WebDNN:Web浏览器上最快的DNN执行框架

时间:2022-03-09 14:58:51

WebDNN:Web浏览器上最快的DNN执行框架

为什么需要WebDNN?

深层神经网络(DNN)在许多应用中受到越来越多的关注。 然而,它需要大量的计算资源,并且有许多巨大的过程来设置基于执行环境的硬件加速,如 GPGPU。 因此,为终端用户提供DNN应用非常困难。

WebDNN通过使用Web浏览器作为无安装的 DNN 执行框架来解决此问题。 该框架优化了经过训练的DNN模型,以压缩模型数据并加快执行速度,并使用新颖的JavaScript API(如WebAssembly和WebGPU)执行,以实现零开销执行。 实证评估显示,其实现了超过200倍的加速。

Why is WebDNN needed?

Deep neural network (DNN) is getting much attention to use in many applications. However, it requires a lot of computational resources, and there are many tremendous processes to setup execution environment based hardware acceleration such as GPGPU. Therefore providing DNN applications to end-users is very hard.

WebDNN solves this problem by using web browser as installation-free DNN execution framework. This framework optimizes trained DNN model to compress the model data and accelerate the execution, and executes it with novel JavaScript API such as WebAssembly and WebGPU to achieve zero-overhead execution. Empirical evaluations showed that it achieved more than 200x acceleration.

github:

https://github.com/mil-tokyo/webdnn

tensorflownews

http://www.tensorflownews.com/