Draw together with a neural network

Source: Internet
Author: User
Tags neural net

Try the SKETCH-RNN demo.

For mobile users on a cellular data connection:the the size of this the is around 5 MB of data. Everytime you to the "model in the" demo, you'll use another 5 MB of data.

We made an interactive Web experiment This lets you draw together with a recurrent neural network model called SKETCH-RNN. We taught this neural net to draw by training it in millions of doodles collected from the Quick, draw! Game. Once you start drawing an object, Sketch-rnn'll come up with many possible ways to continue drawing the this object based on where you are off. Try the "the".

In the above demo, your are instructed to start drawing a particular object. Once you stop doodling, the neural network takes over and attempts to guess the rest of the Your. You can take over drawing again and continue where to left. We trained around models can choose to experiment with, and some models the are on trained multiple. Other sketch-rnn Demos

The demos below are best experienced on a desktop browser, rather on a mobile than. multi-prediction

Multiple predict Demo

The demo is similar to the "the" "predicts" the rest of your drawing. In this version, you'll draw the beginning of a sketch inside the "area" and the model'll predict the rest Of the drawing inside the smaller boxes on the right. This way can be a variety of different endings predicted by the model. The predicted endings sometimes feel expected, sometimes unexpected and weird, and also can sometimes is hideous and total Ly wrong.

can also choose different categories to get the "model to draw" different objects based on the same incomplete Sketch, to get the model to draw things like square cats, or circular trucks. Can always interrupt the model and continue working on your drawing inside the "area" on the left, and have the Model Co Ntinually predict where you are off afterwards.

This is my firetruck. There are many like it, but this one is mine.

Since The model is trained on a dataset of How other people Doodle, we also found it interesting to Deliberat Ely draw in a way this is different compared to the model's predictions to help with we own mental search process for Nov Elty, and not conform to the masses. Try The multi Predict demo. interpolation

Interpolation Demo

In addition to predicting the rest of a incomplete drawing, sketch-rnn is also able To morph from One drawing to another drawing. In The interpolation Demo, you can get the model to randomly generate two images using the Two randomize bu Ttons on the sides of the. After hitting The interpolate! button in the middle, the model would come up with new drawings that it believes t o be the interpolation between the two original drawings. In the image above, the model interpolates between a bicycle and a yoga position. Try The interpolation demo to morph between two randomly generated. variational Auto-encoder

variational autoencoder Demo

The model can also mimic your drawings and produce similar. In the variational autoencoder Demo, you are are to draw a complete drawing of a specified object. After you draw a complete sketch inside the "area" to the left, hit the Auto-encode button and the model'll start drawing Similar sketches inside the smaller boxes on the right. Rather than drawing a perfect duplicate copy of your drawing, the model would try to mimic your the drawing.

You can experiment drawing objects this are not the category you are supposed to draw, and the model interprets yo ur drawing. For example, try to draw a cat, and have a model trained to draw crabs generate cat-like. Try the variational autoencoder demo. Want to learn more?

If you are want to learn more about what are going on, here are a few pointers to explore:

Google Search blog post about this model.

Read Our paper A neural representation of Sketch drawings.

Earlier magenta blog post about the TensorFlow implementation of this model. GitHub repo.

JavaScript implementation of this model along with pre-trained model weights. GitHub repo.

Original address: Https://magenta.tensorflow.org/sketch-rnn-demo

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.