Meta tags:
description=Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there s more! (An implementation of Semantic Style Transfer.) - alexjc/neural-doodle;

Headings (most frequently used words):

it, uh, oh, navigation, to, saved, searches, neural, doodle, filter, and, files, installation, footer, image, gpu, is, optimization, an, this, want, search, code, repositories, users, issues, pull, requests, provide, feedback, alexjc, menu, use, your, results, more, quickly, folders, latest, commit, history, repository, examples, usage, setup, troubleshooting, problems, frequent, questions, about, releases, packages, contributors, languages, analogy, style, transfer, texture, synthesis, script, parameters, using, docker, recommended, manual, optional, running, out, of, ram, throwing, memoryerror, help, how, much, being, used, doesn, seem, very, fast, can, install, or, unable, find, pgen, not, compiling, formal, grammar, notimplementederror, abstractconv2d, theano, failed, typeerror, max_pool_2d, got, unexpected, keyword, argument, mode, valueerror, unknown, locale, utf, error, the, diverged, nans, were, encountered, when, will, be, possible, in, realtime, as, there, application, for, download, topics, resources, license, stars, watchers, forks,

Text of the page (most frequently used words):
the (98), you (46), and (41), this (35), style (29), image (24), doodle (22), your (21), can (20), for (20), with (19), samples (17), #neural (16), use (15), from (13), run (13), code (13), docker (13), #transfer (12), gpu (12), png (12), github (11), there (11), python3 (11), cpu (11), security (10), fix (10), setup (10), output (10), more (9), install (9), using (9), all (9), networks (8), script (8), seed (8), that (7), python (7), reload (7), semantic (7), have (7), how (7), see (7), need (7), also (7), content (7), view (7), time (6), not (6), but (6), are (6), quality (6), images (6), installed (6), nvidia (6), device (6), source (6), installation (6), alexjc (6), files (6), noise (6), jpg (6), iterations (6), enterprise (6), navigation (5), was (5), error (5), page (5), repository (5), license (5), deep (5), into (5), generate (5), another (5), want (5), synthesis (5), will (5), which (5), pip (5), requirements (5), txt (5), lasagne (5), theano (5), features (5), without (5), system (5), memory (5), cuda (5), environment (5), folder (5), examples (5), weight (5), input (5), seth (5), search (5), perform (4), community (4), while (4), loading (4), please (4), readme (4), resources (4), two (4), textures (4), one (4), based (4), take (4), requests (4), project (4), real (4), possible (4), platform (4), try (4), command (4), dev (4), running (4), used (4), should (4), ram (4), default (4), advanced (4), frames (4), file (4), available (4), algorithm (4), wall (4), phases (4), uses (4), target (4), gogh (4), results (4), actions (4), support (4), docs (3), stars (3), topics (3), turn (3), bit (3), doodles (3), example (3), implementation (3), about (3), services (3), too (3), make (3), realtime (3), texture (3), resolution (3), libraries (3), were (3), terminal (3), way (3), than (3), these (3), get (3), found (3), network (3), called (3), find (3), column (3), under (3), like (3), save (3), better (3), work (3), out (3), help (3), pyvenv (3), pre (3), simply (3), here (3), following (3), alias (3), its (3), every (3), match (3), patches (3), parameters (3), size (3), annotations (3), photo (3), gpu0 (3), portrait (3), _sem (3), renoir (3), monet (3), new (3), read (3), commit (3), name (3), open (3), insights (3), pull (3), signed (3), settings (3), tab (3), window (3), refresh (3), session (3), sign (3), saved (3), documentation (3), feedback (3), grade (3), copilot (3), solutions (3), explore (3), manage (2), footer (2), shell (2), packages (2), tags (2), forks (2), 893 (2), agpl (2), fine (2), artworks (2), seamless (2), photos (2), upscaling (2), wait (2), provide (2), takes (2), application (2), download (2), focus (2), when (2), filter (2), frequent (2), questions (2), disable (2), optimizations (2), mode (2), bug (2), compiler (2), clear (2), issue (2), optimization (2), utf (2), may (2), change (2), startup (2), once (2), instance (2), bash_rc (2), directly (2), versions (2), rather (2), older (2), required (2), argument (2), sudo (2), apt (2), libblas (2), extension (2), compute (2), multiple (2), scripts (2), parallel (2), first (2), correctly (2), set (2), then (2), tool (2), very (2), main (2), improve (2), version (2), cudnn (2), card (2), software (2), troubleshooting (2), put (2), same (2), delete (2), dependencies (2), create (2), local (2), commands (2), osx (2), linux (2), well (2), optional (2), now (2), any (2), above (2), pwd (2), current (2), directory (2), access (2), easiest (2), built (2), layers (2), type (2), options (2), range (2), pattern (2), only (2), case (2), specify (2), johnson (2), what (2), look (2), synthesize (2), masks (2), both (2), cases (2), coastline (2), neuraldoodle (2), hours (2), even (2), twice (2), rendering (2), below (2), usage (2), annotation (2), they (2), skills (2), 2016 (2), workflow (2), rst (2), gitignore (2), 122 (2), commits (2), last (2), message (2), menu (2), projects (2), archive (2), appearance (2), cancel (2), searches (2), repositories (2), issues (2), business (2), developer (2), customer (2), devops (2), app (2), action, share, personal, information, cookies, contact, status, privacy, terms, 2026, inc, languages, contributors, releases, report, watching, watchers, activity, generation, manipulation, processing, learning, many, online, basic, twitter, facebook, bot, web, interface, forgeries, queue, patient, deepforger, designed, ideal, training, capable, precomputed, markovian, generative, adversarial, perceptual, losses, super, feed, forward, stylized, related, algorithms, shown, willing, accept, slightly, lower, flag, safe, underlying, has, been, reported, macos, capitan, prevent, diverged, nans, encountered, export, lc_all, en_us, seems, misconfigured, compatible, treats, locales, other, alternatively, valueerror, unknown, locale, specified, alternatives, don, typeerror, max_pool_2d, got, unexpected, keyword, libopenblas, happens, expressions, cannot, evaluated, raising, exception, notimplementederror, abstractconv2d, failed, cython3, cython, missing, inproperly, getting, package, manager, unable, pgen, compiling, formal, grammar, check, smi, dmon, third, utilitazition, fourth, increase, allocated, sure, variables, reinstall, everything, regularly, gradient, calculations, offloaded, monitoring, looks, something, much, being, doesn, seem, fast, consumption, library, allows, convolutional, faster, space, good, ideally, 2gb, 4gb, still, 8gb, 12gb, larger, resolutions, does, fallback, since, likely, throwing, memoryerror, problems, after, virtual, vgg19, 80mb, done, just, trained, scikit, venv, site, bin, activate, ignore, module, bash, active, afterward, fetching, expert, windows, mac, intermediate, requires, numerical, computing, wide, detailed, instructions, follow, scipy, numpy, manual, instead, comes, host, machine, zshrc, console, expose, mount, visualization, easy, automatically, able, downloand, line, hub, recommended, frequently, often, log, statistics, stdout, print, path, smoothing, scheme, smoothness, global, semantics, 3_1, 4_1, relative, configure, full, list, control, parameter, depends, 512x512, 128, 192, 255, second, lighter, darker, synthesizing, bitmap, anotations, follows, regular, rename, maps, originally, concept, kyle, mcdonald, sethasgogh, goghasseth, vincent, van, would, reference, given, lines, map, loaded, filename, matches, notice, little, some, rotational, variations, could, arch, outline, particular, landscape, scene, around, lake, painting, painted, analogies, call, hashtag, post, included, execute, analogy, already, variable, speed, improvements, minimal, omp_num_threads, 12h, hardware, runs, assuming, enough, board, process, complete, minutes, iteration, count, lets, performance, thanks, creative, join, vienna, july, nucl, conference, important, making, skill, adjusted, adjust, values, modify, data, practice, reach, almost, realistic, iterate, ask, advice, note, generates, three, four, inputs, depending, trying, original, extracts, annotated, incrementally, transfers, them, over, closely, borrow, artists, masterpieces, champandard, motivation, watch, inspiration, video, depth, article, items, history, latest, date, folders, branches, master, additional, star, fork, must, notification, notifications, public, archived, owner, jan, 2021, dismiss, alert, switched, accounts, resetting, qualifiers, our, query, quickly, submit, include, email, address, contacted, piece, seriously, syntax, tips, users, jump, pricing, premium, add, ons, powered, collections, trending, program, accelerator, maintainer, lab, programs, fund, developers, sponsors, partners, trust, center, forum, ebooks, reports, events, webinars, stories, development, topic, industries, government, manufacturing, financial, healthcare, industry, devsecops, modernization, nonprofits, startups, small, medium, teams, enterprises, company, marketplace, changelog, blog, why, stop, leaks, before, start, secret, protection, secure, build, vulnerabilities, changes, review, plan, track, instant, environments, codespaces, automate, workflows, integrate, external, tools, mcp, registry, direct, agents, merge, write, creation, toggle, skip,

Text of the page (random words):
doodles into fine artworks with deep neural networks generate seamless textures from photos transfer style from one image to another perform example based upscaling but wait there s more an implementation of semantic style transfer github skip to content navigation menu toggle navigation sign in appearance settings platform ai code creation github copilot write better code with ai github copilot app direct agents from issue to merge mcp registry new integrate external tools developer workflows actions automate any workflow codespaces instant dev environments issues plan and track work code review manage code changes application security github advanced security find and fix vulnerabilities code security secure your code as you build secret protection stop leaks before they start explore why github documentation blog changelog marketplace view all features solutions by company size enterprises small and medium teams startups nonprofits by use case app modernization devsecops devops ci cd view all use cases by industry healthcare financial services manufacturing government view all industries view all solutions resources explore by topic ai software development devops security view all topics explore by type customer stories events webinars ebooks reports business insights github skills support services documentation customer support community forum trust center partners view all resources open source community github sponsors fund open source developers programs security lab maintainer community accelerator github stars archive program repositories topics trending collections enterprise enterprise solutions enterprise platform ai powered developer platform available add ons github advanced security enterprise grade security features copilot for business enterprise grade ai features premium support enterprise grade 24 7 support pricing search or jump to search code repositories users issues pull requests search clear search syntax tips provide feedback we read every piece of feedback and take your input very seriously include my email address so i can be contacted cancel submit feedback saved searches use saved searches to filter your results more quickly name query to see all available qualifiers see our documentation cancel create saved search sign in sign up appearance settings resetting focus 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 this repository was archived by the owner on jan 2 2021 it is now read only alexjc neural doodle public archive notifications you must be signed in to change notification settings fork 893 star 9 8k code pull requests 3 actions projects security and quality 0 insights additional navigation options code pull requests actions projects security and quality insights alexjc neural doodle master branches tags go to file code open more actions menu folders and files name name last commit message last commit date latest commit history 122 commits 122 commits docker docker docs docs samples samples gitignore gitignore license license readme rst readme rst docker cpu df docker cpu df docker gpu df docker gpu df doodle py doodle py requirements txt requirements txt view all files repository files navigation readme agpl 3 0 license more items neural doodle use a deep neural network to borrow the skills of real artists and turn your two bit doodles into masterpieces this project is an implementation of semantic style transfer champandard 2016 based on the neural patches algorithm li 2016 read more about the motivation in this in depth article and watch this workflow video for inspiration the doodle py script generates a new image by using one two three or four images as inputs depending what you re trying to do the original style and its annotation and a target content image optional with its annotation a k a your doodle the algorithm extracts annotated patches from the style image and incrementally transfers them over to the target image based on how closely they match note making a neuraldoodle is a skill the parameters in the script were adjusted to work well by default and with the examples below for new images you may need to adjust values and modify on your input data too it takes practice but you can reach almost photo realistic results if you iterate ask for advice here or see examples examples usage installation troubleshooting frequent questions important this project is possible thanks to the nucl ai conference on creative ai july 18 20 join us in vienna 1 examples usage the main script is called doodle py which you can run with python 3 4 see setup below the device argument that lets you specify which gpu or cpu to use for the samples above here are the performance results gpu rendering assuming you have cuda setup and enough on board ram the process should complete in 3 to 8 minutes even with twice the iteration count cpu rendering this will take hours and hours even up to 12h on older hardware to match quality it d take twice the time do multiple runs in parallel the default is to use cpu if you have nvidia card setup with cuda already try gpu0 on the cpu you can also set environment variable to omp_num_threads 4 but we ve found the speed improvements to be minimal 1 a image analogy the algorithm is built for style transfer but can also generate image analogies that we call a neuraldoodle use the hashtag if you post your images example files are included in the samples folder execute with these commands synthesize a coastline as if painted by monet this uses _sem png masks for both images python3 doodle py style samples monet jpg output samples coastline png device cpu iterations 40 generate a scene around a lake in the style of a renoir painting python3 doodle py style samples renoir jpg output samples landscape png device gpu0 iterations 80 notice the renoir results look a little better than the monet some rotational variations of the source image could improve the quality of the arch outline in particular 1 b style transfer if you want to transfer the style given a source style with annotations and a target content image with annotations you can use the following command lines in all cases the semantic map is loaded and used if it s found under the _sem png filename that matches the input file synthesize a portrait of seth johnson like a gogh portrait this uses _sem png masks for both images python3 doodle py style samples gogh jpg content samples seth png output sethasgogh png device cpu phases 4 iterations 40 generate what a photo of vincent van gogh would look like using seth s portrait as reference python3 doodle py style samples seth jpg content samples gogh png output goghasseth png device gpu0 phases 4 iterations 80 to perform regular style transfer without semantic annotations simply delete or rename the files with the semantic maps the photo is originally by seth johnson and the concept for this style transfer by kyle mcdonald 1 c texture synthesis for synthesizing bitmap textures you only need an input style without anotations and without target output in this case you simply specify one input style image and the output file as follows first synthesis uses a darker noise pattern as seed python3 doodle py style samples wall jpg output wall png seed noise seed range 0 128 iterations 50 phases 3 second synthesis uses a lighter noise pattern as seed python3 doodle py style samples wall jpg output wall png seed noise seed range 192 255 iterations 50 phases 3 you can also control the output resolution using output size 512x512 parameter which also depends on the memory you have available by default the size will be the same as the style image 1 d script parameters you can configure the algorithm using the following parameters type python3 doodle py help for the full list of options or see the source code style weight 50 0 weight of style relative to content style layers 3_1 4_1 the layers to match style patches semantic weight 1 0 global weight of semantics vs features smoothness 1 0 weight of image smoothing scheme seed noise seed image path noise or content print every 10 how often to log statistics to stdout save every 10 how frequently to save png into frames 2 installation setup 2 a using docker image recommended the easiest way to get up and running is to install docker then you should be able to downloand and run the pre built image using the docker command line tool find out more about the alexjc neural doodle image on its docker hub page the easiest way to run the script from the docker image is to setup an easy access command called doodle this will automatically mount the frames folder from current directory into the instance for visualization expose the samples folder from the current directory so the script can access files this is how you can do it in your terminal console on osx or linux setup the alias put this in your bash_rc or zshrc file so it s available at startup alias doodle docker run v pwd samples nd samples v pwd frames nd frames it alexjc neural doodle now run any of the examples above using this alias without the py extension doodle help if you want to run on your nvidia gpu you can instead use the image alexjc neural doodle gpu which comes with cuda and cudnn pre installed in the image see the scripts in docker sh for how to setup your host machine advanced 2 b manual installation optional this project requires python 3 4 and you ll also need numpy and scipy numerical computing libraries as well as python3 dev installed system wide if you want more detailed instructions follow these linux installation of lasagne intermediate mac osx installation of lasagne advanced windows installation of lasagne expert afterward fetching the repository you can run the following commands from your terminal to setup a local environment create a local environment for python 3 x to install dependencies here python3 m venv pyvenv system site packages if you re using bash make this the active version of python source pyvenv bin activate setup the required dependencies simply using the pip module python3 m pip install ignore installed r requirements txt after this you should have scikit image theano and lasagne installed in your virtual environment you ll also need to download this pre trained neural network vgg19 80mb and put it in the same folder as the script to run once you re done you can just delete the pyvenv folder 3 troubleshooting problems it s running out of gpu ram throwing memoryerror help you ll need a good nvidia card with cuda to run this software on gpu ideally 2gb 4gb or better still 8gb to 12gb for larger resolutions the code does work on cpu by default so use that as fallback since you likely have more system ram to improve memory consumption you can also install nvidia s cudnn library version 3 0 or 4 0 this allows convolutional neural networks to run faster and save space in gpu ram fix use device cpu to use main system memory how much gpu is being used it doesn t seem very fast first make sure cuda is installed correctly and environment variables are set then reinstall theano if everything is setup correctly the gpu should be used regularly as the gradient calculations are offloaded if you run nvidia s monitoring tool it looks something like this the third column is the utilitazition of compute resources and the fourth column is the use of memory if memory is under used you can increase resolution if compute is under allocated too you can try running multiple scripts in parallel fix run nvidia smi dmon and check the sm column can t install or unable to find pgen not compiling formal grammar there s a python extension compiler called cython and it s missing or inproperly installed try getting it directly from the system package manager rather than pip fix sudo apt get install cython3 notimplementederror abstractconv2d theano optimization failed this happens when you re running without a gpu and the cpu libraries were not found e g libblas the neural network expressions cannot be evaluated by theano and it s raising an exception fix sudo apt get install libblas dev libopenblas dev typeerror max_pool_2d got an unexpected keyword argument mode you need to install lasagne and theano directly from the versions specified in requirements txt rather than from the pip versions these alternatives are older and don t have the required features fix python3 m pip install r requirements txt valueerror unknown locale utf 8 it seems your terminal is misconfigured and not compatible with the way python treats locales you may need to change this in your bash_rc or other startup script alternatively this command will fix it once for this shell instance fix export lc_all en_us utf 8 error the optimization diverged and nans were encountered it s possible there s a platform bug in the underlying libraries or compiler which has been reported on macos el capitan it s not clear how to fix it but you can try to disable optimizations to prevent the bug see issue 8 fix use safe mode flag to disable optimizations 4 frequent questions q when will this be possible in realtime i want it as filter related algorithms have shown this is possible in realtime if you re willing to accept slightly lower quality texture networks feed forward synthesis of textures and stylized images perceptual losses for real time style transfer and super resolution precomputed real time texture synthesis with markovian generative adversarial networks this project is not designed for real time use the focus is on quality the code in this repository is ideal for training realtime capable networks q is there an application for this i want to download it there are many online services that provide basic style transfer with neural networks we run deepforger a twitter facebook bot with web interface that can take your requests too it takes time to make forgeries so there s a queue be patient about turn your two bit doodles into fine artworks with deep neural networks generate seamless textures from photos transfer style from one image to another perform example based upscaling but wait there s more an implementation of semantic style transfer topics deep neural networks deep learning image processing image manipulation image generation resources readme license agpl 3 0 license uh oh there was an error while loading please reload this page activity stars 9 8k stars watchers 1 watching forks 893 forks report repository releases 1 tags packages 0 uh oh there was an error while loading please reload this page uh oh there was an error while loading please reload this page contributors uh oh there was an error while loading please reload this page languages python 96 3 shell 3 7 footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal in...