Fast Neural Style

TensorFire runs neural networks in the browser using WebGL  #MachineLearning

  • TensorFire is a library that runs neural networks in the browser.
  • TensorFire mobile is not quite ready for prime-time, but here’s a video of how this demo would look:

    If possible please open this page in a desktop browser!

This is a demo app showing off TensorFire’s ability to run the style-transfer neural network in your browser as fast as CPU TensorFlow on a desktop.

@algoritmic: TensorFire runs neural networks in the browser using WebGL #MachineLearning

TensorFire is a library that runs neural networks in the browser.

TensorFire mobile is not quite ready for prime-time, but here’s a video of how this demo would look:

If possible please open this page in a desktop browser!

This is a demo app showing off TensorFire’s ability to run the style-transfer neural network in your browser as fast as CPU TensorFlow on a desktop.

You can learn more about TensorFire and what makes it fast (spoiler: WebGL) on the Project Page.

You can also sign up to get notified when we publish new demos or launch.

We won’t spam you or give your email to third parties.

TensorFire is developed by Kevin Kwok, Guillermo Webster, Anish Athalye, and Logan Engstrom.

Fast Neural Style