, scenes, increasing, difficulty, convergence, tensor, first, ordinary, numeric, ranges, warps, samples, once, color, collapses, matrix, beta, drop, replacement, native, lut, matrices, albumentations, torchvision, kornia, repeated, interpolation, fused_transforms, synth_datasets, formerly, fuse, augmentations, instance, keypoint, described, equations, existing, point, where, stop, short, written, down, each, trained, tier, numbers, head, measures, cost, stated, teaching, artifact, explicitly, smoke, scale, weights, numbered, yolo26, plug, play, anything, outputs, bounding, original, wrapped, forks, integrates, natively, wiring, tuned, parameters, benchmarked, mot, detections, bot, bytetrack, new, brings, level, speeds, stands, matching, beating, state, art, being, straightforward, fine, tune, complex, anchor, tuning, hacks, needed, transformer, plugging, specific, tools, providing, filtering, annotating, chaining, operations, would, otherwise, require, unified, transformers, toolkit, spans, always, aiming, enjoyable, organized, ieee, tmi, tcia, major, international, conferences, icip, accv, miccai, journal, conference, czech, university, certified, leading, change, practical, foundations, years, driving, broader, mentored, contributors, scaled, engagement, ensured, cross, coordination, cycles, feature, roadmaps, startup, now, defunct, delivered, prototype, kendaxa, manager, competitions, problems, strong, focus, commit, hooks, contributed, reports, create, several, use, precisely, are, efforts, turning, ideas, durable, facing, interfaces, evolution, practice, writing, explainer, histology, researcher, author, discipline, llm, infrastructure, releases, agnostic, adapters, examples, roboflow, contribution, role, artifacts, area, impact, ledger, turn, apis, background, readme, behavior, reporting, maximum, 250, characters, include, such, legal, names, email, addresses, only, visible, optional, owned, account, closed, close, issues, pull, requests, discussions, opened, must, logged, prevent, interacting, sending, notifications, blocking, organizations, pro, program, member, highlights, jborovec, www, jirkaborovec, orcid, org, 0000, 0001, 7437, 824x, following, 348, followers, machine, bio, deeplearn, master, sponsor, message, dismiss, alert, switched, accounts, appearance, settings, search, pricing, event, talks, next, partners, company, forum, events, webinars, blog, resource, connect, resources, premium, advanced, ons, trust, insights, why, evaluate, see, industries, government, manufacturing, financial, services, healthcare, industry, nonprofits, startups, enterprises, stage, businesses, latest, trending, repos, explore, certifications, scanning, leak, prevention, protection, vulnerability, remediation, secure, cloud, environments, codespaces, enforcement, hosting, collaboration, menu, skip,
Text of the page (random words):
hub status company about partners changelog github universe github universe the event for developers by developers talks workshops and what s next for github pricing search sign in sign up appearance settings you signed in with another tab or window reload to refresh your session you signed out in another tab or window reload to refresh your session you switched accounts on another tab or window reload to refresh your session dismiss alert message borda follow overview repositories 136 projects 0 packages 0 stars 926 sponsoring 1 more overview repositories projects packages stars sponsoring borda follow oss shepherd jirka borovec borda oss shepherd follow sponsor computer vision machine learning bio medical imaging deeplearn kaggle master 4 1k followers 348 following prague https orcid org 0000 0001 7437 824x linkedin in jirka borovec https www kaggle com jirkaborovec https medium com jborovec sponsoring achievements x2 x4 x4 x3 achievements x2 x4 x4 x3 highlights developer program member pro organizations block or report user block or report borda block user prevent this user from interacting with your repositories and sending you notifications learn more about blocking users you must be logged in to block users close all issues pull requests and discussions opened by this user content in all repositories owned by your account will be closed add an optional note maximum 250 characters please don t include any personal information such as legal names or email addresses this note will only be visible to you block user report abuse contact github support about this user s behavior learn more about reporting abuse report abuse overview repositories 136 projects 0 packages 0 stars 926 sponsoring 1 more overview repositories projects packages stars sponsoring borda readme md hi there i m jirka borovec open source ml cv systems maintainer i turn research grade computer vision and pytorch workflows into reliable python libraries reproducible benchmarks clean apis and contributor friendly maintainer systems background ph d in medical imaging former director of oss at lightning ai and long term practitioner across ml frameworks cv tooling and reproducible research impact ledger area artifacts my role contribution signature computer vision systems supervision rf detr trackers maintainer in the roboflow cv ecosystem model agnostic detection segmentation tracking adapters examples reliability own cv research tooling lucid yolo vision synth vision delivery creator maintainer from scratch detector reproduction with recorded assumptions synthetic datasets augmentation fusion agent ready cv delivery skills pytorch ecosystem emeritus pytorch lightning torchmetrics former director of oss emeritus maintainer training infrastructure distributed metrics oss governance releases pytorch ecosystem past core lightning utilities bolts flash thunder tutorials ecosystem ci litgpt core maintainer contributor shared infra reference implementations tutorials ci tooling llm tooling maintainer tooling github ai rig pydeprecate affordable gpu ci cachier creator maintainer defaults agents api migration ci reliability release discipline medical imaging benchmarks anhir birl pyimsegm researcher organizer library author histology registration segmentation benchmarking reproducibility community applied ml kaggle medium tutorials reviews practitioner explainer reviewer reproducible notebooks ml practice public technical writing i use creator maintainer contributor emeritus maintainer and organizer precisely large ecosystem projects are team efforts my signature is turning research grade ideas into durable tested user facing python systems reliable interfaces reproducible benchmarks safe api evolution and contributor friendly maintainer infra ️ developer track create maintain several open source python packages used by thousands of developers contributed code ci cd pipelines issue reports reviews across the ml ecosystem strong focus on testing automation and developer experience from pre commit hooks to github actions kaggle contributor across notebooks competitions and datasets applied ml on real world problems with published reproducible work manager track built and led a team at kendaxa startup now defunct delivered a video analysis platform from prototype to production former director of open source at lightning ai led the oss team for 3 years driving feature roadmaps release cycles and cross team coordination across pytorch lightning torchmetrics and the broader lightning ecosystem mentored contributors scaled community engagement and ensured quality across 10 active repositories linkedin learning certified in leadership foundations leadership practical skills and leading your team through change academic track ph d in medical imaging czech technical university in prague 15 journal articles 20 conference papers isbi icip accv miccai workshops reviewer for ieee tmi tcia and major international conferences co organized the anhir challenge on histological image registration open source projects long term open source contributor and maintainer my work spans ml frameworks developer tooling and computer vision always aiming to make research more reproducible and engineering more enjoyable active projects i maintain ️ supervision the go to python toolkit for plugging any detection or segmentation model into real world cv pipelines unlike framework specific tools it works with yolo transformers or any custom model out of the box providing a unified api for tracking filtering annotating and chaining operations that would otherwise require glue code rf detr a new take on real time object detection that brings transformer accuracy to yolo level speeds stands out by matching or beating state of the art on coco while being straightforward to fine tune on custom datasets no complex anchor tuning or nms hacks needed trackers plug and play multi object tracking for any detection model yolo detr or anything that outputs bounding boxes ships clean room implementations of sort bytetrack oc sort and bot sort rebuilt from the original papers not wrapped forks integrates natively with supervision detections for zero glue wiring with pre tuned parameters benchmarked across four standard mot datasets lucid yolo independent from scratch pytorch lightning implementation of the detection instance segmentation oriented detection and keypoint methods described in the yolo26 paper rebuilt from the published equations without consulting any existing implementation every point where the papers stop short is written down as one of 73 numbered assumptions and each trained tier ships the run behind its numbers the nms free head measures a 1 11 ap cost against the paper s stated 0 6 0 8 a teaching artifact and research baseline explicitly not a production detector smoke scale training no weights shipped ️ vision synth formerly fuse augmentations two independent halves for building and testing cv training pipelines synth_datasets generates reproducible torch free synthetic datasets in coco or yolo format for detection segmentation oriented boxes and keypoints fixed seeds configurable scenes increasing difficulty for convergence checks fused_transforms is a tensor first augmentation engine that cuts repeated interpolation write the pipeline as ordinary independent transforms kornia torchvision albumentations or plain numeric ranges and compatible geometry matrices compose so a run of warps samples the image once while compatible color collapses into one matrix or lut beta a fusion engine not a drop in replacement for native compose ️ vision delivery agent ready computer vision skills that take you from a business problem to a deployed model shipped as the sentinel plugin for claude code and codex describe the operational outcome you need from images or video it turns that into a task definition success gate baseline and go no go recommendation checking a baseline before recommending training evidence is published with its limits and production acceptance stays a human decision ai rig execution layer for ai assisted maintainer workflows specialist agents for code review release audit and human in the loop quality checks built to keep agents calibrated and maintainers in control ️ pydeprecate born from the pain of managing api changes in large libraries like pytorch lightning a zero dependency tool that lets library authors deprecate rename and redirect functions or classes with automatic call forwarding so users get clear migration warnings instead of silent breakage emeritus maintainer projects i co created and still partially supervise pytorch lightning the most widely adopted framework for scaling pytorch used by thousands of teams from academic labs to fortune 500 companies eliminates training loop boilerplate and lets the same code run on a laptop gpu or a 10 000 gpu cluster without changes bridging the gap between research prototypes and production systems torchmetrics the standard metrics library for the pytorch ecosystem solving the surprisingly hard problem of computing correct metrics in distributed training ships 100 metrics for classification regression nlp and retrieval all with automatic accumulation and device synchronization that just works across multi gpu setups ️ cachier unlike functools lru_cache cachier persists results across sessions and even across machines ideal for caching expensive computations like api calls or data processing supports mongodb and file based backends with built in staleness handling so cached results stay fresh without manual invalidation past core maintainer projects ️ lightning utilities the shared foundation that keeps all lightning projects consistent and maintainable extracts common patterns packaging helpers testing utilities cli tooling and ci cd workflows into one place so that fixes and improvements propagate across the entire ecosystem automatically lightning bolts a community driven collection of reference implementations vaes gans simclr and more built on pytorch lightning designed to give researchers battle tested baselines they can reproduce in one command and extend for their own experiments lightning flash made transfer learning as simple as a few lines of code across 15 tasks image classification object detection text classification tabular data and more built on pytorch lightning it let practitioners go from idea to baseline in minutes instead of hours ️ lightning thunder a source to source compiler for pytorch that delivers up to 40 faster training and inference through kernel fusion operator optimization and gpu memory management unlike opaque compilers thunder provides a transparent pythonic ir that developers can inspect and customize with composable plugins for distributed training quantization and cuda graphs lightning tutorials the official tutorial collection powering the pytorch lightning documentation uses a script based format instead of heavy notebooks automatically converting to executable notebooks with full reproducibility tracking ci tested across cpu gpu and tpu to ensure every example actually runs ecosystem ci the safety net for the entire lightning ecosystem automatically runs downstream test suites against every nightly build and release candidate catches breaking changes before they ship ensuring that hundreds of dependent projects don t break on upgrade day litgpt an opinionated hackable codebase for working with 20 llms gpt llama mistral and more unlike heavyweight frameworks litgpt uses plain pytorch with no abstraction layers making it easy to modify any part of the training pipeline while still getting optimized performance out of the box past research projects ️ pyimsegm a complete image segmentation pipeline developed during ph d research combining superpixels graph cuts and region growing for medical imaging used in multiple published studies on histological tissue analysis and designed to be reproducible from raw data to final results birl the benchmarking engine behind the anhir grand challenge at isbi which brought together teams worldwide to compare image registration methods on histological data automates the full pipeline from running registration to evaluating alignment accuracy using expert annotated landmarks notable contributions to other projects ultralytics yolov5 dipy and more github stats kaggle stats support consulting if my open source work is useful consider sponsoring me who sponsors and what it funded is recorded in sponsors md team workshops practitioner sessions on your own repositories github platform governance actions for polyglot estates supply chain security in ci agentic engineering with claude code copilot one session half day full day a two session package on site in the eu or a four session programme prices and terms in support md signature support areas priced in support md bought as tiers on github sponsors oss health audit repository structure ci release process docs issue pr flow contributor experience and maintenance risk api lifecycle migration sprint versioning strategy deprecation policy migration warnings compatibility layers tests and release notes for python libraries computer vision pipeline reliability sprint detection segmentation tracking adapter fixture evaluation and reproducibility gaps in cv systems ai assisted maintainer workflow setup github defaults ai rig style review workflows release checks pr evidence cards and human in the loop review for python ml oss teams i do not sell generic ai adoption i help teams make ml repositories maintainable testable and release safe pinned loading pydeprecate pydeprecate public smoothly deprecate and redirect python functions classes with smart warnings and auto routing keep your codebase clean while maintaining backward compatibility python 64 8 ai rig ai rig public a collection of personal ai coding assistant configurations specialist agents and automated workflows optimized for python and ml open source development python 31 4 affordable gpu ci affordable gpu ci public archive run gpu tests on real nvidia hardware for pennies triggered by a github pr label powered by modal s serverlesss python 6 vision delivery vision delivery public agent ready computer vision skills that take you from problem to deployed model claude code codex and any agentic harness python 5 vision synth vision synth public write image augmentation as independent transforms execute compatible geometry with fewer resampling passes python 8 lucid yolo lucid yolo public clean room pytorch lightning reproduction of yolo nms free for detection segmentation oriented boxes and keypoints python 6 1 something went wrong please refresh the page to try again if the problem persists check the github status page or contact support uh oh there was an error while loading please reload this page footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal information you can t ...
|