//hella derpy but I think a good start for first times using the program. hella nice program//
Paper: https://arxiv.org/pdf/1703.06870.pdf
FB really likes detecting things. I went with their PyTorch version. The matterport version didn’t work out of the box, so went with FB’s code to try image segmentation.
Caffe2 version: https://github.com/facebookresearch/Detectron
PyTorch version: https://github.com/facebookresearch/Detectron2
Matterport’s version: https://github.com/matterport/Mask_RCNN
Deep Learning based Image Segmentation with OpenCV: https://www.pyimagesearch.com/2018/11/26/instance-segmentation-with-opencv/
https://engineering.matterport.com/splash-of-color-instance-segmentation-with-mask-r-cnn-and-tensorflow-7c761e238b46
Also Watershed algorithm is available in OpenCV:
Watershed: http://www.cmm.mines-paristech.fr/~beucher/wtshed.html
Segmenting an image by the watershed transformation is therefore a two-step process:
* Finding the markers and the segmentation criterion (the criterion or function which will be used to split the regions – it is most often the contrast or gradient, but not necessarily). * Performing a marker-controlled watershed with these two elements. |
SLIDE
CPU beating GPU. Lol NVIDIA. SELL! SELL!
https://news.rice.edu/2020/03/02/deep-learning-rethink-overcomes-major-obstacle-in-ai-industry/
arxiv: https://arxiv.org/pdf/1903.03129.pdf
Conclusion:
We provide the first evidence that a smart algorithm with
modest CPU OpenMP parallelism can outperform the best
available hardware NVIDIA-V100, for training large deep
learning architectures. Our system SLIDE is a combination
of carefully tailored randomized hashing algorithms with
the right data structures that allow asynchronous parallelism.
We show up to 3.5x gain against TF-GPU and 10x gain
against TF-CPU in training time with similar precision on
popular extreme classification datasets. Our next steps are to
extend SLIDE to include convolutional layers. SLIDE has
unique benefits when it comes to random memory accesses
and parallelism. We anticipate that a distributed implementation of SLIDE would be very appealing because the
communication costs are minimal due to sparse gradients.
It was a simple life, being a shredder. Well, not the actual shredder; they have machines to do that now. My profession was to wait for the babies to hatch and throw all the hours-old squealing boys into the gnashing jaws of the shredding device. You see it takes a bit more money to raise a boy, as they don’t suffer from the fat, juicy tenderness and hyper-fertility that only an overload of synthetic bio-chemicals can provoke in the girls. Not much more money, but these little squealing fluffy yellow ping pong balls with vestigial wings are what the Capatriarchal bosses called “economically unviable entities”. I can relate, in a way. I used to work on an Outside Farm, where I would tend to orchards of cloned oranges, decipher the needs of transgenic maize and pollinate almond trees. But, they have machines to do that now.
As clever and strong as they are, it’s hard for the average industrial machine to tell the difference between boy and girl chicks, so I’d use my multi million-year evolved vision and the advanced tactile response mechanisms of my nimble fingers to differentiate and toss them as fast as I could, for fear of becoming economically univiable, into the machine, and at the end of the month I could pay my Shelter Fee to the Capatriarchalists, and every night I’d have food on my table. Usually rice, and some vegetables, and beans for protein, because meat was too expensive. And I couldn’t stand the smell of chicken after spending all that time handling the tepid strawberry milkshake-like puree of chicks, plucking out clumped meshes of minikin feathers so we could sell it in vats to the pig factory at the best price per litre.
These comforts became threatened when the robots were released. It started a few batteries away. My friends told me that Rainbow Chickens & co. got shut down, because some robot appeared one day and set all the chickens free. I laughed. But the muscles in my friends’ faces had flatlined. The robot seemed hard-wired to protect the chickens at whatever cost, and the workers, the gun-laden security guards and all the cages and fences proved no match for the aggressively dexterous and intelligent machine.
The Rainbow Chickens and their robot roamed around the outskirts of the city. Watching the vernacular video of the odd codependency, which got a couple thousand virtual hearts on The Citizen’s Channel, we could never have imagined our routine and whole way of life could be disrupted by this artificial symbiosis. But it was when the next generation hatched that things became inescapably peculiar; the first being the chicks saw when cracking through their chalky shells was an aluminium arm, riddled with bolts glinting in the sunlight, with the warm hum of servo motors mumbling in unison with the delicate tending to of the egg. In an act of evolutionary misguidance, the chicks presumed this being was their mother and imprinted on the machine. Some kind of feedback loop was created between the ever-evolving artificial intelligence and the fast-adapting chicks, and their resulting behaviours were unintelligible to the human mind. For one, the machine took over the task of incubating the eggs which opened up a lot of time for hens to pursue other endeavours, which we could only comprehend to be cultural activities.
As the flock grew, so did hierarchical tensions, leading to social unrest and violence within the group. It became apparent that a split was necessary, yet the newly afforded freedoms that came with the robot complexified this natural process. The AI quantified that the only way to solve this was to mechanically clone itself. Stored somewhere on its SD card was the memory of other robots used to handle chickens, although techno-evolutionarily misguided ones. Components from automated feeders, roaming faeces vacuums, incubators, mechanical deboners, boy chick shredders, and factory climate control units were gently dismantled and reassembled into as-similar-as-possible robots. The need for more parts meant going to more battery farms, which in turn also meant more chickens being released. The rate of liberation was exponential, and before we had even taken the peculiar situation seriously, the system keeping our daily lives in check had begun to unravel.
With their nutritionally diverse menus of scraps and incandescent warmth, many flocks migrated to urban spaces, causing a surprising amount of inconvenience for the normative city functionings. For one, they seemed very drawn to the tar roads, as the asphalt soaked up the sun’s heat and the gravel debris was a popular digestive aid to be pecked at. Attempts to drive through the encampments were futile; between a mass of angry talons and an advanced AI that could hack any device within eighty metres, cars and trucks were abandoned and only small, non-motorised transportation was possible when navigating the city. People who worked far from home lost their jobs. Inter-city trade fell apart. Store shelves became barren. The smog cleared, and the sky was blue and brilliant for the first time in two hundred and fifty years.
***
For bakeries to survive, parking lots were transformed into emergency flax farms. Cosmetic and biotechnology companies had to produce expensive lab-grown albumen for their products. Wine became murkier. Cinema houses became overrun by broods of plumage and pistons, due to their pre-existing bulk maize-cooking technology. The inconvenience and discomfort experienced by movie-goers led to a gradual deterioration of interest in the stereotype-perpetuating Capatriarchal-issued movies, while citizens sought consolatory media which more sensitively reflected the changes they were experiencing in their daily lives.
As a result of the chickens’ extensive urban roaming, seeds in neat packages of faecal fertiliser were distributed in ruderal landscapes across cities. Tomatoes, berries, corn, lemons – whatever genetically unmodified fresh produce still had viable seeds inside – began sprouting in traffic islands, in dog-walking parks, between cracks in cement pavements. Municipalities’ urban cleaning departments were ordered to remove these “weeds”, these unexpected, uncurated nourishing invasives, but the human residents began to protest. Never before had they had access to such fresh, organically-grown produce, which was of course also free, and easily harvestable on their commute home. Those who had lost their jobs in the rippling chaos, like myself, had grown dependent on these impromptu, decentralised farms. Along with the fresh, unfertilised eggs which the robots would cautiously leave on the edges of pathways, the nutritional requirements of many urban human residents were being met free of charge.
The financial devastation to many multi-million Zoplar industries was of course met with bureaucratic rage within the Capatriarchalist structure, and a rogue hacktivist group called the Technowitches were tracked down as being responsible. They had caught them via their digital footprint, with the picture created by their Virtual Value transactions, search terms used when accessing Digital Information Archives, keywords in personal messaging communications, and blatant disrespect for the Capatriarchalist system evident in all of their Community Media posts over the last decade. They had triangulated on these clues, which led them directly to the Shelter Fee collector the hacktivists were registered with.
The Technowitches were indefinitely detained on the grounds of treason and disrupting public order, until they could terminate the anarchic devices. Even in duressed collaboration with the authorities’ top digital scientists, this proved seemingly impossible; the artificial intelligence had evolved autonomously and the Capatriarchalist’s weaponised technology was rendered useless against the metallic creatures.
At some point the Capatriarchalist / Technowitch saga faded from the digital newspapers, as we tried to adapt and get on with our lives. Now I spend my days making sure the farms in my neighbourhood are all running smoothly, teaching my neighbours about the patience you need when working with living organisms as most of them only know how to interact with pixels and trackpads, which don’t talk back. I like to flex my nimble fingers separating grains from chaff, at whatever speed relates to how much bread I’d like from the bakery before they close for the night, and it is a simple life.
In the uncertain times, in the thick of the system’s crisis, it was less simple; we were working night and day to keep the water supplies consistent after they cut off the pipes to our neighbourhood. We would have to manually collect, filter, distill and treat the water, keeping it in a closed cycle to waste as little as possible. It was a stressful and exhausting time. But, we have machines to do that now.
Diegetic Prototype
Egg-protecting Robot
Made with chicken bones from the trash (v. nice prototyping material)
flash notes on text
aka some thoughts on a speculative fiction about chicken-protecting robots
non-anthropocentric robotic laws | Digital Colonialism
find-and-replace-game-civil-laws-robotics-eu-chickened.pdf
Can also be listened to hear ( well like 3/4 of it)
Radomir Strikes Again!
https://hackaday.io/project/9065-tote-zero
https://bitbucket.org/thesheep/tote0/downloads/
and, using an adafruit “feather” board, but I dunno maybe interesting at some point https://bitbucket.org/thesheep/circuitpython-spiderwing/src/default/python/
Raspberry Pi Powered Quadruped
Samira PeirisPublished January 25, 2019 © GPL3+
A four-legged robot imbued with the power of deep learning.
https://www.hackster.io/yasaspeiris/raspberry-pi-powered-quadruped-bbb68b
Free 3D embeds?
test oof
(dan says: seems to have ad splash screen)
mrnda meets rpi
+ pca9685
https://learn.adafruit.com/16-channel-pwm-servo-driver/python-circuitpython
https://learn.adafruit.com/adafruits-raspberry-pi-lesson-6-using-ssh/enabling-ssh
https://github.com/adafruit/Adafruit_CircuitPython_ServoKit
https://learn.adafruit.com/circuitpython-on-raspberrypi-linux
https://learn.adafruit.com/adafruits-raspberry-pi-lesson-4-gpio-setup/adafruit-pi-code
https://github.com/adafruit/Adafruit_CircuitPython_PCA9685/tree/master/examples
https://learn.adafruit.com/circuitpython-on-raspberrypi-linux/pwm-outputs-servos
https://github.com/adafruit/Adafruit_CircuitPython_PCA9685
https://cdn-learn.adafruit.com/downloads/pdf/adafruit-16-channel-servo-driver-with-raspberry-pi.pdf
https://circuitpython.readthedocs.io/projects/pca9685/en/latest/index.html
+Misc
aka what is Computors
https://www.lifewire.com/uses-of-command-cd-2201063
+PYTHON
aka snakes or something idk I`m not a programmer
https://www.guru99.com/learn-python-main-function-with-examples-understand-main.html